Token |
|
Token ID | 198 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
burn | +0.006 |
blowing | +0.005 |
waving | +0.005 |
spinning | +0.004 |
driveway | +0.004 |
Neg logit contributions | |
ounces | -0.010 |
izards | -0.009 |
bors | -0.009 |
affe | -0.009 |
hell | -0.009 |
Token | " |
Token ID | 1 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
ounces | +0.016 |
ils | +0.014 |
affe | +0.014 |
izards | +0.014 |
bors | +0.014 |
Neg logit contributions | |
burn | -0.013 |
blowing | -0.012 |
waving | -0.012 |
neighborhood | -0.010 |
spinning | -0.010 |
Token | WHAT |
Token ID | 32971 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
ounces | +0.080 |
ils | +0.072 |
izards | +0.071 |
bors | +0.071 |
affe | +0.071 |
Neg logit contributions | |
burn | -0.057 |
blowing | -0.052 |
waving | -0.051 |
spinning | -0.045 |
driveway | -0.044 |
Token | ARE |
Token ID | 15986 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
ounces | +0.160 |
bors | +0.144 |
affe | +0.137 |
ils | +0.135 |
izards | +0.134 |
Neg logit contributions | |
burn | -0.100 |
waving | -0.086 |
blowing | -0.080 |
my | -0.078 |
window | -0.075 |
Token | YOU |
Token ID | 7013 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
ounces | +0.179 |
bors | +0.155 |
affe | +0.155 |
ils | +0.149 |
ious | +0.148 |
Neg logit contributions | |
burn | -0.155 |
waving | -0.143 |
blowing | -0.140 |
spinning | -0.137 |
daddy | -0.135 |
Token | DO |
Token ID | 8410 |
Feature activation | +9.23e+00 |
Pos logit contributions | |
ounces | +0.150 |
izards | +0.130 |
bors | +0.130 |
affe | +0.129 |
ils | +0.128 |
Neg logit contributions | |
burn | -0.103 |
waving | -0.093 |
blowing | -0.093 |
spinning | -0.080 |
leaning | -0.079 |
Token | ING |
Token ID | 2751 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
ounces | +0.291 |
bors | +0.243 |
ils | +0.229 |
izards | +0.225 |
affe | +0.223 |
Neg logit contributions | |
burn | -0.230 |
waving | -0.212 |
blowing | -0.206 |
vac | -0.202 |
window | -0.200 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
ounces | +0.097 |
izards | +0.086 |
ils | +0.085 |
hell | +0.082 |
bors | +0.081 |
Neg logit contributions | |
burn | -0.078 |
waving | -0.066 |
blowing | -0.065 |
crying | -0.061 |
daddy | -0.060 |
Token | Mom |
Token ID | 11254 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
ounces | +0.097 |
ils | +0.089 |
affe | +0.088 |
izards | +0.087 |
bors | +0.087 |
Neg logit contributions | |
burn | -0.048 |
waving | -0.043 |
blowing | -0.043 |
daddy | -0.037 |
spinning | -0.036 |
Token | yells |
Token ID | 42675 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
burn | +0.094 |
blowing | +0.083 |
waving | +0.078 |
driveway | +0.073 |
neighborhood | +0.073 |
Neg logit contributions | |
ounces | -0.089 |
izards | -0.082 |
ils | -0.080 |
affe | -0.077 |
bors | -0.076 |
Token | . |
Token ID | 13 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
ounces | +0.128 |
ils | +0.115 |
bors | +0.115 |
affe | +0.113 |
izards | +0.112 |
Neg logit contributions | |
burn | -0.075 |
waving | -0.069 |
blowing | -0.067 |
crying | -0.062 |
spinning | -0.059 |
Token | could |
Token ID | 714 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
blowing | +0.018 |
burn | +0.017 |
waving | +0.017 |
crying | +0.014 |
leaning | +0.014 |
Neg logit contributions | |
ounces | -0.039 |
izards | -0.036 |
bors | -0.035 |
affe | -0.035 |
ils | -0.035 |
Token | see |
Token ID | 766 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
burn | +0.040 |
blowing | +0.037 |
waving | +0.036 |
spinning | +0.032 |
crying | +0.031 |
Neg logit contributions | |
ounces | -0.071 |
ils | -0.064 |
bors | -0.064 |
izards | -0.063 |
affe | -0.063 |
Token | lots |
Token ID | 6041 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
ounces | +0.060 |
bors | +0.055 |
affe | +0.055 |
izards | +0.055 |
ils | +0.053 |
Neg logit contributions | |
burn | -0.031 |
waving | -0.031 |
blowing | -0.031 |
my | -0.027 |
leaning | -0.026 |
Token | of |
Token ID | 286 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
ounces | +0.103 |
bors | +0.095 |
ils | +0.094 |
izards | +0.094 |
affe | +0.091 |
Neg logit contributions | |
blowing | -0.065 |
waving | -0.062 |
burn | -0.059 |
spinning | -0.055 |
shining | -0.053 |
Token | av |
Token ID | 1196 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
ounces | +0.020 |
izards | +0.018 |
affe | +0.018 |
ils | +0.018 |
bors | +0.018 |
Neg logit contributions | |
blowing | -0.015 |
burn | -0.015 |
waving | -0.014 |
neighborhood | -0.013 |
spinning | -0.013 |
Token | oc |
Token ID | 420 |
Feature activation | +7.75e+00 |
Pos logit contributions | |
ounces | +0.057 |
izards | +0.051 |
bors | +0.048 |
ils | +0.048 |
ily | +0.047 |
Neg logit contributions | |
burn | -0.129 |
blowing | -0.123 |
waving | -0.120 |
my | -0.117 |
neighborhood | -0.115 |
Token | ados |
Token ID | 22484 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ounces | +0.116 |
izards | +0.113 |
bors | +0.108 |
hell | +0.105 |
isy | +0.104 |
Neg logit contributions | |
burn | -0.281 |
blowing | -0.269 |
waving | -0.266 |
leaning | -0.261 |
neighborhood | -0.252 |
Token | that |
Token ID | 326 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
ounces | +0.095 |
bors | +0.087 |
affe | +0.087 |
izards | +0.084 |
ils | +0.084 |
Neg logit contributions | |
blowing | -0.051 |
burn | -0.051 |
waving | -0.050 |
spinning | -0.041 |
leaning | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
blowing | +0.014 |
burn | +0.013 |
waving | +0.013 |
daddy | +0.012 |
my | +0.011 |
Neg logit contributions | |
ounces | -0.028 |
izards | -0.025 |
affe | -0.025 |
bors | -0.025 |
ils | -0.024 |
Token | supplier |
Token ID | 22693 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
burn | +0.021 |
waving | +0.019 |
blowing | +0.019 |
neighborhood | +0.017 |
daddy | +0.017 |
Neg logit contributions | |
ounces | -0.028 |
ils | -0.026 |
izards | -0.026 |
bors | -0.025 |
affe | -0.025 |
Token | had |
Token ID | 550 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
ounces | +0.028 |
bors | +0.026 |
izards | +0.025 |
affe | +0.025 |
ils | +0.025 |
Neg logit contributions | |
waving | -0.016 |
burn | -0.016 |
blowing | -0.015 |
my | -0.015 |
daddy | -0.014 |
Token | I |
Token ID | 40 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
ounces | +0.021 |
ils | +0.019 |
izards | +0.019 |
hell | +0.018 |
affe | +0.018 |
Neg logit contributions | |
burn | -0.011 |
blowing | -0.010 |
waving | -0.009 |
my | -0.009 |
neighborhood | -0.008 |
Token | will |
Token ID | 481 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
burn | +0.013 |
blowing | +0.012 |
waving | +0.012 |
driveway | +0.011 |
spinning | +0.010 |
Neg logit contributions | |
ounces | -0.015 |
affe | -0.013 |
ils | -0.013 |
izards | -0.013 |
hell | -0.013 |
Token | buy |
Token ID | 2822 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
burn | +0.022 |
blowing | +0.020 |
waving | +0.019 |
neighborhood | +0.018 |
driveway | +0.018 |
Neg logit contributions | |
ounces | -0.027 |
ils | -0.024 |
affe | -0.023 |
bors | -0.023 |
izards | -0.023 |
Token | more |
Token ID | 517 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
ounces | +0.046 |
affe | +0.046 |
bors | +0.044 |
isy | +0.044 |
izards | +0.043 |
Neg logit contributions | |
grandma | -0.027 |
waving | -0.026 |
daddy | -0.025 |
burn | -0.025 |
my | -0.024 |
Token | av |
Token ID | 1196 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
ounces | +0.027 |
bors | +0.026 |
ils | +0.025 |
affe | +0.025 |
izards | +0.025 |
Neg logit contributions | |
waving | -0.016 |
burn | -0.016 |
blowing | -0.015 |
spinning | -0.014 |
window | -0.014 |
Token | oc |
Token ID | 420 |
Feature activation | +7.70e+00 |
Pos logit contributions | |
ounces | +0.073 |
izards | +0.069 |
bors | +0.065 |
ily | +0.062 |
ils | +0.061 |
Neg logit contributions | |
burn | -0.140 |
my | -0.129 |
blowing | -0.127 |
waving | -0.123 |
neighborhood | -0.119 |
Token | ados |
Token ID | 22484 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
izards | +0.112 |
ounces | +0.111 |
hell | +0.105 |
isy | +0.103 |
bors | +0.102 |
Neg logit contributions | |
burn | -0.287 |
blowing | -0.265 |
waving | -0.263 |
leaning | -0.259 |
my | -0.250 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ounces | +0.147 |
bors | +0.141 |
affe | +0.131 |
ils | +0.130 |
izards | +0.128 |
Neg logit contributions | |
burn | -0.061 |
blowing | -0.058 |
waving | -0.058 |
my | -0.052 |
daddy | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
ounces | +0.036 |
bors | +0.033 |
izards | +0.033 |
ils | +0.032 |
affe | +0.032 |
Neg logit contributions | |
burn | -0.026 |
blowing | -0.024 |
waving | -0.024 |
my | -0.022 |
daddy | -0.021 |
Token | You |
Token ID | 921 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
burn | +0.015 |
waving | +0.014 |
my | +0.013 |
daddy | +0.013 |
grandma | +0.013 |
Neg logit contributions | |
ils | -0.026 |
ounces | -0.025 |
hell | -0.024 |
bors | -0.024 |
izards | -0.023 |
Token | can |
Token ID | 460 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
ounces | +0.104 |
bors | +0.102 |
izards | +0.096 |
ils | +0.095 |
isy | +0.095 |
Neg logit contributions | |
burn | -0.038 |
my | -0.038 |
daddy | -0.034 |
only | -0.033 |
turn | -0.033 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
burn | +0.005 |
blowing | +0.005 |
waving | +0.005 |
seat | +0.004 |
ric | +0.004 |
Neg logit contributions | |
ils | -0.008 |
ounces | -0.008 |
affe | -0.008 |
isy | -0.008 |
ily | -0.008 |
Token | would |
Token ID | 561 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
waving | +0.070 |
burn | +0.068 |
blowing | +0.063 |
driveway | +0.060 |
spinning | +0.059 |
Neg logit contributions | |
ils | -0.134 |
ounces | -0.129 |
affe | -0.125 |
isy | -0.124 |
ily | -0.123 |
Token | bake |
Token ID | 28450 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
burn | +0.038 |
blowing | +0.034 |
waving | +0.033 |
neighborhood | +0.030 |
driveway | +0.030 |
Neg logit contributions | |
ounces | -0.045 |
ils | -0.041 |
bors | -0.040 |
affe | -0.040 |
hell | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
ounces | +0.047 |
affe | +0.044 |
bors | +0.041 |
izards | +0.041 |
ocket | +0.039 |
Neg logit contributions | |
burn | -0.029 |
blowing | -0.026 |
waving | -0.025 |
daddy | -0.023 |
my | -0.023 |
Token | fresh |
Token ID | 4713 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
ounces | +0.016 |
izards | +0.014 |
ils | +0.014 |
bors | +0.014 |
affe | +0.014 |
Neg logit contributions | |
burn | -0.013 |
waving | -0.012 |
blowing | -0.012 |
daddy | -0.011 |
spinning | -0.010 |
Token | batch |
Token ID | 15458 |
Feature activation | +7.66e+00 |
Pos logit contributions | |
ounces | +0.018 |
izards | +0.017 |
bors | +0.016 |
ils | +0.016 |
affe | +0.016 |
Neg logit contributions | |
burn | -0.013 |
blowing | -0.011 |
waving | -0.011 |
my | -0.010 |
spinning | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ounces | +0.306 |
bors | +0.285 |
affe | +0.271 |
cod | +0.264 |
ns | +0.263 |
Neg logit contributions | |
blowing | -0.112 |
burn | -0.111 |
waving | -0.098 |
crying | -0.088 |
my | -0.087 |
Token | cookies |
Token ID | 14746 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ounces | +0.064 |
izards | +0.060 |
affe | +0.060 |
bors | +0.057 |
ocket | +0.055 |
Neg logit contributions | |
burn | -0.041 |
waving | -0.039 |
blowing | -0.039 |
grandma | -0.037 |
daddy | -0.037 |
Token | for |
Token ID | 329 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
ounces | +0.076 |
bors | +0.070 |
affe | +0.068 |
izards | +0.067 |
hell | +0.065 |
Neg logit contributions | |
burn | -0.033 |
blowing | -0.031 |
waving | -0.029 |
my | -0.024 |
daddy | -0.024 |
Token | her |
Token ID | 607 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
ounces | +0.154 |
affe | +0.146 |
izards | +0.137 |
hell | +0.137 |
bors | +0.134 |
Neg logit contributions | |
burn | -0.071 |
blowing | -0.064 |
daddy | -0.063 |
waving | -0.060 |
grandma | -0.056 |
Token | to |
Token ID | 284 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
ounces | +0.020 |
izards | +0.019 |
bors | +0.018 |
ils | +0.018 |
affe | +0.018 |
Neg logit contributions | |
burn | -0.011 |
blowing | -0.010 |
waving | -0.010 |
daddy | -0.009 |
neighborhood | -0.008 |
Token | until |
Token ID | 1566 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ounces | +0.013 |
affe | +0.012 |
izards | +0.012 |
bors | +0.011 |
ils | +0.011 |
Neg logit contributions | |
burn | -0.007 |
blowing | -0.007 |
waving | -0.006 |
my | -0.006 |
spinning | -0.006 |
Token | he |
Token ID | 339 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
ounces | +0.033 |
affe | +0.032 |
izards | +0.031 |
ils | +0.031 |
bors | +0.031 |
Neg logit contributions | |
burn | -0.024 |
blowing | -0.023 |
waving | -0.022 |
daddy | -0.021 |
spinning | -0.020 |
Token | had |
Token ID | 550 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
ounces | +0.090 |
affe | +0.084 |
bors | +0.083 |
izards | +0.083 |
hell | +0.081 |
Neg logit contributions | |
burn | -0.037 |
blowing | -0.034 |
waving | -0.032 |
daddy | -0.028 |
spinning | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
ounces | +0.024 |
affe | +0.023 |
izards | +0.022 |
bors | +0.022 |
ils | +0.022 |
Neg logit contributions | |
burn | -0.012 |
blowing | -0.011 |
waving | -0.010 |
spinning | -0.009 |
daddy | -0.009 |
Token | delicious |
Token ID | 12625 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
burn | +0.005 |
blowing | +0.005 |
waving | +0.005 |
my | +0.004 |
neighborhood | +0.004 |
Neg logit contributions | |
ounces | -0.006 |
hell | -0.006 |
affe | -0.006 |
isy | -0.005 |
ils | -0.005 |
Token | batch |
Token ID | 15458 |
Feature activation | +7.48e+00 |
Pos logit contributions | |
ounces | +0.058 |
ils | +0.052 |
affe | +0.051 |
bors | +0.050 |
hell | +0.050 |
Neg logit contributions | |
burn | -0.053 |
blowing | -0.048 |
waving | -0.048 |
neighborhood | -0.043 |
driveway | -0.042 |
Token | of |
Token ID | 286 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
bors | +0.290 |
ounces | +0.284 |
cod | +0.270 |
affe | +0.267 |
ns | +0.259 |
Neg logit contributions | |
blowing | -0.112 |
burn | -0.099 |
waving | -0.095 |
spinning | -0.087 |
holding | -0.085 |
Token | brown |
Token ID | 7586 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ounces | +0.035 |
affe | +0.034 |
izards | +0.034 |
bors | +0.032 |
hell | +0.032 |
Neg logit contributions | |
burn | -0.024 |
blowing | -0.023 |
waving | -0.023 |
daddy | -0.021 |
spinning | -0.020 |
Token | ies |
Token ID | 444 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
ounces | +0.046 |
izards | +0.046 |
affe | +0.044 |
bors | +0.043 |
ocket | +0.043 |
Neg logit contributions | |
burn | -0.039 |
blowing | -0.036 |
waving | -0.034 |
spinning | -0.032 |
window | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
ounces | +0.034 |
bors | +0.032 |
affe | +0.031 |
izards | +0.030 |
hell | +0.030 |
Neg logit contributions | |
burn | -0.016 |
blowing | -0.016 |
waving | -0.015 |
spinning | -0.013 |
leaning | -0.012 |
Token | When |
Token ID | 1649 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
ounces | +0.010 |
ils | +0.009 |
izards | +0.009 |
bors | +0.009 |
affe | +0.009 |
Neg logit contributions | |
burn | -0.005 |
waving | -0.004 |
blowing | -0.004 |
neighborhood | -0.003 |
driveway | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
ounces | +0.072 |
izards | +0.067 |
ils | +0.066 |
hell | +0.065 |
affe | +0.065 |
Neg logit contributions | |
burn | -0.059 |
blowing | -0.053 |
waving | -0.053 |
driveway | -0.048 |
neighborhood | -0.046 |
Token | brave |
Token ID | 14802 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
ounces | +0.002 |
affe | +0.002 |
isy | +0.001 |
hell | +0.001 |
bors | +0.001 |
Neg logit contributions | |
burn | -0.001 |
blowing | -0.001 |
waving | -0.001 |
driveway | -0.001 |
my | -0.001 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
ounces | +0.010 |
ils | +0.009 |
bors | +0.009 |
izards | +0.009 |
hell | +0.008 |
Neg logit contributions | |
burn | -0.006 |
waving | -0.006 |
blowing | -0.005 |
daddy | -0.005 |
spinning | -0.005 |
Token | named |
Token ID | 3706 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
ounces | +0.102 |
ils | +0.093 |
izards | +0.091 |
affe | +0.091 |
bors | +0.090 |
Neg logit contributions | |
burn | -0.101 |
blowing | -0.092 |
waving | -0.091 |
driveway | -0.082 |
spinning | -0.081 |
Token | Let |
Token ID | 3914 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ounces | +0.098 |
affe | +0.087 |
bors | +0.086 |
ils | +0.085 |
izards | +0.083 |
Neg logit contributions | |
burn | -0.058 |
waving | -0.053 |
my | -0.051 |
blowing | -0.051 |
daddy | -0.049 |
Token | icia |
Token ID | 33577 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
ounces | +0.042 |
ils | +0.037 |
izards | +0.037 |
affe | +0.037 |
bors | +0.036 |
Neg logit contributions | |
burn | -0.033 |
blowing | -0.030 |
waving | -0.029 |
spinning | -0.026 |
neighborhood | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
ounces | +0.290 |
bors | +0.258 |
affe | +0.257 |
hell | +0.256 |
izards | +0.253 |
Neg logit contributions | |
burn | -0.141 |
waving | -0.126 |
blowing | -0.122 |
daddy | -0.112 |
my | -0.111 |
Token | She |
Token ID | 1375 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ounces | +0.033 |
ils | +0.030 |
bors | +0.029 |
izards | +0.029 |
affe | +0.029 |
Neg logit contributions | |
burn | -0.018 |
waving | -0.016 |
blowing | -0.016 |
neighborhood | -0.014 |
spinning | -0.014 |
Token | lived |
Token ID | 5615 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ounces | +0.052 |
izards | +0.047 |
affe | +0.047 |
ils | +0.046 |
bors | +0.046 |
Neg logit contributions | |
burn | -0.022 |
blowing | -0.019 |
waving | -0.019 |
neighborhood | -0.016 |
spinning | -0.016 |
Token | on |
Token ID | 319 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
burn | +0.030 |
blowing | +0.026 |
waving | +0.026 |
driveway | +0.024 |
daddy | +0.023 |
Neg logit contributions | |
ounces | -0.036 |
izards | -0.035 |
ils | -0.035 |
ily | -0.033 |
hell | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
ounces | +0.058 |
ils | +0.053 |
izards | +0.052 |
affe | +0.052 |
bors | +0.052 |
Neg logit contributions | |
burn | -0.036 |
blowing | -0.032 |
waving | -0.032 |
spinning | -0.027 |
driveway | -0.027 |
Token | house |
Token ID | 2156 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
burn | +0.008 |
blowing | +0.007 |
waving | +0.006 |
spinning | +0.005 |
leaning | +0.005 |
Neg logit contributions | |
ounces | -0.019 |
ils | -0.018 |
affe | -0.017 |
bors | -0.017 |
izards | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
burn | +0.019 |
blowing | +0.016 |
waving | +0.016 |
spinning | +0.014 |
neighborhood | +0.014 |
Neg logit contributions | |
ounces | -0.029 |
ils | -0.027 |
affe | -0.026 |
hell | -0.026 |
izards | -0.026 |
Token | made |
Token ID | 925 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
burn | +0.007 |
blowing | +0.006 |
waving | +0.006 |
spinning | +0.005 |
neighborhood | +0.005 |
Neg logit contributions | |
ounces | -0.010 |
ils | -0.009 |
izards | -0.009 |
affe | -0.009 |
bors | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
ounces | +0.045 |
affe | +0.042 |
izards | +0.040 |
bors | +0.040 |
hell | +0.040 |
Neg logit contributions | |
burn | -0.026 |
blowing | -0.024 |
waving | -0.024 |
daddy | -0.023 |
crying | -0.021 |
Token | fresh |
Token ID | 4713 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
burn | +0.010 |
blowing | +0.009 |
waving | +0.008 |
driveway | +0.007 |
neighborhood | +0.007 |
Neg logit contributions | |
ounces | -0.015 |
affe | -0.014 |
hell | -0.013 |
ils | -0.013 |
bors | -0.013 |
Token | batch |
Token ID | 15458 |
Feature activation | +7.39e+00 |
Pos logit contributions | |
ounces | +0.007 |
ils | +0.006 |
affe | +0.006 |
izards | +0.006 |
bors | +0.006 |
Neg logit contributions | |
burn | -0.006 |
blowing | -0.005 |
waving | -0.005 |
spinning | -0.004 |
neighborhood | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ounces | +0.286 |
bors | +0.265 |
izards | +0.252 |
affe | +0.252 |
ns | +0.249 |
Neg logit contributions | |
blowing | -0.116 |
burn | -0.110 |
waving | -0.107 |
crying | -0.096 |
daddy | -0.094 |
Token | blue |
Token ID | 4171 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
ounces | +0.042 |
izards | +0.040 |
affe | +0.040 |
ils | +0.039 |
bors | +0.039 |
Neg logit contributions | |
burn | -0.026 |
waving | -0.026 |
blowing | -0.025 |
daddy | -0.022 |
spinning | -0.022 |
Token | berry |
Token ID | 8396 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
burn | +0.009 |
blowing | +0.008 |
waving | +0.008 |
spinning | +0.007 |
daddy | +0.007 |
Neg logit contributions | |
ounces | -0.013 |
ils | -0.012 |
izards | -0.012 |
bors | -0.012 |
affe | -0.012 |
Token | muff |
Token ID | 27563 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ounces | +0.079 |
bors | +0.074 |
izards | +0.072 |
ocket | +0.069 |
ils | +0.069 |
Neg logit contributions | |
burn | -0.049 |
blowing | -0.047 |
waving | -0.044 |
shining | -0.039 |
daddy | -0.038 |
Token | ins |
Token ID | 1040 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ounces | +0.041 |
affe | +0.040 |
bors | +0.039 |
nic | +0.037 |
ger | +0.036 |
Neg logit contributions | |
burn | -0.030 |
blowing | -0.028 |
waving | -0.025 |
my | -0.024 |
shining | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
ounces | +0.026 |
ils | +0.025 |
ily | +0.025 |
hell | +0.024 |
affe | +0.024 |
Neg logit contributions | |
burn | -0.020 |
blowing | -0.017 |
waving | -0.016 |
spinning | -0.015 |
ric | -0.015 |
Token | forgot |
Token ID | 16453 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
ounces | +0.025 |
affe | +0.023 |
izards | +0.023 |
ils | +0.023 |
bors | +0.022 |
Neg logit contributions | |
burn | -0.014 |
blowing | -0.013 |
waving | -0.013 |
daddy | -0.011 |
crying | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ounces | +0.024 |
affe | +0.022 |
bors | +0.021 |
izards | +0.021 |
ils | +0.021 |
Neg logit contributions | |
burn | -0.010 |
blowing | -0.010 |
waving | -0.010 |
crying | -0.008 |
daddy | -0.008 |
Token | buy |
Token ID | 2822 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
burn | +0.023 |
blowing | +0.020 |
waving | +0.020 |
daddy | +0.017 |
driveway | +0.017 |
Neg logit contributions | |
ounces | -0.037 |
izards | -0.034 |
affe | -0.034 |
ils | -0.034 |
bors | -0.034 |
Token | av |
Token ID | 1196 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
ounces | +0.044 |
affe | +0.040 |
bors | +0.040 |
izards | +0.040 |
isy | +0.039 |
Neg logit contributions | |
burn | -0.019 |
waving | -0.016 |
blowing | -0.016 |
my | -0.016 |
daddy | -0.016 |
Token | oc |
Token ID | 420 |
Feature activation | +7.37e+00 |
Pos logit contributions | |
ounces | +0.055 |
izards | +0.047 |
bors | +0.045 |
ils | +0.044 |
affe | +0.041 |
Neg logit contributions | |
burn | -0.126 |
blowing | -0.117 |
waving | -0.114 |
my | -0.114 |
neighborhood | -0.109 |
Token | ados |
Token ID | 22484 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
ounces | +0.113 |
izards | +0.104 |
hell | +0.102 |
bors | +0.100 |
isy | +0.099 |
Neg logit contributions | |
burn | -0.278 |
waving | -0.257 |
blowing | -0.256 |
leaning | -0.248 |
my | -0.246 |
Token | . |
Token ID | 13 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
ounces | +0.120 |
bors | +0.110 |
affe | +0.107 |
ils | +0.106 |
izards | +0.105 |
Neg logit contributions | |
burn | -0.051 |
blowing | -0.047 |
waving | -0.045 |
my | -0.040 |
daddy | -0.037 |
Token | Lily |
Token ID | 20037 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
burn | +0.011 |
blowing | +0.010 |
waving | +0.009 |
neighborhood | +0.008 |
spinning | +0.008 |
Neg logit contributions | |
ounces | -0.014 |
ils | -0.013 |
izards | -0.013 |
affe | -0.013 |
bors | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
burn | +0.016 |
blowing | +0.014 |
waving | +0.014 |
spinning | +0.012 |
driveway | +0.012 |
Neg logit contributions | |
ounces | -0.024 |
ils | -0.022 |
affe | -0.021 |
bors | -0.021 |
izards | -0.021 |
Token | sad |
Token ID | 6507 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
burn | +0.029 |
blowing | +0.024 |
waving | +0.024 |
driveway | +0.023 |
neighborhood | +0.021 |
Neg logit contributions | |
ounces | -0.034 |
izards | -0.030 |
ils | -0.030 |
ily | -0.030 |
bors | -0.029 |
Token | kitchen |
Token ID | 9592 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ounces | +0.010 |
affe | +0.009 |
ils | +0.009 |
bors | +0.009 |
hell | +0.008 |
Neg logit contributions | |
burn | -0.005 |
blowing | -0.004 |
waving | -0.004 |
spinning | -0.003 |
leaning | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
ounces | +0.047 |
ils | +0.043 |
affe | +0.042 |
hell | +0.041 |
bors | +0.041 |
Neg logit contributions | |
burn | -0.025 |
blowing | -0.021 |
waving | -0.020 |
spinning | -0.017 |
leaning | -0.016 |
Token | made |
Token ID | 925 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
burn | +0.006 |
blowing | +0.005 |
waving | +0.005 |
spinning | +0.004 |
neighborhood | +0.004 |
Neg logit contributions | |
ounces | -0.008 |
ils | -0.008 |
izards | -0.007 |
affe | -0.007 |
bors | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
ounces | +0.046 |
affe | +0.042 |
izards | +0.042 |
ils | +0.042 |
bors | +0.041 |
Neg logit contributions | |
burn | -0.033 |
blowing | -0.030 |
waving | -0.030 |
daddy | -0.027 |
crying | -0.026 |
Token | fresh |
Token ID | 4713 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
burn | +0.005 |
blowing | +0.004 |
waving | +0.004 |
leaning | +0.004 |
spinning | +0.004 |
Neg logit contributions | |
ounces | -0.006 |
affe | -0.005 |
hell | -0.005 |
bors | -0.005 |
isy | -0.005 |
Token | batch |
Token ID | 15458 |
Feature activation | +7.36e+00 |
Pos logit contributions | |
ounces | +0.013 |
affe | +0.011 |
hell | +0.011 |
ils | +0.011 |
bors | +0.011 |
Neg logit contributions | |
burn | -0.012 |
waving | -0.011 |
blowing | -0.011 |
driveway | -0.010 |
spinning | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ounces | +0.269 |
bors | +0.251 |
izards | +0.241 |
ils | +0.241 |
affe | +0.238 |
Neg logit contributions | |
blowing | -0.135 |
burn | -0.129 |
waving | -0.126 |
crying | -0.115 |
spinning | -0.108 |
Token | sa |
Token ID | 473 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ounces | +0.039 |
ils | +0.035 |
izards | +0.034 |
affe | +0.034 |
bors | +0.034 |
Neg logit contributions | |
burn | -0.040 |
blowing | -0.036 |
waving | -0.036 |
spinning | -0.032 |
neighborhood | -0.032 |
Token | us |
Token ID | 385 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
ounces | +0.054 |
izards | +0.046 |
ils | +0.046 |
bors | +0.046 |
affe | +0.046 |
Neg logit contributions | |
burn | -0.077 |
blowing | -0.071 |
waving | -0.070 |
daddy | -0.064 |
neighborhood | -0.064 |
Token | ages |
Token ID | 1095 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
ounces | +0.067 |
izards | +0.065 |
affe | +0.059 |
bors | +0.058 |
ils | +0.057 |
Neg logit contributions | |
burn | -0.112 |
blowing | -0.105 |
waving | -0.100 |
daddy | -0.100 |
crying | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
ounces | +0.093 |
bors | +0.085 |
izards | +0.085 |
affe | +0.084 |
ils | +0.084 |
Neg logit contributions | |
burn | -0.058 |
blowing | -0.054 |
waving | -0.053 |
spinning | -0.045 |
daddy | -0.045 |
Token | man |
Token ID | 582 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
burn | +0.015 |
blowing | +0.013 |
waving | +0.012 |
ric | +0.012 |
driveway | +0.012 |
Neg logit contributions | |
ounces | -0.017 |
affe | -0.017 |
hell | -0.016 |
isy | -0.016 |
bors | -0.015 |
Token | who |
Token ID | 508 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ounces | +0.005 |
affe | +0.004 |
ils | +0.004 |
izards | +0.004 |
bors | +0.004 |
Neg logit contributions | |
burn | -0.004 |
blowing | -0.003 |
waving | -0.003 |
driveway | -0.003 |
neighborhood | -0.003 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
burn | +0.043 |
blowing | +0.036 |
waving | +0.036 |
driveway | +0.034 |
spinning | +0.032 |
Neg logit contributions | |
ounces | -0.058 |
ils | -0.055 |
izards | -0.053 |
affe | -0.053 |
bors | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
burn | +0.018 |
blowing | +0.015 |
waving | +0.015 |
spinning | +0.011 |
crying | +0.011 |
Neg logit contributions | |
ounces | -0.060 |
ils | -0.055 |
affe | -0.055 |
izards | -0.055 |
bors | -0.055 |
Token | prevent |
Token ID | 2948 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
burn | +0.011 |
blowing | +0.010 |
waving | +0.010 |
spinning | +0.008 |
crying | +0.008 |
Neg logit contributions | |
ounces | -0.026 |
ils | -0.024 |
izards | -0.024 |
affe | -0.023 |
bors | -0.023 |
Token | Sof |
Token ID | 41427 |
Feature activation | +7.33e+00 |
Pos logit contributions | |
ounces | +0.099 |
affe | +0.094 |
ils | +0.091 |
hell | +0.091 |
bors | +0.089 |
Neg logit contributions | |
burn | -0.060 |
blowing | -0.055 |
waving | -0.055 |
crying | -0.049 |
spinning | -0.048 |
Token | ia |
Token ID | 544 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ounces | +0.187 |
ils | +0.156 |
bors | +0.155 |
izards | +0.145 |
affe | +0.145 |
Neg logit contributions | |
burn | -0.237 |
blowing | -0.217 |
waving | -0.211 |
my | -0.200 |
leaning | -0.193 |
Token | from |
Token ID | 422 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
ounces | +0.074 |
ils | +0.067 |
affe | +0.066 |
izards | +0.066 |
bors | +0.066 |
Neg logit contributions | |
burn | -0.050 |
blowing | -0.045 |
waving | -0.044 |
spinning | -0.039 |
crying | -0.038 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
burn | +0.010 |
driveway | +0.008 |
neighborhood | +0.007 |
waving | +0.007 |
blowing | +0.007 |
Neg logit contributions | |
ounces | -0.023 |
ils | -0.021 |
izards | -0.021 |
bors | -0.021 |
isy | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
burn | +0.046 |
waving | +0.043 |
blowing | +0.043 |
spinning | +0.040 |
crying | +0.039 |
Neg logit contributions | |
ounces | -0.113 |
affe | -0.103 |
izards | -0.101 |
bors | -0.101 |
ils | -0.100 |
Token | violin |
Token ID | 38283 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
burn | +0.006 |
ric | +0.005 |
waving | +0.005 |
bie | +0.005 |
blowing | +0.005 |
Neg logit contributions | |
ounces | -0.010 |
ils | -0.010 |
affe | -0.010 |
isy | -0.010 |
hell | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +8.88e-03 |
Pos logit contributions | |
ounces | +0.018 |
ils | +0.016 |
bors | +0.016 |
hell | +0.016 |
affe | +0.016 |
Neg logit contributions | |
burn | -0.007 |
blowing | -0.007 |
waving | -0.007 |
spinning | -0.006 |
leaning | -0.005 |
Token | Betty |
Token ID | 29504 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
ounces | +0.000 |
ils | +0.000 |
hell | +0.000 |
bors | +0.000 |
izards | +0.000 |
Neg logit contributions | |
burn | -0.000 |
blowing | -0.000 |
waving | -0.000 |
spinning | -0.000 |
shining | -0.000 |
Token | made |
Token ID | 925 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
ounces | +0.017 |
ils | +0.016 |
izards | +0.016 |
affe | +0.016 |
bors | +0.016 |
Neg logit contributions | |
burn | -0.010 |
blowing | -0.008 |
waving | -0.008 |
spinning | -0.007 |
neighborhood | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
ounces | +0.015 |
affe | +0.014 |
ils | +0.014 |
izards | +0.013 |
bors | +0.013 |
Neg logit contributions | |
burn | -0.007 |
blowing | -0.006 |
waving | -0.006 |
crying | -0.005 |
spinning | -0.005 |
Token | big |
Token ID | 1263 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
burn | +0.015 |
blowing | +0.013 |
waving | +0.013 |
driveway | +0.011 |
neighborhood | +0.011 |
Neg logit contributions | |
ounces | -0.020 |
affe | -0.019 |
hell | -0.018 |
ils | -0.018 |
isy | -0.018 |
Token | batch |
Token ID | 15458 |
Feature activation | +7.17e+00 |
Pos logit contributions | |
ounces | +0.000 |
affe | +0.000 |
ils | +0.000 |
hell | +0.000 |
bors | +0.000 |
Neg logit contributions | |
burn | -0.000 |
blowing | -0.000 |
waving | -0.000 |
driveway | -0.000 |
neighborhood | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
ounces | +0.305 |
bors | +0.281 |
ns | +0.258 |
cod | +0.257 |
affe | +0.255 |
Neg logit contributions | |
blowing | -0.108 |
waving | -0.100 |
burn | -0.100 |
crying | -0.098 |
spinning | -0.091 |
Token | butter |
Token ID | 9215 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ounces | +0.028 |
izards | +0.026 |
affe | +0.025 |
ils | +0.025 |
bors | +0.024 |
Neg logit contributions | |
burn | -0.027 |
blowing | -0.025 |
waving | -0.024 |
daddy | -0.023 |
spinning | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
ounces | +0.051 |
bors | +0.046 |
izards | +0.045 |
affe | +0.044 |
ils | +0.044 |
Neg logit contributions | |
burn | -0.027 |
blowing | -0.024 |
waving | -0.022 |
spinning | -0.019 |
my | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
ounces | +0.155 |
hell | +0.143 |
affe | +0.143 |
bridge | +0.132 |
ger | +0.132 |
Neg logit contributions | |
blowing | -0.056 |
waving | -0.054 |
burn | -0.052 |
singing | -0.047 |
spinning | -0.047 |
Token | party |
Token ID | 2151 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
ounces | +0.004 |
ils | +0.004 |
izards | +0.004 |
affe | +0.004 |
bors | +0.004 |
Neg logit contributions | |
burn | -0.003 |
blowing | -0.003 |
waving | -0.003 |
spinning | -0.002 |
neighborhood | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ounces | +0.013 |
affe | +0.012 |
ils | +0.012 |
hell | +0.011 |
bors | +0.011 |
Neg logit contributions | |
burn | -0.005 |
waving | -0.004 |
blowing | -0.004 |
spinning | -0.003 |
daddy | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
ounces | +0.004 |
ils | +0.004 |
affe | +0.004 |
hell | +0.004 |
izards | +0.004 |
Neg logit contributions | |
burn | -0.003 |
blowing | -0.002 |
waving | -0.002 |
daddy | -0.002 |
spinning | -0.002 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
burn | +0.004 |
blowing | +0.004 |
waving | +0.004 |
driveway | +0.003 |
seat | +0.003 |
Neg logit contributions | |
ounces | -0.008 |
ils | -0.008 |
affe | -0.008 |
izards | -0.008 |
isy | -0.008 |
Token | baked |
Token ID | 22979 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
burn | +0.087 |
waving | +0.079 |
blowing | +0.078 |
spinning | +0.069 |
driveway | +0.068 |
Neg logit contributions | |
ounces | -0.139 |
ils | -0.131 |
affe | -0.128 |
bors | -0.126 |
izards | -0.124 |
Token | a |
Token ID | 257 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
ounces | +0.058 |
affe | +0.053 |
izards | +0.052 |
bors | +0.052 |
ils | +0.050 |
Neg logit contributions | |
burn | -0.028 |
blowing | -0.025 |
waving | -0.024 |
daddy | -0.022 |
my | -0.021 |
Token | batch |
Token ID | 15458 |
Feature activation | +7.15e+00 |
Pos logit contributions | |
ounces | +0.004 |
affe | +0.004 |
ils | +0.004 |
hell | +0.004 |
bors | +0.004 |
Neg logit contributions | |
burn | -0.003 |
blowing | -0.003 |
waving | -0.003 |
driveway | -0.003 |
spinning | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ounces | +0.294 |
bors | +0.268 |
izards | +0.251 |
cod | +0.250 |
ns | +0.245 |
Neg logit contributions | |
burn | -0.112 |
blowing | -0.110 |
waving | -0.094 |
my | -0.090 |
daddy | -0.089 |
Token | cookies |
Token ID | 14746 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ounces | +0.051 |
izards | +0.047 |
affe | +0.046 |
bors | +0.044 |
hell | +0.044 |
Neg logit contributions | |
burn | -0.041 |
blowing | -0.039 |
waving | -0.039 |
daddy | -0.036 |
crying | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
ounces | +0.075 |
bors | +0.068 |
izards | +0.068 |
affe | +0.067 |
ils | +0.065 |
Neg logit contributions | |
burn | -0.030 |
blowing | -0.027 |
waving | -0.025 |
my | -0.021 |
daddy | -0.020 |
Token | put |
Token ID | 1234 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
ounces | +0.034 |
izards | +0.031 |
affe | +0.031 |
hell | +0.031 |
bors | +0.030 |
Neg logit contributions | |
burn | -0.023 |
blowing | -0.021 |
waving | -0.021 |
daddy | -0.019 |
my | -0.018 |
Token | them |
Token ID | 606 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
burn | +0.001 |
blowing | +0.001 |
my | +0.001 |
daddy | +0.001 |
waving | +0.001 |
Neg logit contributions | |
ounces | -0.001 |
izards | -0.001 |
affe | -0.001 |
bors | -0.001 |
isy | -0.001 |
Token | M |
Token ID | 44 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ounces | +0.031 |
izards | +0.029 |
ils | +0.028 |
hell | +0.028 |
affe | +0.028 |
Neg logit contributions | |
burn | -0.018 |
blowing | -0.018 |
waving | -0.016 |
neighborhood | -0.015 |
daddy | -0.015 |
Token | ama |
Token ID | 1689 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ounces | +0.061 |
ils | +0.057 |
hell | +0.056 |
izards | +0.056 |
bors | +0.056 |
Neg logit contributions | |
burn | -0.029 |
blowing | -0.026 |
waving | -0.025 |
daddy | -0.022 |
neighborhood | -0.021 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
burn | +0.035 |
blowing | +0.032 |
waving | +0.032 |
my | +0.026 |
daddy | +0.026 |
Neg logit contributions | |
ounces | -0.082 |
izards | -0.075 |
ils | -0.074 |
hell | -0.073 |
bors | -0.073 |
Token | , |
Token ID | 11 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
ounces | +0.004 |
hell | +0.004 |
izards | +0.004 |
affe | +0.004 |
ils | +0.004 |
Neg logit contributions | |
burn | -0.001 |
daddy | -0.001 |
blowing | -0.001 |
waving | -0.001 |
my | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
burn | +0.009 |
blowing | +0.009 |
waving | +0.009 |
spinning | +0.007 |
daddy | +0.007 |
Neg logit contributions | |
ounces | -0.016 |
ils | -0.014 |
izards | -0.014 |
affe | -0.014 |
hell | -0.014 |
Token | P |
Token ID | 47 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
ounces | +0.075 |
ils | +0.069 |
izards | +0.069 |
affe | +0.068 |
hell | +0.068 |
Neg logit contributions | |
burn | -0.042 |
blowing | -0.037 |
waving | -0.037 |
spinning | -0.031 |
neighborhood | -0.031 |
Token | apa |
Token ID | 32678 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
ounces | +0.183 |
bors | +0.177 |
hell | +0.175 |
ger | +0.174 |
ils | +0.169 |
Neg logit contributions | |
burn | -0.182 |
my | -0.168 |
rou | -0.165 |
daddy | -0.164 |
blowing | -0.160 |
Token | , |
Token ID | 11 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ounces | +0.027 |
hell | +0.024 |
izards | +0.024 |
ils | +0.024 |
bors | +0.024 |
Neg logit contributions | |
burn | -0.012 |
blowing | -0.011 |
waving | -0.010 |
my | -0.010 |
daddy | -0.009 |
Token | can |
Token ID | 460 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
burn | +0.004 |
blowing | +0.004 |
waving | +0.004 |
daddy | +0.003 |
spinning | +0.003 |
Neg logit contributions | |
ounces | -0.005 |
affe | -0.005 |
hell | -0.005 |
ils | -0.005 |
bors | -0.005 |
Token | we |
Token ID | 356 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
daddy | +0.038 |
burn | +0.037 |
waving | +0.037 |
blowing | +0.037 |
spinning | +0.034 |
Neg logit contributions | |
ounces | -0.052 |
ils | -0.050 |
hell | -0.050 |
affe | -0.048 |
izards | -0.047 |
Token | use |
Token ID | 779 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
ounces | +0.053 |
bors | +0.048 |
izards | +0.048 |
ils | +0.048 |
hell | +0.048 |
Neg logit contributions | |
burn | -0.028 |
blowing | -0.025 |
waving | -0.024 |
daddy | -0.022 |
spinning | -0.021 |
Token | there |
Token ID | 612 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ounces | +0.005 |
izards | +0.004 |
ils | +0.004 |
affe | +0.004 |
bors | +0.004 |
Neg logit contributions | |
burn | -0.004 |
blowing | -0.004 |
waving | -0.004 |
neighborhood | -0.003 |
driveway | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
burn | +0.043 |
blowing | +0.037 |
waving | +0.036 |
driveway | +0.031 |
spinning | +0.031 |
Neg logit contributions | |
ounces | -0.076 |
affe | -0.070 |
hell | -0.069 |
ils | -0.069 |
bors | -0.068 |
Token | a |
Token ID | 257 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
ounces | +0.054 |
affe | +0.046 |
hell | +0.046 |
bors | +0.045 |
izards | +0.045 |
Neg logit contributions | |
burn | -0.051 |
blowing | -0.044 |
waving | -0.043 |
driveway | -0.041 |
neighborhood | -0.041 |
Token | loud |
Token ID | 7812 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
ounces | +0.005 |
affe | +0.005 |
hell | +0.005 |
bors | +0.005 |
isy | +0.005 |
Neg logit contributions | |
burn | -0.004 |
blowing | -0.003 |
waving | -0.003 |
driveway | -0.003 |
my | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
ounces | +0.029 |
ils | +0.026 |
izards | +0.026 |
affe | +0.026 |
bors | +0.026 |
Neg logit contributions | |
burn | -0.024 |
blowing | -0.022 |
waving | -0.022 |
spinning | -0.020 |
neighborhood | -0.019 |
Token | P |
Token ID | 47 |
Feature activation | +7.10e+00 |
Pos logit contributions | |
ounces | +0.070 |
ils | +0.064 |
izards | +0.063 |
affe | +0.063 |
bors | +0.062 |
Neg logit contributions | |
burn | -0.065 |
blowing | -0.059 |
waving | -0.057 |
spinning | -0.052 |
my | -0.051 |
Token | OP |
Token ID | 3185 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
ounces | +0.172 |
bors | +0.170 |
ils | +0.169 |
izards | +0.151 |
mushrooms | +0.151 |
Neg logit contributions | |
burn | -0.207 |
waving | -0.184 |
blowing | -0.180 |
neighborhood | -0.175 |
leaning | -0.174 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ounces | +0.104 |
izards | +0.098 |
ils | +0.092 |
bors | +0.091 |
affe | +0.090 |
Neg logit contributions | |
burn | -0.140 |
blowing | -0.129 |
waving | -0.124 |
spinning | -0.116 |
leaning | -0.112 |
Token | Rob |
Token ID | 3851 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
ounces | +0.076 |
ils | +0.069 |
izards | +0.068 |
affe | +0.068 |
bors | +0.068 |
Neg logit contributions | |
burn | -0.051 |
blowing | -0.046 |
waving | -0.046 |
spinning | -0.040 |
neighborhood | -0.039 |
Token | stopped |
Token ID | 5025 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
burn | +0.001 |
blowing | +0.001 |
waving | +0.001 |
daddy | +0.001 |
spinning | +0.001 |
Neg logit contributions | |
ounces | -0.002 |
izards | -0.002 |
ils | -0.002 |
bors | -0.002 |
affe | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
burn | +0.145 |
driveway | +0.127 |
icycle | +0.111 |
salon | +0.111 |
bars | +0.110 |
Neg logit contributions | |
izards | -0.127 |
ounces | -0.123 |
itself | -0.118 |
beetles | -0.114 |
isy | -0.113 |
Token | and |
Token ID | 290 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
burn | +0.023 |
blowing | +0.019 |
waving | +0.019 |
driveway | +0.016 |
neighborhood | +0.016 |
Neg logit contributions | |
ounces | -0.055 |
ils | -0.051 |
affe | -0.050 |
izards | -0.050 |
bors | -0.050 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
burn | +0.012 |
blowing | +0.010 |
waving | +0.010 |
neighborhood | +0.009 |
driveway | +0.009 |
Neg logit contributions | |
ounces | -0.017 |
ils | -0.016 |
bors | -0.016 |
affe | -0.016 |
izards | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
ounces | +0.061 |
ils | +0.056 |
izards | +0.056 |
affe | +0.056 |
bors | +0.056 |
Neg logit contributions | |
burn | -0.023 |
blowing | -0.020 |
waving | -0.020 |
spinning | -0.016 |
neighborhood | -0.015 |
Token | make |
Token ID | 787 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
burn | +0.020 |
blowing | +0.019 |
waving | +0.018 |
neighborhood | +0.016 |
spinning | +0.016 |
Neg logit contributions | |
ounces | -0.026 |
ils | -0.024 |
affe | -0.024 |
bors | -0.023 |
izards | -0.023 |
Token | another |
Token ID | 1194 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ounces | +0.049 |
affe | +0.046 |
izards | +0.044 |
bors | +0.044 |
ils | +0.044 |
Neg logit contributions | |
burn | -0.032 |
blowing | -0.029 |
waving | -0.028 |
daddy | -0.026 |
spinning | -0.025 |
Token | batch |
Token ID | 15458 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
burn | +0.032 |
blowing | +0.029 |
waving | +0.028 |
spinning | +0.025 |
neighborhood | +0.025 |
Neg logit contributions | |
ounces | -0.040 |
ils | -0.036 |
izards | -0.036 |
affe | -0.036 |
bors | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
ounces | +0.275 |
bors | +0.253 |
affe | +0.245 |
ns | +0.242 |
ocket | +0.237 |
Neg logit contributions | |
blowing | -0.113 |
burn | -0.105 |
waving | -0.099 |
laughing | -0.093 |
crying | -0.092 |
Token | muff |
Token ID | 27563 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ounces | +0.031 |
affe | +0.031 |
izards | +0.031 |
ils | +0.030 |
bors | +0.030 |
Neg logit contributions | |
blowing | -0.019 |
waving | -0.019 |
burn | -0.019 |
spinning | -0.017 |
crying | -0.017 |
Token | ins |
Token ID | 1040 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
affe | +0.048 |
ounces | +0.047 |
bors | +0.046 |
nic | +0.043 |
ger | +0.043 |
Neg logit contributions | |
burn | -0.031 |
blowing | -0.030 |
my | -0.026 |
waving | -0.025 |
rou | -0.025 |
Token | together |
Token ID | 1978 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
ounces | +0.103 |
bors | +0.096 |
affe | +0.092 |
izards | +0.091 |
ils | +0.088 |
Neg logit contributions | |
burn | -0.041 |
blowing | -0.038 |
waving | -0.035 |
my | -0.032 |
daddy | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -3.85e-03 |
Pos logit contributions | |
burn | +0.005 |
blowing | +0.005 |
waving | +0.005 |
spinning | +0.004 |
crying | +0.004 |
Neg logit contributions | |
ounces | -0.011 |
izards | -0.010 |
affe | -0.010 |
bors | -0.010 |
ils | -0.009 |
Token | knock |
Token ID | 10643 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
burn | +0.024 |
blowing | +0.021 |
waving | +0.021 |
neighborhood | +0.018 |
driveway | +0.018 |
Neg logit contributions | |
ounces | -0.034 |
ils | -0.030 |
affe | -0.030 |
izards | -0.030 |
bors | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
burn | +0.045 |
blowing | +0.042 |
waving | +0.041 |
spinning | +0.036 |
leaning | +0.036 |
Neg logit contributions | |
ounces | -0.072 |
affe | -0.066 |
bors | -0.065 |
izards | -0.065 |
ils | -0.065 |
Token | a |
Token ID | 257 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ounces | +0.025 |
ils | +0.022 |
izards | +0.022 |
bors | +0.022 |
affe | +0.022 |
Neg logit contributions | |
burn | -0.017 |
blowing | -0.014 |
waving | -0.014 |
neighborhood | -0.013 |
driveway | -0.012 |
Token | fresh |
Token ID | 4713 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
ounces | +0.004 |
affe | +0.003 |
ils | +0.003 |
izards | +0.003 |
bors | +0.003 |
Neg logit contributions | |
burn | -0.002 |
blowing | -0.002 |
waving | -0.002 |
spinning | -0.002 |
neighborhood | -0.002 |
Token | new |
Token ID | 649 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
ounces | +0.003 |
ils | +0.003 |
izards | +0.003 |
affe | +0.003 |
bors | +0.003 |
Neg logit contributions | |
burn | -0.002 |
blowing | -0.002 |
waving | -0.002 |
spinning | -0.002 |
driveway | -0.002 |
Token | batch |
Token ID | 15458 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
burn | +0.021 |
blowing | +0.019 |
waving | +0.019 |
driveway | +0.016 |
neighborhood | +0.016 |
Neg logit contributions | |
ounces | -0.034 |
affe | -0.030 |
ils | -0.030 |
hell | -0.030 |
bors | -0.030 |
Token | of |
Token ID | 286 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ounces | +0.264 |
bors | +0.251 |
cod | +0.246 |
reath | +0.236 |
izards | +0.231 |
Neg logit contributions | |
blowing | -0.110 |
burn | -0.102 |
waving | -0.098 |
crying | -0.088 |
daddy | -0.086 |
Token | letters |
Token ID | 7475 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
ounces | +0.040 |
izards | +0.037 |
affe | +0.037 |
ils | +0.036 |
bors | +0.036 |
Neg logit contributions | |
burn | -0.035 |
blowing | -0.034 |
waving | -0.033 |
spinning | -0.030 |
daddy | -0.030 |
Token | would |
Token ID | 561 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
burn | +0.006 |
blowing | +0.005 |
waving | +0.005 |
spinning | +0.004 |
daddy | +0.004 |
Neg logit contributions | |
ounces | -0.009 |
ils | -0.008 |
bors | -0.008 |
izards | -0.008 |
affe | -0.008 |
Token | tumble |
Token ID | 47978 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
ounces | +0.000 |
izards | +0.000 |
ils | +0.000 |
affe | +0.000 |
bors | +0.000 |
Neg logit contributions | |
burn | -0.000 |
blowing | -0.000 |
waving | -0.000 |
spinning | -0.000 |
crying | -0.000 |
Token | out |
Token ID | 503 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
ounces | +0.026 |
izards | +0.024 |
bors | +0.024 |
affe | +0.024 |
ils | +0.024 |
Neg logit contributions | |
burn | -0.013 |
blowing | -0.012 |
waving | -0.011 |
spinning | -0.010 |
my | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
burn | +0.010 |
blowing | +0.009 |
waving | +0.009 |
spinning | +0.008 |
crying | +0.008 |
Neg logit contributions | |
ounces | -0.017 |
ils | -0.016 |
bors | -0.016 |
affe | -0.016 |
izards | -0.016 |
Token | do |
Token ID | 466 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
burn | +0.009 |
waving | +0.009 |
blowing | +0.009 |
spinning | +0.008 |
daddy | +0.007 |
Neg logit contributions | |
ounces | -0.020 |
ils | -0.018 |
affe | -0.017 |
izards | -0.017 |
bors | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ounces | +0.068 |
affe | +0.066 |
bors | +0.061 |
izards | +0.061 |
ils | +0.060 |
Neg logit contributions | |
waving | -0.027 |
blowing | -0.027 |
burn | -0.025 |
spinning | -0.024 |
crying | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ounces | +0.041 |
affe | +0.037 |
ils | +0.036 |
bors | +0.036 |
izards | +0.036 |
Neg logit contributions | |
burn | -0.023 |
blowing | -0.022 |
waving | -0.021 |
spinning | -0.018 |
crying | -0.018 |
Token | pick |
Token ID | 2298 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
burn | +0.003 |
waving | +0.003 |
blowing | +0.003 |
spinning | +0.002 |
daddy | +0.002 |
Neg logit contributions | |
ounces | -0.005 |
affe | -0.005 |
izards | -0.005 |
ils | -0.005 |
bors | -0.005 |
Token | da |
Token ID | 12379 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
ounces | +0.100 |
affe | +0.090 |
bors | +0.088 |
izards | +0.085 |
ils | +0.084 |
Neg logit contributions | |
burn | -0.039 |
waving | -0.034 |
blowing | -0.034 |
my | -0.032 |
shining | -0.030 |
Token | is |
Token ID | 271 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
ounces | +0.217 |
affe | +0.175 |
pounds | +0.164 |
bors | +0.164 |
izards | +0.161 |
Neg logit contributions | |
burn | -0.187 |
blowing | -0.181 |
waving | -0.173 |
shining | -0.160 |
spinning | -0.159 |
Token | ies |
Token ID | 444 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ounces | +0.114 |
affe | +0.105 |
ocket | +0.099 |
izards | +0.097 |
ger | +0.096 |
Neg logit contributions | |
burn | -0.047 |
blowing | -0.047 |
waving | -0.040 |
my | -0.037 |
spinning | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
ounces | +0.064 |
affe | +0.057 |
bors | +0.056 |
ils | +0.055 |
izards | +0.055 |
Neg logit contributions | |
burn | -0.025 |
waving | -0.024 |
blowing | -0.023 |
spinning | -0.019 |
crying | -0.018 |
Token | give |
Token ID | 1577 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
ounces | +0.011 |
ils | +0.010 |
affe | +0.010 |
izards | +0.010 |
bors | +0.010 |
Neg logit contributions | |
burn | -0.007 |
blowing | -0.006 |
waving | -0.006 |
spinning | -0.005 |
daddy | -0.005 |
Token | them |
Token ID | 606 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ounces | +0.031 |
affe | +0.028 |
izards | +0.027 |
hell | +0.027 |
bors | +0.026 |
Neg logit contributions | |
burn | -0.019 |
blowing | -0.017 |
waving | -0.017 |
daddy | -0.016 |
my | -0.016 |
Token | she |
Token ID | 673 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
ounces | +0.016 |
ils | +0.015 |
izards | +0.015 |
affe | +0.015 |
bors | +0.015 |
Neg logit contributions | |
burn | -0.014 |
blowing | -0.013 |
waving | -0.013 |
driveway | -0.011 |
neighborhood | -0.011 |
Token | asked |
Token ID | 1965 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
ounces | +0.065 |
ils | +0.062 |
izards | +0.059 |
affe | +0.058 |
bors | +0.058 |
Neg logit contributions | |
burn | -0.049 |
blowing | -0.044 |
waving | -0.043 |
spinning | -0.037 |
driveway | -0.036 |
Token | him |
Token ID | 683 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ounces | +0.033 |
affe | +0.029 |
hell | +0.029 |
bors | +0.029 |
izards | +0.029 |
Neg logit contributions | |
burn | -0.015 |
blowing | -0.013 |
waving | -0.013 |
daddy | -0.012 |
crying | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ounces | +0.049 |
bors | +0.044 |
affe | +0.043 |
ils | +0.043 |
hell | +0.043 |
Neg logit contributions | |
burn | -0.010 |
waving | -0.009 |
daddy | -0.009 |
my | -0.008 |
crying | -0.007 |
Token | " |
Token ID | 366 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
burn | +0.006 |
blowing | +0.005 |
waving | +0.005 |
driveway | +0.005 |
neighborhood | +0.005 |
Neg logit contributions | |
ounces | -0.007 |
affe | -0.006 |
izards | -0.006 |
bors | -0.006 |
ils | -0.006 |
Token | P |
Token ID | 47 |
Feature activation | +7.00e+00 |
Pos logit contributions | |
ounces | +0.086 |
ils | +0.078 |
bors | +0.077 |
affe | +0.077 |
izards | +0.076 |
Neg logit contributions | |
burn | -0.055 |
blowing | -0.052 |
waving | -0.051 |
spinning | -0.044 |
crying | -0.044 |
Token | apa |
Token ID | 32678 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
ounces | +0.215 |
bors | +0.194 |
ils | +0.189 |
hell | +0.182 |
affe | +0.181 |
Neg logit contributions | |
burn | -0.183 |
blowing | -0.153 |
waving | -0.152 |
my | -0.150 |
neighborhood | -0.149 |
Token | , |
Token ID | 11 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
ounces | +0.013 |
izards | +0.012 |
ils | +0.012 |
bors | +0.012 |
affe | +0.012 |
Neg logit contributions | |
burn | -0.007 |
blowing | -0.006 |
waving | -0.006 |
daddy | -0.005 |
my | -0.005 |
Token | why |
Token ID | 1521 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ounces | +0.002 |
ils | +0.002 |
affe | +0.002 |
izards | +0.002 |
bors | +0.002 |
Neg logit contributions | |
burn | -0.002 |
blowing | -0.002 |
waving | -0.002 |
spinning | -0.002 |
daddy | -0.002 |
Token | do |
Token ID | 466 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
burn | +0.041 |
blowing | +0.037 |
waving | +0.037 |
driveway | +0.033 |
neighborhood | +0.033 |
Neg logit contributions | |
ounces | -0.050 |
ils | -0.045 |
izards | -0.045 |
affe | -0.045 |
hell | -0.044 |
Token | you |
Token ID | 345 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
burn | +0.014 |
daddy | +0.014 |
waving | +0.014 |
blowing | +0.013 |
grandma | +0.013 |
Neg logit contributions | |
ounces | -0.018 |
hell | -0.017 |
ils | -0.017 |
affe | -0.016 |
izards | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
ounces | +0.019 |
ils | +0.017 |
affe | +0.017 |
hell | +0.017 |
izards | +0.017 |
Neg logit contributions | |
burn | -0.013 |
blowing | -0.012 |
waving | -0.012 |
daddy | -0.011 |
spinning | -0.011 |
Token | could |
Token ID | 714 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
ounces | +0.035 |
bors | +0.031 |
affe | +0.030 |
izards | +0.030 |
hell | +0.030 |
Neg logit contributions | |
burn | -0.018 |
blowing | -0.016 |
waving | -0.016 |
my | -0.014 |
neighborhood | -0.013 |
Token | grow |
Token ID | 1663 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
burn | +0.087 |
blowing | +0.078 |
waving | +0.077 |
neighborhood | +0.068 |
driveway | +0.068 |
Neg logit contributions | |
ounces | -0.112 |
ils | -0.101 |
izards | -0.100 |
affe | -0.099 |
bors | -0.098 |
Token | more |
Token ID | 517 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
ounces | +0.047 |
affe | +0.042 |
bors | +0.041 |
ils | +0.040 |
izards | +0.038 |
Neg logit contributions | |
burn | -0.020 |
blowing | -0.019 |
waving | -0.018 |
shining | -0.017 |
spinning | -0.016 |
Token | av |
Token ID | 1196 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ounces | +0.012 |
affe | +0.010 |
bors | +0.010 |
ils | +0.010 |
izards | +0.010 |
Neg logit contributions | |
blowing | -0.010 |
waving | -0.010 |
burn | -0.010 |
neighborhood | -0.009 |
window | -0.009 |
Token | oc |
Token ID | 420 |
Feature activation | +6.96e+00 |
Pos logit contributions | |
ounces | +0.046 |
izards | +0.038 |
bors | +0.037 |
ils | +0.037 |
affe | +0.034 |
Neg logit contributions | |
burn | -0.112 |
blowing | -0.105 |
waving | -0.103 |
my | -0.099 |
neighborhood | -0.097 |
Token | ados |
Token ID | 22484 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ounces | +0.103 |
izards | +0.097 |
hell | +0.089 |
bors | +0.089 |
isy | +0.084 |
Neg logit contributions | |
burn | -0.267 |
blowing | -0.251 |
waving | -0.246 |
leaning | -0.240 |
crying | -0.227 |
Token | and |
Token ID | 290 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ounces | +0.099 |
bors | +0.090 |
affe | +0.088 |
ils | +0.086 |
izards | +0.086 |
Neg logit contributions | |
burn | -0.045 |
blowing | -0.041 |
waving | -0.041 |
my | -0.034 |
daddy | -0.034 |
Token | share |
Token ID | 2648 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ounces | +0.013 |
affe | +0.012 |
ils | +0.012 |
izards | +0.012 |
bors | +0.012 |
Neg logit contributions | |
burn | -0.009 |
waving | -0.008 |
blowing | -0.008 |
spinning | -0.007 |
daddy | -0.007 |
Token | them |
Token ID | 606 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
waving | +0.004 |
burn | +0.004 |
blowing | +0.004 |
daddy | +0.004 |
my | +0.004 |
Neg logit contributions | |
ounces | -0.008 |
affe | -0.007 |
izards | -0.007 |
bors | -0.007 |
ils | -0.007 |
Token | with |
Token ID | 351 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
ounces | +0.059 |
affe | +0.054 |
bors | +0.053 |
izards | +0.052 |
ils | +0.050 |
Neg logit contributions | |
burn | -0.010 |
waving | -0.010 |
blowing | -0.009 |
my | -0.008 |
daddy | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ounces | +0.043 |
ils | +0.039 |
affe | +0.039 |
izards | +0.038 |
bors | +0.038 |
Neg logit contributions | |
burn | -0.035 |
blowing | -0.033 |
waving | -0.032 |
spinning | -0.029 |
daddy | -0.028 |
Token | shook |
Token ID | 14682 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ounces | +0.053 |
affe | +0.048 |
bors | +0.048 |
izards | +0.048 |
hell | +0.048 |
Neg logit contributions | |
burn | -0.032 |
blowing | -0.029 |
waving | -0.029 |
neighborhood | -0.026 |
spinning | -0.025 |
Token | it |
Token ID | 340 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
burn | +0.026 |
blowing | +0.023 |
waving | +0.023 |
spinning | +0.020 |
neighborhood | +0.020 |
Neg logit contributions | |
ounces | -0.035 |
ils | -0.031 |
izards | -0.031 |
affe | -0.031 |
bors | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
ounces | +0.046 |
ils | +0.042 |
izards | +0.042 |
bors | +0.042 |
affe | +0.042 |
Neg logit contributions | |
burn | -0.027 |
blowing | -0.025 |
waving | -0.024 |
spinning | -0.021 |
crying | -0.021 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
burn | +0.009 |
waving | +0.008 |
blowing | +0.008 |
neighborhood | +0.007 |
daddy | +0.007 |
Neg logit contributions | |
ounces | -0.020 |
ils | -0.019 |
izards | -0.018 |
bors | -0.018 |
affe | -0.018 |
Token | Pa |
Token ID | 28875 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
burn | +0.055 |
blowing | +0.048 |
waving | +0.048 |
spinning | +0.040 |
neighborhood | +0.040 |
Neg logit contributions | |
ounces | -0.107 |
ils | -0.098 |
izards | -0.097 |
affe | -0.097 |
bors | -0.096 |
Token | ola |
Token ID | 5708 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
ounces | +0.207 |
bors | +0.177 |
izards | +0.170 |
ils | +0.169 |
hell | +0.164 |
Neg logit contributions | |
burn | -0.190 |
waving | -0.174 |
blowing | -0.170 |
my | -0.165 |
neighborhood | -0.159 |
Token | and |
Token ID | 290 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
ounces | +0.106 |
ils | +0.100 |
affe | +0.097 |
bors | +0.096 |
izards | +0.096 |
Neg logit contributions | |
burn | -0.059 |
blowing | -0.051 |
waving | -0.050 |
spinning | -0.042 |
crying | -0.041 |
Token | her |
Token ID | 607 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
burn | +0.007 |
blowing | +0.006 |
waving | +0.006 |
spinning | +0.005 |
driveway | +0.005 |
Neg logit contributions | |
ounces | -0.008 |
affe | -0.007 |
izards | -0.007 |
ils | -0.007 |
bors | -0.007 |
Token | mother |
Token ID | 2802 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
affe | +0.006 |
ily | +0.006 |
ils | +0.006 |
ounces | +0.006 |
izards | +0.006 |
Neg logit contributions | |
burn | -0.004 |
blowing | -0.004 |
waving | -0.003 |
driveway | -0.003 |
seat | -0.003 |
Token | were |
Token ID | 547 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
burn | +0.055 |
blowing | +0.049 |
waving | +0.047 |
spinning | +0.043 |
driveway | +0.041 |
Neg logit contributions | |
ounces | -0.070 |
ils | -0.069 |
affe | -0.065 |
bors | -0.064 |
izards | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
burn | +0.016 |
blowing | +0.014 |
waving | +0.014 |
spinning | +0.011 |
neighborhood | +0.011 |
Neg logit contributions | |
ounces | -0.040 |
ils | -0.037 |
izards | -0.036 |
affe | -0.036 |
bors | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ounces | +0.017 |
ils | +0.016 |
affe | +0.015 |
izards | +0.015 |
bors | +0.015 |
Neg logit contributions | |
burn | -0.005 |
blowing | -0.004 |
waving | -0.004 |
neighborhood | -0.003 |
my | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
ounces | +0.038 |
ils | +0.037 |
izards | +0.036 |
ocket | +0.035 |
affe | +0.035 |
Neg logit contributions | |
burn | -0.023 |
blowing | -0.022 |
waving | -0.021 |
neighborhood | -0.020 |
driveway | -0.019 |
Token | two |
Token ID | 734 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
burn | +0.023 |
blowing | +0.020 |
waving | +0.020 |
spinning | +0.018 |
neighborhood | +0.018 |
Neg logit contributions | |
ounces | -0.031 |
ils | -0.028 |
izards | -0.027 |
affe | -0.027 |
bors | -0.027 |
Token | combatants |
Token ID | 40711 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
burn | +0.006 |
waving | +0.005 |
blowing | +0.005 |
spinning | +0.005 |
daddy | +0.005 |
Neg logit contributions | |
ounces | -0.009 |
ils | -0.008 |
izards | -0.008 |
bors | -0.008 |
hell | -0.008 |
Token | stopped |
Token ID | 5025 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
burn | +0.023 |
blowing | +0.021 |
waving | +0.021 |
spinning | +0.018 |
neighborhood | +0.018 |
Neg logit contributions | |
ounces | -0.035 |
ils | -0.031 |
izards | -0.031 |
affe | -0.031 |
bors | -0.031 |
Token | fighting |
Token ID | 4330 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
burn | +0.163 |
driveway | +0.138 |
icycle | +0.122 |
tr | +0.118 |
salon | +0.117 |
Neg logit contributions | |
ounces | -0.210 |
izards | -0.197 |
ils | -0.191 |
bors | -0.189 |
ious | -0.178 |
Token | and |
Token ID | 290 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
burn | +0.048 |
blowing | +0.041 |
waving | +0.040 |
neighborhood | +0.036 |
driveway | +0.036 |
Neg logit contributions | |
ounces | -0.079 |
ils | -0.073 |
izards | -0.072 |
affe | -0.071 |
hell | -0.071 |
Token | looked |
Token ID | 3114 |
Feature activation | +9.62e-02 |
Pos logit contributions | |
burn | +0.005 |
blowing | +0.005 |
waving | +0.005 |
spinning | +0.004 |
daddy | +0.004 |
Neg logit contributions | |
ounces | -0.008 |
ils | -0.007 |
affe | -0.007 |
izards | -0.007 |
bors | -0.007 |
Token | at |
Token ID | 379 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
ounces | +0.003 |
affe | +0.003 |
izards | +0.003 |
ils | +0.003 |
bors | +0.003 |
Neg logit contributions | |
burn | -0.002 |
waving | -0.002 |
blowing | -0.002 |
spinning | -0.002 |
crying | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
burn | +0.013 |
blowing | +0.011 |
waving | +0.011 |
spinning | +0.010 |
daddy | +0.010 |
Neg logit contributions | |
ounces | -0.019 |
ils | -0.017 |
affe | -0.017 |
izards | -0.017 |
bors | -0.017 |
Token | using |
Token ID | 1262 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
ounces | +0.049 |
ils | +0.045 |
izards | +0.044 |
bors | +0.044 |
affe | +0.043 |
Neg logit contributions | |
burn | -0.027 |
blowing | -0.023 |
waving | -0.023 |
driveway | -0.020 |
neighborhood | -0.020 |
Token | his |
Token ID | 465 |
Feature activation | -9.03e-02 |
Pos logit contributions | |
burn | +0.012 |
blowing | +0.011 |
waving | +0.011 |
spinning | +0.010 |
daddy | +0.009 |
Neg logit contributions | |
ounces | -0.018 |
ils | -0.016 |
affe | -0.016 |
izards | -0.016 |
bors | -0.016 |
Token | problem |
Token ID | 1917 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
burn | +0.002 |
blowing | +0.002 |
waving | +0.002 |
spinning | +0.002 |
neighborhood | +0.002 |
Neg logit contributions | |
ounces | -0.003 |
ils | -0.003 |
izards | -0.003 |
affe | -0.003 |
bors | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
ounces | +0.007 |
ils | +0.006 |
affe | +0.006 |
izards | +0.006 |
bors | +0.006 |
Neg logit contributions | |
burn | -0.005 |
blowing | -0.004 |
waving | -0.004 |
spinning | -0.004 |
neighborhood | -0.004 |
Token | s |
Token ID | 82 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
ounces | +0.101 |
izards | +0.090 |
affe | +0.090 |
ils | +0.089 |
bors | +0.088 |
Neg logit contributions | |
burn | -0.098 |
blowing | -0.092 |
waving | -0.089 |
my | -0.083 |
spinning | -0.082 |
Token | olving |
Token ID | 10890 |
Feature activation | -6.47e+00 |
Pos logit contributions | |
burn | +0.010 |
blowing | +0.009 |
waving | +0.009 |
driveway | +0.007 |
neighborhood | +0.007 |
Neg logit contributions | |
ounces | -0.014 |
ils | -0.013 |
izards | -0.012 |
affe | -0.012 |
bors | -0.012 |
Token | skills |
Token ID | 4678 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
burn | +0.196 |
blowing | +0.177 |
waving | +0.177 |
crying | +0.158 |
spinning | +0.157 |
Neg logit contributions | |
ounces | -0.178 |
ils | -0.156 |
affe | -0.152 |
izards | -0.151 |
hell | -0.150 |
Token | . |
Token ID | 13 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ounces | +0.036 |
ils | +0.032 |
izards | +0.032 |
affe | +0.032 |
bors | +0.032 |
Neg logit contributions | |
burn | -0.023 |
blowing | -0.021 |
waving | -0.020 |
spinning | -0.018 |
neighborhood | -0.017 |
Token | From |
Token ID | 3574 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
burn | +0.007 |
blowing | +0.007 |
waving | +0.007 |
daddy | +0.006 |
neighborhood | +0.006 |
Neg logit contributions | |
ounces | -0.009 |
ils | -0.009 |
izards | -0.008 |
bors | -0.008 |
affe | -0.008 |
Token | that |
Token ID | 326 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
ounces | +0.034 |
ils | +0.031 |
izards | +0.030 |
affe | +0.030 |
bors | +0.030 |
Neg logit contributions | |
burn | -0.042 |
blowing | -0.037 |
waving | -0.036 |
driveway | -0.034 |
neighborhood | -0.033 |
Token | day |
Token ID | 1110 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
burn | +0.083 |
waving | +0.067 |
blowing | +0.063 |
driveway | +0.061 |
seat | +0.059 |
Neg logit contributions | |
ounces | -0.109 |
affe | -0.101 |
ils | -0.100 |
isy | -0.098 |
hell | -0.097 |
Token | it |
Token ID | 340 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
ounces | +0.055 |
ils | +0.051 |
affe | +0.050 |
bors | +0.050 |
izards | +0.050 |
Neg logit contributions | |
burn | -0.037 |
waving | -0.035 |
blowing | -0.035 |
spinning | -0.031 |
leaning | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ounces | +0.100 |
ils | +0.092 |
bors | +0.092 |
affe | +0.090 |
izards | +0.089 |
Neg logit contributions | |
burn | -0.045 |
blowing | -0.042 |
waving | -0.042 |
spinning | -0.037 |
crying | -0.035 |
Token | but |
Token ID | 475 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
burn | +0.004 |
waving | +0.004 |
blowing | +0.004 |
spinning | +0.004 |
crying | +0.004 |
Neg logit contributions | |
ounces | -0.007 |
ils | -0.006 |
affe | -0.006 |
bors | -0.006 |
izards | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ounces | +0.007 |
ils | +0.006 |
bors | +0.006 |
affe | +0.006 |
hell | +0.006 |
Neg logit contributions | |
burn | -0.004 |
waving | -0.004 |
blowing | -0.004 |
daddy | -0.004 |
spinning | -0.004 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
burn | +0.026 |
blowing | +0.025 |
waving | +0.022 |
typing | +0.022 |
ric | +0.022 |
Neg logit contributions | |
ounces | -0.033 |
affe | -0.032 |
aces | -0.030 |
hell | -0.030 |
izards | -0.030 |
Token | stopped |
Token ID | 5025 |
Feature activation | -6.30e+00 |
Pos logit contributions | |
burn | +0.112 |
blowing | +0.100 |
waving | +0.099 |
driveway | +0.091 |
neighborhood | +0.089 |
Neg logit contributions | |
ounces | -0.128 |
ils | -0.117 |
affe | -0.116 |
izards | -0.114 |
bors | -0.112 |
Token | him |
Token ID | 683 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
burn | +0.174 |
driveway | +0.150 |
neighborhood | +0.136 |
waving | +0.134 |
blowing | +0.133 |
Neg logit contributions | |
ounces | -0.171 |
izards | -0.162 |
bors | -0.158 |
ils | -0.149 |
isy | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
burn | +0.018 |
blowing | +0.016 |
waving | +0.016 |
neighborhood | +0.015 |
driveway | +0.014 |
Neg logit contributions | |
ounces | -0.025 |
ils | -0.023 |
hell | -0.023 |
affe | -0.023 |
izards | -0.023 |
Token | She |
Token ID | 1375 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
ounces | +0.007 |
affe | +0.007 |
ils | +0.006 |
izards | +0.006 |
hell | +0.006 |
Neg logit contributions | |
burn | -0.006 |
blowing | -0.006 |
waving | -0.005 |
spinning | -0.005 |
daddy | -0.005 |
Token | told |
Token ID | 1297 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ounces | +0.026 |
izards | +0.024 |
ils | +0.024 |
hell | +0.024 |
bors | +0.023 |
Neg logit contributions | |
burn | -0.015 |
blowing | -0.014 |
waving | -0.014 |
daddy | -0.012 |
spinning | -0.012 |
Token | him |
Token ID | 683 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
ounces | +0.099 |
ils | +0.089 |
affe | +0.088 |
izards | +0.088 |
bors | +0.088 |
Neg logit contributions | |
burn | -0.053 |
waving | -0.048 |
blowing | -0.048 |
daddy | -0.042 |
my | -0.042 |
Token | But |
Token ID | 887 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ounces | +0.020 |
ils | +0.019 |
izards | +0.018 |
bors | +0.018 |
affe | +0.018 |
Neg logit contributions | |
burn | -0.015 |
waving | -0.014 |
blowing | -0.014 |
neighborhood | -0.013 |
driveway | -0.013 |
Token | he |
Token ID | 339 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
ounces | +0.035 |
ils | +0.031 |
affe | +0.031 |
izards | +0.031 |
bors | +0.031 |
Neg logit contributions | |
burn | -0.026 |
blowing | -0.023 |
waving | -0.023 |
driveway | -0.020 |
neighborhood | -0.020 |
Token | wasn |
Token ID | 2492 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
ounces | +0.033 |
ils | +0.031 |
izards | +0.030 |
affe | +0.030 |
bors | +0.030 |
Neg logit contributions | |
burn | -0.020 |
waving | -0.018 |
blowing | -0.018 |
driveway | -0.016 |
spinning | -0.015 |
Token | 't |
Token ID | 470 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
ounces | +0.003 |
izards | +0.002 |
affe | +0.002 |
hell | +0.002 |
ils | +0.002 |
Neg logit contributions | |
burn | -0.002 |
waving | -0.002 |
blowing | -0.002 |
neighborhood | -0.001 |
driveway | -0.001 |
Token | happy |
Token ID | 3772 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
burn | +0.062 |
blowing | +0.057 |
waving | +0.055 |
spinning | +0.048 |
crying | +0.047 |
Neg logit contributions | |
ounces | -0.113 |
ils | -0.103 |
affe | -0.102 |
bors | -0.101 |
izards | -0.100 |
Token | living |
Token ID | 2877 |
Feature activation | -6.30e+00 |
Pos logit contributions | |
ounces | +0.020 |
izards | +0.018 |
ils | +0.018 |
affe | +0.017 |
hell | +0.017 |
Neg logit contributions | |
burn | -0.016 |
blowing | -0.014 |
waving | -0.014 |
driveway | -0.013 |
neighborhood | -0.013 |
Token | high |
Token ID | 1029 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
burn | +0.157 |
blowing | +0.140 |
waving | +0.138 |
driveway | +0.127 |
spinning | +0.119 |
Neg logit contributions | |
ounces | -0.202 |
ils | -0.187 |
izards | -0.184 |
bors | -0.175 |
hell | -0.174 |
Token | above |
Token ID | 2029 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
burn | +0.005 |
blowing | +0.004 |
waving | +0.004 |
driveway | +0.004 |
spinning | +0.004 |
Neg logit contributions | |
ounces | -0.008 |
ils | -0.007 |
izards | -0.007 |
affe | -0.007 |
bors | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
burn | +0.034 |
blowing | +0.033 |
waving | +0.032 |
leaning | +0.028 |
my | +0.028 |
Neg logit contributions | |
ounces | -0.086 |
izards | -0.079 |
bors | -0.079 |
ils | -0.079 |
affe | -0.077 |
Token | rest |
Token ID | 1334 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
ounces | +0.015 |
affe | +0.014 |
ils | +0.013 |
bors | +0.013 |
izards | +0.013 |
Neg logit contributions | |
burn | -0.009 |
blowing | -0.008 |
waving | -0.008 |
spinning | -0.007 |
driveway | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | -2.10e-03 |
Pos logit contributions | |
burn | +0.069 |
blowing | +0.068 |
waving | +0.065 |
spinning | +0.059 |
my | +0.058 |
Neg logit contributions | |
ounces | -0.092 |
bors | -0.085 |
ils | -0.082 |
affe | -0.081 |
hell | -0.079 |
Token | unk |
Token ID | 2954 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
burn | +0.026 |
blowing | +0.024 |
waving | +0.023 |
spinning | +0.021 |
neighborhood | +0.021 |
Neg logit contributions | |
ounces | -0.026 |
affe | -0.022 |
hell | -0.022 |
ils | -0.022 |
bors | -0.022 |
Token | ! |
Token ID | 0 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ounces | +0.026 |
bors | +0.023 |
izards | +0.023 |
hell | +0.023 |
ils | +0.023 |
Neg logit contributions | |
burn | -0.014 |
blowing | -0.014 |
waving | -0.014 |
crying | -0.013 |
spinning | -0.012 |
Token | He |
Token ID | 679 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
ounces | +0.005 |
ils | +0.005 |
hell | +0.005 |
izards | +0.005 |
isy | +0.005 |
Neg logit contributions | |
burn | -0.005 |
blowing | -0.004 |
waving | -0.004 |
daddy | -0.004 |
crying | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
burn | +0.001 |
blowing | +0.001 |
waving | +0.001 |
crying | +0.001 |
my | +0.001 |
Neg logit contributions | |
ounces | -0.002 |
hell | -0.002 |
izards | -0.002 |
affe | -0.002 |
bors | -0.002 |
Token | been |
Token ID | 587 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
burn | +0.025 |
blowing | +0.022 |
waving | +0.022 |
spinning | +0.019 |
driveway | +0.018 |
Neg logit contributions | |
ounces | -0.045 |
ils | -0.041 |
izards | -0.041 |
affe | -0.041 |
bors | -0.041 |
Token | living |
Token ID | 2877 |
Feature activation | -6.30e+00 |
Pos logit contributions | |
burn | +0.033 |
blowing | +0.029 |
waving | +0.028 |
driveway | +0.024 |
neighborhood | +0.024 |
Neg logit contributions | |
ounces | -0.063 |
ils | -0.057 |
izards | -0.057 |
bors | -0.057 |
affe | -0.056 |
Token | around |
Token ID | 1088 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
burn | +0.146 |
blowing | +0.132 |
waving | +0.131 |
spinning | +0.115 |
neighborhood | +0.114 |
Neg logit contributions | |
ounces | -0.213 |
ils | -0.192 |
affe | -0.192 |
izards | -0.191 |
bors | -0.190 |
Token | here |
Token ID | 994 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
burn | +0.037 |
blowing | +0.036 |
waving | +0.035 |
spinning | +0.030 |
crying | +0.030 |
Neg logit contributions | |
ounces | -0.082 |
affe | -0.075 |
hell | -0.074 |
izards | -0.074 |
ils | -0.074 |
Token | for |
Token ID | 329 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
burn | +0.016 |
blowing | +0.015 |
waving | +0.015 |
spinning | +0.012 |
neighborhood | +0.012 |
Neg logit contributions | |
ounces | -0.033 |
ils | -0.030 |
izards | -0.030 |
affe | -0.030 |
bors | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
affe | +0.099 |
ounces | +0.098 |
hell | +0.093 |
izards | +0.092 |
ils | +0.092 |
Neg logit contributions | |
blowing | -0.034 |
waving | -0.032 |
burn | -0.031 |
spinning | -0.028 |
crying | -0.027 |
Token | while |
Token ID | 981 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
burn | +0.003 |
blowing | +0.003 |
waving | +0.003 |
spinning | +0.003 |
daddy | +0.003 |
Neg logit contributions | |
ounces | -0.005 |
ils | -0.005 |
izards | -0.005 |
affe | -0.005 |
bors | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
ounces | +0.016 |
ils | +0.014 |
izards | +0.014 |
bors | +0.014 |
affe | +0.014 |
Neg logit contributions | |
burn | -0.011 |
blowing | -0.010 |
waving | -0.010 |
spinning | -0.009 |
crying | -0.009 |
Token | Max |
Token ID | 5436 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
ounces | +0.023 |
affe | +0.022 |
hell | +0.021 |
izards | +0.021 |
bors | +0.021 |
Neg logit contributions | |
burn | -0.015 |
blowing | -0.013 |
waving | -0.013 |
crying | -0.011 |
neighborhood | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
burn | +0.018 |
blowing | +0.016 |
waving | +0.016 |
spinning | +0.014 |
neighborhood | +0.013 |
Neg logit contributions | |
ounces | -0.030 |
ils | -0.027 |
izards | -0.027 |
affe | -0.027 |
bors | -0.027 |
Token | very |
Token ID | 845 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
burn | +0.030 |
driveway | +0.026 |
neighborhood | +0.025 |
blowing | +0.025 |
seat | +0.024 |
Neg logit contributions | |
ounces | -0.030 |
izards | -0.029 |
ily | -0.028 |
affe | -0.027 |
isy | -0.026 |
Token | happy |
Token ID | 3772 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
ounces | +0.045 |
izards | +0.041 |
ils | +0.040 |
affe | +0.040 |
bors | +0.040 |
Neg logit contributions | |
burn | -0.033 |
blowing | -0.030 |
waving | -0.029 |
driveway | -0.026 |
neighborhood | -0.026 |
Token | living |
Token ID | 2877 |
Feature activation | -6.30e+00 |
Pos logit contributions | |
burn | +0.014 |
blowing | +0.012 |
waving | +0.012 |
driveway | +0.012 |
neighborhood | +0.011 |
Neg logit contributions | |
ounces | -0.014 |
izards | -0.014 |
ils | -0.013 |
affe | -0.013 |
hell | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
burn | +0.132 |
blowing | +0.117 |
waving | +0.116 |
spinning | +0.099 |
neighborhood | +0.098 |
Neg logit contributions | |
ounces | -0.229 |
ils | -0.208 |
izards | -0.206 |
affe | -0.206 |
bors | -0.205 |
Token | the |
Token ID | 262 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
burn | +0.024 |
blowing | +0.022 |
waving | +0.022 |
spinning | +0.019 |
daddy | +0.019 |
Neg logit contributions | |
ounces | -0.036 |
ils | -0.033 |
izards | -0.032 |
affe | -0.032 |
bors | -0.032 |
Token | farm |
Token ID | 5318 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ounces | +0.010 |
affe | +0.009 |
isy | +0.009 |
ils | +0.009 |
bors | +0.009 |
Neg logit contributions | |
burn | -0.008 |
waving | -0.007 |
blowing | -0.007 |
crying | -0.006 |
seat | -0.006 |
Token | with |
Token ID | 351 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ounces | +0.050 |
bors | +0.045 |
izards | +0.045 |
affe | +0.045 |
ils | +0.045 |
Neg logit contributions | |
burn | -0.031 |
blowing | -0.028 |
waving | -0.028 |
spinning | -0.024 |
neighborhood | -0.024 |
Token | his |
Token ID | 465 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ounces | +0.057 |
izards | +0.053 |
ils | +0.053 |
affe | +0.052 |
bors | +0.052 |
Neg logit contributions | |
burn | -0.029 |
waving | -0.026 |
blowing | -0.025 |
daddy | -0.024 |
spinning | -0.022 |
Token | house |
Token ID | 2156 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
affe | +0.009 |
bors | +0.008 |
ounces | +0.008 |
ils | +0.008 |
nic | +0.008 |
Neg logit contributions | |
burn | -0.013 |
blowing | -0.011 |
bie | -0.011 |
waving | -0.011 |
asleep | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
ounces | +0.006 |
ils | +0.005 |
izards | +0.005 |
affe | +0.005 |
hell | +0.005 |
Neg logit contributions | |
burn | -0.004 |
blowing | -0.003 |
waving | -0.003 |
daddy | -0.003 |
neighborhood | -0.003 |
Token | when |
Token ID | 618 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
burn | +0.013 |
blowing | +0.010 |
eddy | +0.010 |
neighborhood | +0.010 |
driveway | +0.010 |
Neg logit contributions | |
ounces | -0.011 |
izards | -0.010 |
bors | -0.010 |
isy | -0.009 |
ils | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
burn | +0.052 |
blowing | +0.046 |
waving | +0.044 |
driveway | +0.042 |
neighborhood | +0.040 |
Neg logit contributions | |
ounces | -0.042 |
izards | -0.037 |
bors | -0.037 |
ils | -0.036 |
ily | -0.035 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
burn | +0.009 |
blowing | +0.008 |
waving | +0.008 |
my | +0.008 |
ric | +0.008 |
Neg logit contributions | |
ounces | -0.014 |
affe | -0.014 |
isy | -0.013 |
ils | -0.013 |
izards | -0.012 |
Token | stopped |
Token ID | 5025 |
Feature activation | -6.28e+00 |
Pos logit contributions | |
burn | +0.073 |
blowing | +0.065 |
waving | +0.063 |
spinning | +0.055 |
driveway | +0.055 |
Neg logit contributions | |
ounces | -0.109 |
ils | -0.102 |
affe | -0.099 |
izards | -0.099 |
bors | -0.098 |
Token | her |
Token ID | 607 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
burn | +0.165 |
driveway | +0.141 |
icycle | +0.127 |
neighborhood | +0.124 |
waving | +0.123 |
Neg logit contributions | |
ounces | -0.165 |
izards | -0.158 |
bors | -0.158 |
ocol | -0.154 |
ils | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
burn | +0.028 |
blowing | +0.023 |
sch | +0.022 |
Look | +0.022 |
neighborhood | +0.022 |
Neg logit contributions | |
isy | -0.033 |
affe | -0.033 |
ounces | -0.032 |
ils | -0.030 |
hell | -0.030 |
Token | Her |
Token ID | 2332 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ounces | +0.009 |
ils | +0.008 |
affe | +0.008 |
izards | +0.008 |
bors | +0.008 |
Neg logit contributions | |
burn | -0.007 |
blowing | -0.006 |
waving | -0.006 |
spinning | -0.005 |
neighborhood | -0.005 |
Token | mother |
Token ID | 2802 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
burn | +0.033 |
blowing | +0.031 |
ric | +0.030 |
waving | +0.027 |
ained | +0.026 |
Neg logit contributions | |
ounces | -0.033 |
ily | -0.033 |
isy | -0.032 |
affe | -0.032 |
hell | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
burn | +0.070 |
blowing | +0.062 |
waving | +0.061 |
driveway | +0.053 |
spinning | +0.053 |
Neg logit contributions | |
ounces | -0.107 |
ils | -0.098 |
affe | -0.097 |
bors | -0.096 |
izards | -0.096 |
Token | actus |
Token ID | 34144 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ounces | +0.077 |
bors | +0.069 |
izards | +0.067 |
ils | +0.067 |
affe | +0.064 |
Neg logit contributions | |
burn | -0.056 |
blowing | -0.047 |
waving | -0.045 |
neighborhood | -0.043 |
window | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
ounces | +0.089 |
bors | +0.081 |
izards | +0.076 |
ils | +0.075 |
affe | +0.075 |
Neg logit contributions | |
burn | -0.042 |
blowing | -0.031 |
waving | -0.030 |
my | -0.029 |
window | -0.029 |
Token | It |
Token ID | 632 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
burn | +0.021 |
waving | +0.019 |
blowing | +0.018 |
daddy | +0.018 |
my | +0.017 |
Neg logit contributions | |
ounces | -0.026 |
ils | -0.026 |
hell | -0.024 |
izards | -0.024 |
bors | -0.023 |
Token | 's |
Token ID | 338 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
burn | +0.003 |
blowing | +0.003 |
waving | +0.003 |
my | +0.002 |
crying | +0.002 |
Neg logit contributions | |
ounces | -0.005 |
izards | -0.005 |
bors | -0.004 |
affe | -0.004 |
ils | -0.004 |
Token | happy |
Token ID | 3772 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
burn | +0.013 |
blowing | +0.012 |
waving | +0.012 |
spinning | +0.010 |
crying | +0.010 |
Neg logit contributions | |
ounces | -0.022 |
affe | -0.020 |
ils | -0.020 |
izards | -0.020 |
bors | -0.020 |
Token | living |
Token ID | 2877 |
Feature activation | -6.26e+00 |
Pos logit contributions | |
burn | +0.020 |
blowing | +0.018 |
waving | +0.018 |
daddy | +0.015 |
spinning | +0.015 |
Neg logit contributions | |
ounces | -0.034 |
ils | -0.031 |
izards | -0.031 |
bors | -0.031 |
affe | -0.031 |
Token | in |
Token ID | 287 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
burn | +0.137 |
blowing | +0.124 |
waving | +0.123 |
spinning | +0.107 |
crying | +0.106 |
Neg logit contributions | |
ounces | -0.222 |
affe | -0.202 |
izards | -0.198 |
bors | -0.198 |
ils | -0.198 |
Token | the |
Token ID | 262 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
burn | +0.069 |
blowing | +0.062 |
waving | +0.062 |
spinning | +0.054 |
neighborhood | +0.054 |
Neg logit contributions | |
ounces | -0.095 |
ils | -0.086 |
izards | -0.085 |
affe | -0.085 |
bors | -0.085 |
Token | desert |
Token ID | 10326 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
burn | +0.001 |
blowing | +0.001 |
waving | +0.001 |
spinning | +0.000 |
daddy | +0.000 |
Neg logit contributions | |
ounces | -0.001 |
ils | -0.001 |
affe | -0.001 |
izards | -0.001 |
bors | -0.001 |
Token | where |
Token ID | 810 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ounces | +0.067 |
affe | +0.061 |
bors | +0.061 |
izards | +0.061 |
ils | +0.059 |
Neg logit contributions | |
burn | -0.037 |
blowing | -0.034 |
waving | -0.033 |
window | -0.029 |
my | -0.029 |
Token | it |
Token ID | 340 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
burn | +0.033 |
blowing | +0.032 |
waving | +0.031 |
daddy | +0.030 |
crying | +0.029 |
Neg logit contributions | |
ounces | -0.043 |
affe | -0.040 |
hell | -0.038 |
ils | -0.037 |
isy | -0.037 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
ounces | +0.038 |
ils | +0.037 |
izards | +0.037 |
keys | +0.036 |
bors | +0.035 |
Neg logit contributions | |
crying | -0.012 |
asleep | -0.011 |
bathroom | -0.011 |
window | -0.011 |
daddy | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
burn | +0.009 |
blowing | +0.008 |
waving | +0.008 |
spinning | +0.006 |
crying | +0.006 |
Neg logit contributions | |
ounces | -0.022 |
izards | -0.020 |
ils | -0.020 |
affe | -0.020 |
bors | -0.020 |
Token | sad |
Token ID | 6507 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
burn | +0.031 |
blowing | +0.026 |
driveway | +0.026 |
waving | +0.025 |
neighborhood | +0.025 |
Neg logit contributions | |
ounces | -0.036 |
izards | -0.033 |
bors | -0.032 |
ils | -0.032 |
hell | -0.032 |
Token | because |
Token ID | 780 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
burn | +0.015 |
waving | +0.013 |
driveway | +0.013 |
blowing | +0.013 |
neighborhood | +0.012 |
Neg logit contributions | |
ounces | -0.013 |
izards | -0.012 |
affe | -0.012 |
hell | -0.011 |
ily | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
burn | +0.033 |
blowing | +0.030 |
waving | +0.029 |
spinning | +0.026 |
neighborhood | +0.026 |
Neg logit contributions | |
ounces | -0.038 |
ils | -0.034 |
izards | -0.033 |
affe | -0.033 |
bors | -0.033 |
Token | snow |
Token ID | 6729 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
burn | +0.065 |
blowing | +0.057 |
waving | +0.055 |
typing | +0.053 |
itating | +0.052 |
Neg logit contributions | |
ounces | -0.077 |
affe | -0.070 |
isy | -0.068 |
hell | -0.067 |
izards | -0.067 |
Token | man |
Token ID | 805 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
burn | +0.128 |
waving | +0.120 |
blowing | +0.115 |
neighborhood | +0.103 |
typing | +0.103 |
Neg logit contributions | |
ounces | -0.210 |
affe | -0.195 |
ils | -0.193 |
hell | -0.193 |
isy | -0.188 |
Token | was |
Token ID | 373 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
burn | +0.048 |
blowing | +0.043 |
waving | +0.042 |
spinning | +0.035 |
crying | +0.035 |
Neg logit contributions | |
ounces | -0.113 |
izards | -0.105 |
ils | -0.103 |
bors | -0.103 |
affe | -0.103 |
Token | disappearing |
Token ID | 28867 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
burn | +0.039 |
waving | +0.033 |
neighborhood | +0.032 |
driveway | +0.032 |
blowing | +0.032 |
Neg logit contributions | |
ounces | -0.062 |
ils | -0.056 |
izards | -0.055 |
hell | -0.055 |
bors | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
burn | +0.010 |
waving | +0.009 |
blowing | +0.009 |
driveway | +0.009 |
neighborhood | +0.008 |
Neg logit contributions | |
ounces | -0.012 |
ils | -0.011 |
izards | -0.011 |
hell | -0.011 |
affe | -0.010 |
Token | She |
Token ID | 1375 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
ounces | +0.000 |
ils | +0.000 |
izards | +0.000 |
bors | +0.000 |
affe | +0.000 |
Neg logit contributions | |
burn | -0.000 |
waving | -0.000 |
blowing | -0.000 |
crying | -0.000 |
neighborhood | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
ounces | +0.003 |
ils | +0.002 |
hell | +0.002 |
affe | +0.002 |
izards | +0.002 |
Neg logit contributions | |
burn | -0.003 |
blowing | -0.003 |
waving | -0.003 |
driveway | -0.003 |
spinning | -0.002 |
Token | Jack |
Token ID | 3619 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ounces | +0.023 |
izards | +0.020 |
affe | +0.020 |
ils | +0.020 |
hell | +0.020 |
Neg logit contributions | |
burn | -0.022 |
blowing | -0.020 |
waving | -0.020 |
spinning | -0.018 |
crying | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
burn | +0.034 |
blowing | +0.028 |
waving | +0.028 |
driveway | +0.025 |
window | +0.025 |
Neg logit contributions | |
ounces | -0.039 |
ils | -0.038 |
hell | -0.036 |
affe | -0.036 |
bors | -0.036 |
Token | very |
Token ID | 845 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
burn | +0.029 |
driveway | +0.026 |
blowing | +0.024 |
neighborhood | +0.024 |
seat | +0.024 |
Neg logit contributions | |
ounces | -0.026 |
izards | -0.026 |
ily | -0.026 |
isy | -0.024 |
ns | -0.023 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ounces | +0.046 |
izards | +0.041 |
affe | +0.040 |
ils | +0.040 |
bors | +0.040 |
Neg logit contributions | |
burn | -0.036 |
blowing | -0.031 |
waving | -0.031 |
driveway | -0.028 |
neighborhood | -0.027 |
Token | living |
Token ID | 2877 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
burn | +0.010 |
driveway | +0.008 |
blowing | +0.008 |
waving | +0.008 |
salon | +0.008 |
Neg logit contributions | |
ounces | -0.007 |
izards | -0.007 |
affe | -0.007 |
ils | -0.007 |
hell | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
burn | +0.142 |
blowing | +0.125 |
waving | +0.124 |
driveway | +0.108 |
spinning | +0.106 |
Neg logit contributions | |
ounces | -0.210 |
ils | -0.194 |
izards | -0.191 |
hell | -0.185 |
bors | -0.185 |
Token | the |
Token ID | 262 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
burn | +0.072 |
blowing | +0.063 |
waving | +0.060 |
neighborhood | +0.058 |
driveway | +0.057 |
Neg logit contributions | |
ounces | -0.071 |
izards | -0.061 |
bors | -0.061 |
ils | -0.061 |
hell | -0.059 |
Token | woods |
Token ID | 16479 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
ounces | +0.023 |
affe | +0.021 |
ils | +0.020 |
bors | +0.020 |
isy | +0.020 |
Neg logit contributions | |
burn | -0.021 |
blowing | -0.019 |
waving | -0.018 |
typing | -0.017 |
vac | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
burn | +0.019 |
blowing | +0.016 |
waving | +0.016 |
daddy | +0.015 |
driveway | +0.015 |
Neg logit contributions | |
ounces | -0.023 |
ils | -0.021 |
izards | -0.020 |
hell | -0.020 |
affe | -0.020 |
Token | Every |
Token ID | 3887 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
ounces | +0.012 |
affe | +0.011 |
izards | +0.011 |
hell | +0.010 |
bors | +0.010 |
Neg logit contributions | |
burn | -0.015 |
blowing | -0.013 |
waving | -0.013 |
spinning | -0.012 |
crying | -0.011 |
Token | Snow |
Token ID | 7967 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
burn | +0.019 |
blowing | +0.017 |
waving | +0.017 |
neighborhood | +0.015 |
driveway | +0.015 |
Neg logit contributions | |
ounces | -0.021 |
ils | -0.019 |
izards | -0.018 |
bors | -0.018 |
affe | -0.018 |
Token | y |
Token ID | 88 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
burn | +0.036 |
waving | +0.032 |
blowing | +0.032 |
driveway | +0.027 |
spinning | +0.026 |
Neg logit contributions | |
ounces | -0.090 |
affe | -0.085 |
ils | -0.084 |
izards | -0.084 |
hell | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
burn | +0.008 |
blowing | +0.007 |
waving | +0.007 |
spinning | +0.006 |
crying | +0.006 |
Neg logit contributions | |
ounces | -0.010 |
izards | -0.009 |
ils | -0.009 |
bors | -0.009 |
affe | -0.009 |
Token | And |
Token ID | 843 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
burn | +0.041 |
blowing | +0.037 |
waving | +0.037 |
daddy | +0.034 |
crying | +0.033 |
Neg logit contributions | |
ounces | -0.039 |
ils | -0.036 |
bors | -0.035 |
izards | -0.035 |
affe | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ounces | +0.026 |
ils | +0.024 |
affe | +0.024 |
bors | +0.023 |
izards | +0.023 |
Neg logit contributions | |
burn | -0.026 |
waving | -0.024 |
blowing | -0.024 |
daddy | -0.023 |
spinning | -0.022 |
Token | living |
Token ID | 2877 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
burn | +0.057 |
blowing | +0.051 |
waving | +0.049 |
neighborhood | +0.043 |
leaning | +0.043 |
Neg logit contributions | |
ounces | -0.079 |
affe | -0.071 |
hell | -0.070 |
bors | -0.069 |
ils | -0.069 |
Token | room |
Token ID | 2119 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
burn | +0.111 |
blowing | +0.099 |
waving | +0.098 |
leaning | +0.082 |
driveway | +0.080 |
Neg logit contributions | |
ounces | -0.230 |
ils | -0.221 |
bors | -0.206 |
izards | -0.206 |
hell | -0.203 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
burn | +0.030 |
blowing | +0.027 |
waving | +0.026 |
spinning | +0.022 |
crying | +0.022 |
Neg logit contributions | |
ounces | -0.059 |
ils | -0.054 |
izards | -0.054 |
affe | -0.054 |
bors | -0.053 |
Token | Mom |
Token ID | 11254 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
burn | +0.033 |
waving | +0.030 |
blowing | +0.030 |
daddy | +0.027 |
spinning | +0.027 |
Neg logit contributions | |
ounces | -0.031 |
ils | -0.028 |
bors | -0.028 |
izards | -0.028 |
affe | -0.027 |
Token | will |
Token ID | 481 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
burn | +0.100 |
waving | +0.088 |
blowing | +0.087 |
driveway | +0.080 |
neighborhood | +0.080 |
Neg logit contributions | |
ounces | -0.174 |
ils | -0.165 |
affe | -0.157 |
bors | -0.156 |
hell | -0.156 |
Token | be |
Token ID | 307 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
burn | +0.022 |
blowing | +0.020 |
waving | +0.019 |
neighborhood | +0.018 |
leaning | +0.017 |
Neg logit contributions | |
ounces | -0.027 |
bors | -0.024 |
hell | -0.024 |
ils | -0.024 |
isy | -0.024 |
Token | The |
Token ID | 464 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ounces | +0.029 |
izards | +0.026 |
ils | +0.026 |
affe | +0.026 |
bors | +0.025 |
Neg logit contributions | |
burn | -0.021 |
blowing | -0.019 |
waving | -0.018 |
spinning | -0.017 |
neighborhood | -0.017 |
Token | dolls |
Token ID | 36062 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
burn | +0.031 |
blowing | +0.027 |
waving | +0.027 |
leaning | +0.022 |
spinning | +0.022 |
Neg logit contributions | |
ounces | -0.050 |
ils | -0.046 |
bors | -0.045 |
izards | -0.045 |
affe | -0.045 |
Token | were |
Token ID | 547 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
burn | +0.024 |
blowing | +0.021 |
waving | +0.021 |
spinning | +0.018 |
neighborhood | +0.018 |
Neg logit contributions | |
ounces | -0.039 |
ils | -0.036 |
izards | -0.035 |
affe | -0.035 |
bors | -0.035 |
Token | very |
Token ID | 845 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
burn | +0.023 |
blowing | +0.020 |
waving | +0.020 |
driveway | +0.019 |
neighborhood | +0.019 |
Neg logit contributions | |
ounces | -0.023 |
ils | -0.021 |
izards | -0.020 |
bors | -0.020 |
hell | -0.020 |
Token | happy |
Token ID | 3772 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
ounces | +0.042 |
ils | +0.038 |
izards | +0.037 |
bors | +0.037 |
hell | +0.037 |
Neg logit contributions | |
burn | -0.036 |
blowing | -0.030 |
waving | -0.030 |
driveway | -0.028 |
neighborhood | -0.027 |
Token | living |
Token ID | 2877 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
burn | +0.013 |
blowing | +0.010 |
waving | +0.010 |
driveway | +0.010 |
neighborhood | +0.009 |
Neg logit contributions | |
ounces | -0.020 |
ils | -0.019 |
izards | -0.019 |
affe | -0.018 |
hell | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
burn | +0.130 |
blowing | +0.115 |
waving | +0.114 |
spinning | +0.098 |
neighborhood | +0.097 |
Neg logit contributions | |
ounces | -0.220 |
ils | -0.200 |
izards | -0.198 |
affe | -0.198 |
bors | -0.197 |
Token | their |
Token ID | 511 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
burn | +0.080 |
blowing | +0.064 |
waving | +0.060 |
driveway | +0.060 |
icycle | +0.059 |
Neg logit contributions | |
ounces | -0.084 |
ils | -0.081 |
bors | -0.077 |
ily | -0.076 |
izards | -0.074 |
Token | new |
Token ID | 649 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ounces | +0.039 |
ils | +0.038 |
bors | +0.035 |
hell | +0.035 |
affe | +0.034 |
Neg logit contributions | |
burn | -0.024 |
blowing | -0.021 |
waving | -0.019 |
leaning | -0.016 |
spinning | -0.015 |
Token | house |
Token ID | 2156 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
burn | +0.027 |
blowing | +0.024 |
waving | +0.022 |
leaning | +0.018 |
spinning | +0.017 |
Neg logit contributions | |
ounces | -0.057 |
ils | -0.054 |
bors | -0.052 |
affe | -0.051 |
hell | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
burn | +0.027 |
blowing | +0.023 |
waving | +0.023 |
spinning | +0.020 |
driveway | +0.020 |
Neg logit contributions | |
ounces | -0.045 |
ils | -0.041 |
affe | -0.040 |
izards | -0.040 |
hell | -0.040 |
Token | she |
Token ID | 673 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
burn | +0.046 |
blowing | +0.041 |
waving | +0.040 |
driveway | +0.037 |
neighborhood | +0.037 |
Neg logit contributions | |
ounces | -0.048 |
affe | -0.042 |
izards | -0.042 |
bors | -0.042 |
ils | -0.042 |
Token | was |
Token ID | 373 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ounces | +0.017 |
izards | +0.015 |
affe | +0.015 |
ils | +0.015 |
hell | +0.015 |
Neg logit contributions | |
burn | -0.010 |
waving | -0.009 |
blowing | -0.009 |
spinning | -0.008 |
daddy | -0.008 |
Token | glad |
Token ID | 9675 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
burn | +0.028 |
blowing | +0.025 |
waving | +0.025 |
spinning | +0.022 |
daddy | +0.022 |
Neg logit contributions | |
ounces | -0.035 |
ils | -0.032 |
affe | -0.032 |
izards | -0.031 |
bors | -0.031 |
Token | she |
Token ID | 673 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
burn | +0.025 |
blowing | +0.022 |
waving | +0.022 |
spinning | +0.019 |
daddy | +0.019 |
Neg logit contributions | |
ounces | -0.036 |
ils | -0.033 |
affe | -0.032 |
izards | -0.032 |
bors | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ounces | +0.003 |
affe | +0.002 |
izards | +0.002 |
hell | +0.002 |
bors | +0.002 |
Neg logit contributions | |
burn | -0.001 |
waving | -0.001 |
blowing | -0.001 |
spinning | -0.001 |
my | -0.001 |
Token | living |
Token ID | 2877 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
burn | +0.034 |
waving | +0.032 |
blowing | +0.032 |
spinning | +0.029 |
crying | +0.028 |
Neg logit contributions | |
ounces | -0.044 |
affe | -0.040 |
ils | -0.039 |
hell | -0.039 |
izards | -0.039 |
Token | in |
Token ID | 287 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
burn | +0.126 |
blowing | +0.112 |
waving | +0.112 |
spinning | +0.096 |
neighborhood | +0.095 |
Neg logit contributions | |
ounces | -0.222 |
affe | -0.202 |
ils | -0.202 |
izards | -0.201 |
bors | -0.200 |
Token | such |
Token ID | 884 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
burn | +0.044 |
blowing | +0.038 |
waving | +0.036 |
driveway | +0.034 |
neighborhood | +0.033 |
Neg logit contributions | |
ounces | -0.053 |
ils | -0.048 |
izards | -0.047 |
bors | -0.046 |
hell | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
ounces | +0.076 |
affe | +0.070 |
ils | +0.069 |
izards | +0.069 |
bors | +0.068 |
Neg logit contributions | |
burn | -0.037 |
waving | -0.035 |
blowing | -0.034 |
spinning | -0.030 |
daddy | -0.030 |
Token | tidy |
Token ID | 43044 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
burn | +0.024 |
blowing | +0.022 |
waving | +0.021 |
leaning | +0.019 |
driveway | +0.019 |
Neg logit contributions | |
ounces | -0.027 |
bors | -0.024 |
hell | -0.024 |
affe | -0.024 |
ils | -0.024 |
Token | home |
Token ID | 1363 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
burn | +0.041 |
blowing | +0.035 |
waving | +0.033 |
leaning | +0.028 |
spinning | +0.028 |
Neg logit contributions | |
ounces | -0.070 |
affe | -0.064 |
bors | -0.063 |
hell | -0.063 |
ils | -0.063 |
Token | box |
Token ID | 3091 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
bors | +0.009 |
ounces | +0.009 |
izards | +0.009 |
ils | +0.009 |
affe | +0.009 |
Neg logit contributions | |
waving | -0.007 |
blowing | -0.007 |
burn | -0.007 |
window | -0.007 |
spinning | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
ounces | +0.045 |
ils | +0.041 |
izards | +0.041 |
affe | +0.041 |
bors | +0.041 |
Neg logit contributions | |
burn | -0.024 |
blowing | -0.022 |
waving | -0.021 |
spinning | -0.018 |
neighborhood | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
burn | +0.013 |
blowing | +0.011 |
waving | +0.011 |
driveway | +0.010 |
neighborhood | +0.010 |
Neg logit contributions | |
ounces | -0.017 |
ils | -0.015 |
bors | -0.015 |
hell | -0.015 |
izards | -0.015 |
Token | when |
Token ID | 618 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
burn | +0.008 |
blowing | +0.007 |
waving | +0.007 |
neighborhood | +0.006 |
daddy | +0.006 |
Neg logit contributions | |
ounces | -0.013 |
ils | -0.011 |
bors | -0.011 |
izards | -0.011 |
affe | -0.011 |
Token | Mama |
Token ID | 40084 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
burn | +0.048 |
waving | +0.042 |
blowing | +0.042 |
driveway | +0.038 |
neighborhood | +0.038 |
Neg logit contributions | |
ounces | -0.059 |
bors | -0.052 |
izards | -0.052 |
ils | -0.051 |
affe | -0.049 |
Token | stopped |
Token ID | 5025 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
burn | +0.045 |
blowing | +0.041 |
waving | +0.041 |
daddy | +0.035 |
spinning | +0.035 |
Neg logit contributions | |
ounces | -0.075 |
ils | -0.067 |
izards | -0.067 |
affe | -0.067 |
hell | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
burn | +0.150 |
waving | +0.119 |
driveway | +0.116 |
blowing | +0.116 |
neighborhood | +0.110 |
Neg logit contributions | |
ounces | -0.195 |
izards | -0.177 |
bors | -0.174 |
ils | -0.174 |
affe | -0.165 |
Token | � |
Token ID | 6184 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
ounces | +0.004 |
ils | +0.004 |
izards | +0.004 |
affe | +0.004 |
bors | +0.004 |
Neg logit contributions | |
burn | -0.002 |
blowing | -0.002 |
waving | -0.002 |
spinning | -0.002 |
daddy | -0.002 |
Token | � |
Token ID | 95 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ounces | +0.087 |
izards | +0.080 |
affe | +0.079 |
hell | +0.078 |
ils | +0.078 |
Neg logit contributions | |
burn | -0.080 |
blowing | -0.074 |
waving | -0.072 |
leaning | -0.068 |
spinning | -0.067 |
Token | € |
Token ID | 26391 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
izards | +0.054 |
ounces | +0.054 |
affe | +0.050 |
ils | +0.050 |
mushrooms | +0.050 |
Neg logit contributions | |
burn | -0.049 |
waving | -0.046 |
blowing | -0.045 |
neighborhood | -0.045 |
driveway | -0.044 |
Token | � |
Token ID | 129 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ounces | +0.077 |
ils | +0.069 |
izards | +0.068 |
affe | +0.067 |
bors | +0.067 |
Neg logit contributions | |
burn | -0.062 |
waving | -0.056 |
blowing | -0.056 |
neighborhood | -0.052 |
driveway | -0.050 |
Token | you |
Token ID | 345 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
burn | +0.012 |
blowing | +0.011 |
waving | +0.011 |
crying | +0.011 |
daddy | +0.010 |
Neg logit contributions | |
ounces | -0.014 |
ils | -0.013 |
affe | -0.013 |
hell | -0.012 |
izards | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ounces | +0.096 |
ils | +0.087 |
bors | +0.086 |
izards | +0.084 |
affe | +0.082 |
Neg logit contributions | |
burn | -0.065 |
blowing | -0.059 |
waving | -0.059 |
crying | -0.054 |
my | -0.054 |
Token | You |
Token ID | 921 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
burn | +0.031 |
waving | +0.028 |
blowing | +0.028 |
daddy | +0.026 |
spinning | +0.025 |
Neg logit contributions | |
ounces | -0.042 |
ils | -0.039 |
hell | -0.038 |
izards | -0.037 |
bors | -0.037 |
Token | are |
Token ID | 389 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ounces | +0.072 |
bors | +0.064 |
izards | +0.062 |
ils | +0.062 |
affe | +0.062 |
Neg logit contributions | |
burn | -0.046 |
blowing | -0.042 |
waving | -0.041 |
my | -0.038 |
daddy | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
burn | +0.022 |
waving | +0.021 |
blowing | +0.021 |
spinning | +0.018 |
crying | +0.018 |
Neg logit contributions | |
ounces | -0.038 |
affe | -0.034 |
bors | -0.034 |
ils | -0.034 |
hell | -0.034 |
Token | living |
Token ID | 2877 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
burn | +0.093 |
blowing | +0.086 |
waving | +0.083 |
driveway | +0.077 |
my | +0.075 |
Neg logit contributions | |
ounces | -0.090 |
affe | -0.079 |
ils | -0.078 |
bors | -0.076 |
hell | -0.076 |
Token | thing |
Token ID | 1517 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
burn | +0.144 |
blowing | +0.130 |
waving | +0.126 |
driveway | +0.111 |
leaning | +0.108 |
Neg logit contributions | |
ounces | -0.204 |
ils | -0.187 |
izards | -0.182 |
affe | -0.180 |
bors | -0.179 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ounces | +0.003 |
bors | +0.003 |
ils | +0.003 |
hell | +0.003 |
izards | +0.003 |
Neg logit contributions | |
burn | -0.002 |
waving | -0.001 |
blowing | -0.001 |
crying | -0.001 |
spinning | -0.001 |
Token | You |
Token ID | 921 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
burn | +0.043 |
waving | +0.039 |
blowing | +0.039 |
daddy | +0.035 |
spinning | +0.035 |
Neg logit contributions | |
ounces | -0.051 |
ils | -0.047 |
hell | -0.046 |
izards | -0.045 |
bors | -0.045 |
Token | have |
Token ID | 423 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ounces | +0.072 |
bors | +0.064 |
izards | +0.062 |
affe | +0.062 |
ils | +0.061 |
Neg logit contributions | |
burn | -0.045 |
blowing | -0.041 |
waving | -0.040 |
my | -0.038 |
daddy | -0.037 |
Token | feelings |
Token ID | 7666 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
burn | +0.024 |
blowing | +0.021 |
waving | +0.020 |
driveway | +0.018 |
spinning | +0.017 |
Neg logit contributions | |
ounces | -0.042 |
ils | -0.039 |
izards | -0.038 |
affe | -0.038 |
bors | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
ounces | +0.077 |
bors | +0.069 |
affe | +0.069 |
ils | +0.068 |
izards | +0.068 |
Neg logit contributions | |
burn | -0.042 |
blowing | -0.041 |
waving | -0.041 |
spinning | -0.035 |
crying | -0.034 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ounces | +0.002 |
ils | +0.002 |
izards | +0.002 |
affe | +0.002 |
bors | +0.002 |
Neg logit contributions | |
burn | -0.001 |
blowing | -0.001 |
waving | -0.001 |
spinning | -0.001 |
neighborhood | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
burn | +0.023 |
waving | +0.022 |
blowing | +0.022 |
neighborhood | +0.019 |
daddy | +0.019 |
Neg logit contributions | |
ounces | -0.048 |
izards | -0.044 |
ils | -0.044 |
hell | -0.043 |
affe | -0.043 |
Token | M |
Token ID | 337 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
burn | +0.041 |
blowing | +0.038 |
waving | +0.038 |
daddy | +0.035 |
spinning | +0.033 |
Neg logit contributions | |
ounces | -0.064 |
affe | -0.059 |
ils | -0.058 |
izards | -0.057 |
hell | -0.057 |
Token | illy |
Token ID | 6548 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
burn | +0.043 |
blowing | +0.040 |
waving | +0.040 |
driveway | +0.037 |
spinning | +0.037 |
Neg logit contributions | |
ounces | -0.028 |
ils | -0.024 |
izards | -0.024 |
affe | -0.024 |
bors | -0.024 |
Token | stopped |
Token ID | 5025 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
burn | +0.015 |
waving | +0.015 |
blowing | +0.014 |
daddy | +0.012 |
my | +0.012 |
Neg logit contributions | |
ounces | -0.035 |
bors | -0.031 |
izards | -0.031 |
affe | -0.031 |
hell | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
burn | +0.145 |
driveway | +0.126 |
icycle | +0.113 |
salon | +0.110 |
waving | +0.109 |
Neg logit contributions | |
izards | -0.181 |
ounces | -0.180 |
mushrooms | -0.178 |
ils | -0.177 |
bors | -0.172 |
Token | discuss |
Token ID | 2112 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
burn | +0.009 |
waving | +0.008 |
blowing | +0.008 |
spinning | +0.007 |
daddy | +0.006 |
Neg logit contributions | |
ounces | -0.018 |
ils | -0.017 |
izards | -0.017 |
affe | -0.017 |
bors | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
ounces | +0.036 |
affe | +0.033 |
bors | +0.032 |
izards | +0.031 |
ils | +0.031 |
Neg logit contributions | |
burn | -0.020 |
waving | -0.019 |
blowing | -0.019 |
crying | -0.016 |
spinning | -0.016 |
Token | berries |
Token ID | 36322 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
burn | +0.011 |
waving | +0.011 |
blowing | +0.011 |
my | +0.011 |
neighborhood | +0.010 |
Neg logit contributions | |
ounces | -0.010 |
affe | -0.009 |
izards | -0.009 |
bors | -0.008 |
ils | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
ounces | +0.018 |
bors | +0.016 |
affe | +0.016 |
ils | +0.015 |
izards | +0.015 |
Neg logit contributions | |
blowing | -0.008 |
burn | -0.008 |
waving | -0.008 |
crying | -0.006 |
my | -0.006 |
Token | you |
Token ID | 345 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
burn | +0.026 |
blowing | +0.023 |
waving | +0.023 |
driveway | +0.023 |
neighborhood | +0.022 |
Neg logit contributions | |
ounces | -0.021 |
affe | -0.019 |
izards | -0.019 |
ils | -0.019 |
bors | -0.018 |
Token | glad |
Token ID | 9675 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ounces | +0.098 |
affe | +0.089 |
ils | +0.089 |
bors | +0.089 |
izards | +0.089 |
Neg logit contributions | |
burn | -0.068 |
blowing | -0.061 |
waving | -0.060 |
driveway | -0.054 |
neighborhood | -0.052 |
Token | that |
Token ID | 326 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
burn | +0.003 |
blowing | +0.003 |
waving | +0.003 |
driveway | +0.003 |
spinning | +0.003 |
Neg logit contributions | |
ounces | -0.003 |
ils | -0.003 |
izards | -0.003 |
affe | -0.003 |
bors | -0.003 |
Token | you |
Token ID | 345 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
burn | +0.092 |
blowing | +0.083 |
waving | +0.083 |
driveway | +0.077 |
neighborhood | +0.075 |
Neg logit contributions | |
ounces | -0.095 |
affe | -0.086 |
ils | -0.085 |
bors | -0.085 |
izards | -0.084 |
Token | are |
Token ID | 389 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
ounces | +0.036 |
ils | +0.033 |
izards | +0.033 |
affe | +0.033 |
bors | +0.033 |
Neg logit contributions | |
burn | -0.022 |
blowing | -0.020 |
waving | -0.019 |
spinning | -0.017 |
neighborhood | -0.017 |
Token | living |
Token ID | 2877 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
burn | +0.019 |
blowing | +0.016 |
waving | +0.016 |
driveway | +0.014 |
neighborhood | +0.014 |
Neg logit contributions | |
ounces | -0.029 |
ils | -0.027 |
izards | -0.027 |
bors | -0.027 |
affe | -0.026 |
Token | in |
Token ID | 287 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
burn | +0.152 |
blowing | +0.135 |
waving | +0.132 |
driveway | +0.120 |
leaning | +0.115 |
Neg logit contributions | |
ounces | -0.194 |
ils | -0.182 |
izards | -0.175 |
bors | -0.170 |
hell | -0.170 |
Token | the |
Token ID | 262 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
burn | +0.091 |
blowing | +0.078 |
waving | +0.076 |
driveway | +0.072 |
leaning | +0.068 |
Neg logit contributions | |
ounces | -0.101 |
ils | -0.091 |
izards | -0.088 |
bors | -0.088 |
hell | -0.086 |
Token | forest |
Token ID | 8222 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
burn | +0.016 |
blowing | +0.014 |
waving | +0.014 |
spinning | +0.011 |
daddy | +0.011 |
Neg logit contributions | |
ounces | -0.025 |
ils | -0.023 |
affe | -0.022 |
hell | -0.022 |
bors | -0.022 |
Token | ?" |
Token ID | 1701 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
burn | +0.010 |
blowing | +0.010 |
waving | +0.009 |
neighborhood | +0.008 |
my | +0.008 |
Neg logit contributions | |
ounces | -0.016 |
izards | -0.015 |
affe | -0.014 |
ils | -0.014 |
bors | -0.014 |
Token | |
Token ID | 220 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
ounces | +0.003 |
ils | +0.003 |
izards | +0.003 |
bors | +0.003 |
hell | +0.003 |
Neg logit contributions | |
burn | -0.001 |
waving | -0.001 |
blowing | -0.001 |
daddy | -0.001 |
crying | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
burn | +0.033 |
blowing | +0.027 |
waving | +0.027 |
driveway | +0.026 |
rolling | +0.024 |
Neg logit contributions | |
ounces | -0.039 |
hell | -0.036 |
ils | -0.036 |
izards | -0.036 |
affe | -0.035 |
Token | sad |
Token ID | 6507 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
burn | +0.013 |
blowing | +0.012 |
waving | +0.012 |
crying | +0.010 |
spinning | +0.010 |
Neg logit contributions | |
ounces | -0.022 |
affe | -0.020 |
ils | -0.020 |
izards | -0.020 |
bors | -0.020 |
Token | because |
Token ID | 780 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ounces | +0.011 |
ils | +0.010 |
izards | +0.010 |
affe | +0.010 |
bors | +0.010 |
Neg logit contributions | |
burn | -0.009 |
blowing | -0.008 |
waving | -0.008 |
spinning | -0.007 |
neighborhood | -0.007 |
Token | she |
Token ID | 673 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
burn | +0.030 |
blowing | +0.026 |
waving | +0.025 |
driveway | +0.024 |
neighborhood | +0.023 |
Neg logit contributions | |
ounces | -0.029 |
izards | -0.026 |
ils | -0.025 |
bors | -0.025 |
hell | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
burn | +0.013 |
blowing | +0.012 |
waving | +0.011 |
spinning | +0.010 |
driveway | +0.010 |
Neg logit contributions | |
ounces | -0.025 |
ils | -0.022 |
izards | -0.022 |
affe | -0.022 |
bors | -0.022 |
Token | living |
Token ID | 2877 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
burn | +0.037 |
blowing | +0.032 |
waving | +0.031 |
driveway | +0.029 |
neighborhood | +0.028 |
Neg logit contributions | |
ounces | -0.055 |
ils | -0.051 |
izards | -0.051 |
bors | -0.050 |
hell | -0.049 |
Token | all |
Token ID | 477 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
burn | +0.150 |
blowing | +0.134 |
waving | +0.132 |
driveway | +0.118 |
spinning | +0.113 |
Neg logit contributions | |
ounces | -0.196 |
ils | -0.182 |
izards | -0.178 |
hell | -0.170 |
bors | -0.170 |
Token | by |
Token ID | 416 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
burn | +0.097 |
blowing | +0.087 |
waving | +0.086 |
driveway | +0.079 |
neighborhood | +0.078 |
Neg logit contributions | |
ounces | -0.095 |
ils | -0.086 |
izards | -0.084 |
hell | -0.083 |
bors | -0.082 |
Token | herself |
Token ID | 5223 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
burn | +0.011 |
blowing | +0.010 |
waving | +0.010 |
spinning | +0.009 |
neighborhood | +0.009 |
Neg logit contributions | |
ounces | -0.010 |
ils | -0.009 |
izards | -0.009 |
affe | -0.009 |
bors | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
ounces | +0.031 |
ils | +0.028 |
affe | +0.028 |
izards | +0.028 |
bors | +0.028 |
Neg logit contributions | |
burn | -0.022 |
blowing | -0.020 |
waving | -0.020 |
spinning | -0.017 |
neighborhood | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
burn | +0.008 |
blowing | +0.007 |
waving | +0.006 |
spinning | +0.005 |
driveway | +0.005 |
Neg logit contributions | |
ounces | -0.014 |
affe | -0.013 |
izards | -0.013 |
ils | -0.013 |
bors | -0.013 |
Token | run |
Token ID | 1057 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
burn | +0.011 |
blowing | +0.009 |
waving | +0.009 |
spinning | +0.008 |
neighborhood | +0.008 |
Neg logit contributions | |
ounces | -0.018 |
ils | -0.017 |
izards | -0.017 |
affe | -0.017 |
bors | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
ounces | +0.059 |
ils | +0.053 |
affe | +0.052 |
izards | +0.052 |
bors | +0.052 |
Neg logit contributions | |
burn | -0.034 |
blowing | -0.030 |
waving | -0.030 |
spinning | -0.026 |
crying | -0.025 |
Token | but |
Token ID | 475 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
burn | +0.009 |
blowing | +0.008 |
waving | +0.008 |
neighborhood | +0.007 |
driveway | +0.007 |
Neg logit contributions | |
ounces | -0.012 |
izards | -0.010 |
affe | -0.010 |
ils | -0.010 |
bors | -0.010 |
Token | his |
Token ID | 465 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
ounces | +0.007 |
ils | +0.006 |
izards | +0.006 |
affe | +0.006 |
bors | +0.006 |
Neg logit contributions | |
burn | -0.006 |
blowing | -0.005 |
waving | -0.005 |
neighborhood | -0.005 |
driveway | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
burn | +0.023 |
blowing | +0.022 |
ric | +0.019 |
waving | +0.018 |
typing | +0.018 |
Neg logit contributions | |
ounces | -0.028 |
affe | -0.025 |
hell | -0.024 |
ily | -0.024 |
ger | -0.023 |
Token | stopped |
Token ID | 5025 |
Feature activation | -6.05e+00 |
Pos logit contributions | |
burn | +0.113 |
blowing | +0.100 |
waving | +0.099 |
driveway | +0.094 |
spinning | +0.090 |
Neg logit contributions | |
ounces | -0.122 |
ils | -0.112 |
affe | -0.112 |
isy | -0.108 |
izards | -0.107 |
Token | him |
Token ID | 683 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
burn | +0.154 |
driveway | +0.141 |
icycle | +0.127 |
tr | +0.122 |
bars | +0.120 |
Neg logit contributions | |
ounces | -0.146 |
izards | -0.142 |
bors | -0.139 |
ocol | -0.137 |
ily | -0.134 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
burn | +0.018 |
blowing | +0.015 |
waving | +0.015 |
neighborhood | +0.014 |
driveway | +0.014 |
Neg logit contributions | |
ounces | -0.023 |
ils | -0.020 |
hell | -0.020 |
affe | -0.020 |
izards | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
ounces | +0.005 |
affe | +0.005 |
izards | +0.005 |
bors | +0.005 |
ils | +0.005 |
Neg logit contributions | |
burn | -0.006 |
blowing | -0.005 |
waving | -0.005 |
crying | -0.005 |
driveway | -0.005 |
Token | Wait |
Token ID | 21321 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
ounces | +0.021 |
ils | +0.019 |
affe | +0.019 |
bors | +0.019 |
izards | +0.019 |
Neg logit contributions | |
burn | -0.015 |
blowing | -0.014 |
waving | -0.014 |
spinning | -0.012 |
daddy | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ounces | +0.026 |
ils | +0.023 |
bors | +0.023 |
izards | +0.023 |
affe | +0.023 |
Neg logit contributions | |
burn | -0.016 |
waving | -0.015 |
blowing | -0.015 |
spinning | -0.013 |
daddy | -0.013 |
Token | The |
Token ID | 383 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
burn | +0.002 |
waving | +0.001 |
blowing | +0.001 |
daddy | +0.001 |
neighborhood | +0.001 |
Neg logit contributions | |
ounces | -0.003 |
ils | -0.003 |
bors | -0.003 |
izards | -0.003 |
hell | -0.003 |
Token | animals |
Token ID | 4695 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
burn | +0.020 |
blowing | +0.018 |
waving | +0.018 |
neighborhood | +0.016 |
daddy | +0.016 |
Neg logit contributions | |
ounces | -0.022 |
ils | -0.019 |
izards | -0.019 |
bors | -0.019 |
hell | -0.019 |
Token | were |
Token ID | 547 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
burn | +0.027 |
blowing | +0.025 |
waving | +0.025 |
crying | +0.021 |
spinning | +0.021 |
Neg logit contributions | |
ounces | -0.048 |
affe | -0.043 |
bors | -0.043 |
izards | -0.042 |
ils | -0.042 |
Token | very |
Token ID | 845 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
burn | +0.022 |
blowing | +0.018 |
driveway | +0.018 |
waving | +0.017 |
neighborhood | +0.016 |
Neg logit contributions | |
ounces | -0.028 |
izards | -0.027 |
ils | -0.027 |
bors | -0.026 |
affe | -0.026 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
ounces | +0.055 |
ils | +0.050 |
izards | +0.050 |
affe | +0.049 |
bors | +0.049 |
Neg logit contributions | |
burn | -0.039 |
blowing | -0.034 |
waving | -0.033 |
driveway | -0.031 |
spinning | -0.030 |
Token | living |
Token ID | 2877 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
burn | +0.005 |
blowing | +0.004 |
waving | +0.004 |
driveway | +0.004 |
spinning | +0.003 |
Neg logit contributions | |
ounces | -0.008 |
izards | -0.008 |
ils | -0.008 |
affe | -0.008 |
bors | -0.008 |
Token | on |
Token ID | 319 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
burn | +0.106 |
blowing | +0.099 |
waving | +0.098 |
crying | +0.084 |
neighborhood | +0.084 |
Neg logit contributions | |
ounces | -0.241 |
affe | -0.224 |
hell | -0.215 |
bors | -0.214 |
isy | -0.211 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
burn | +0.017 |
waving | +0.015 |
blowing | +0.015 |
spinning | +0.012 |
leaning | +0.012 |
Neg logit contributions | |
ounces | -0.039 |
affe | -0.035 |
izards | -0.035 |
ils | -0.035 |
hell | -0.035 |
Token | farm |
Token ID | 5318 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ounces | +0.007 |
izards | +0.006 |
hell | +0.006 |
ils | +0.006 |
bors | +0.006 |
Neg logit contributions | |
burn | -0.004 |
blowing | -0.003 |
waving | -0.003 |
window | -0.003 |
neighborhood | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
ounces | +0.057 |
izards | +0.050 |
affe | +0.050 |
bors | +0.050 |
hell | +0.049 |
Neg logit contributions | |
burn | -0.027 |
waving | -0.026 |
blowing | -0.026 |
neighborhood | -0.022 |
crying | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
burn | +0.005 |
waving | +0.005 |
blowing | +0.005 |
neighborhood | +0.004 |
daddy | +0.004 |
Neg logit contributions | |
ounces | -0.017 |
ils | -0.016 |
bors | -0.015 |
izards | -0.015 |
hell | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
ounces | +0.003 |
bors | +0.002 |
ils | +0.002 |
izards | +0.002 |
affe | +0.002 |
Neg logit contributions | |
burn | -0.002 |
waving | -0.001 |
blowing | -0.001 |
spinning | -0.001 |
crying | -0.001 |
Token | One |
Token ID | 1881 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
burn | +0.001 |
blowing | +0.001 |
waving | +0.001 |
spinning | +0.001 |
neighborhood | +0.001 |
Neg logit contributions | |
ounces | -0.002 |
ils | -0.001 |
izards | -0.001 |
bors | -0.001 |
affe | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
burn | +0.009 |
waving | +0.008 |
blowing | +0.008 |
driveway | +0.007 |
spinning | +0.007 |
Neg logit contributions | |
ounces | -0.018 |
affe | -0.017 |
hell | -0.016 |
isy | -0.016 |
ils | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
ounces | +0.024 |
affe | +0.022 |
ils | +0.021 |
izards | +0.021 |
hell | +0.021 |
Neg logit contributions | |
burn | -0.016 |
blowing | -0.015 |
waving | -0.014 |
driveway | -0.013 |
neighborhood | -0.013 |
Token | Wh |
Token ID | 854 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
ounces | +0.006 |
ils | +0.006 |
izards | +0.006 |
affe | +0.006 |
bors | +0.006 |
Neg logit contributions | |
burn | -0.004 |
blowing | -0.004 |
waving | -0.004 |
spinning | -0.003 |
neighborhood | -0.003 |
Token | isk |
Token ID | 1984 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
ounces | +0.088 |
bors | +0.077 |
ils | +0.077 |
izards | +0.077 |
affe | +0.076 |
Neg logit contributions | |
burn | -0.064 |
blowing | -0.057 |
waving | -0.056 |
my | -0.052 |
neighborhood | -0.051 |
Token | ers |
Token ID | 364 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
ounces | +0.094 |
affe | +0.069 |
cents | +0.064 |
ocol | +0.064 |
mmm | +0.064 |
Neg logit contributions | |
burn | -0.208 |
blowing | -0.199 |
my | -0.190 |
waving | -0.189 |
neighborhood | -0.178 |
Token | went |
Token ID | 1816 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
ounces | +0.016 |
ils | +0.015 |
affe | +0.014 |
izards | +0.014 |
bors | +0.014 |
Neg logit contributions | |
burn | -0.011 |
blowing | -0.010 |
waving | -0.010 |
spinning | -0.009 |
driveway | -0.008 |
Token | on |
Token ID | 319 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
burn | +0.017 |
blowing | +0.015 |
waving | +0.014 |
daddy | +0.014 |
driveway | +0.013 |
Neg logit contributions | |
ounces | -0.026 |
ils | -0.025 |
izards | -0.025 |
affe | -0.025 |
hell | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
ounces | +0.045 |
ils | +0.043 |
izards | +0.042 |
mushrooms | +0.041 |
bors | +0.040 |
Neg logit contributions | |
burn | -0.056 |
blowing | -0.048 |
waving | -0.046 |
driveway | -0.046 |
daddy | -0.045 |
Token | walk |
Token ID | 2513 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
ounces | +0.029 |
hell | +0.027 |
affe | +0.027 |
isy | +0.027 |
bors | +0.027 |
Neg logit contributions | |
burn | -0.014 |
blowing | -0.012 |
waving | -0.012 |
leaning | -0.010 |
seat | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
burn | +0.008 |
blowing | +0.007 |
waving | +0.007 |
daddy | +0.006 |
crying | +0.005 |
Neg logit contributions | |
ounces | -0.022 |
ils | -0.020 |
affe | -0.020 |
izards | -0.020 |
bors | -0.020 |
Token | pet |
Token ID | 4273 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
burn | +0.007 |
blowing | +0.006 |
waving | +0.006 |
neighborhood | +0.005 |
driveway | +0.005 |
Neg logit contributions | |
ounces | -0.011 |
affe | -0.010 |
ils | -0.010 |
izards | -0.010 |
bors | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ounces | +0.051 |
ils | +0.046 |
bors | +0.046 |
hell | +0.045 |
izards | +0.045 |
Neg logit contributions | |
burn | -0.033 |
waving | -0.028 |
blowing | -0.027 |
my | -0.025 |
daddy | -0.025 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
burn | +0.010 |
blowing | +0.009 |
waving | +0.008 |
spinning | +0.008 |
driveway | +0.007 |
Neg logit contributions | |
ounces | -0.012 |
affe | -0.011 |
ils | -0.011 |
bors | -0.011 |
izards | -0.011 |
Token | in |
Token ID | 259 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
burn | +0.032 |
blowing | +0.029 |
waving | +0.028 |
neighborhood | +0.025 |
my | +0.025 |
Neg logit contributions | |
ounces | -0.035 |
ils | -0.031 |
bors | -0.031 |
izards | -0.031 |
affe | -0.030 |
Token | oc |
Token ID | 420 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
ounces | +0.011 |
izards | +0.011 |
ils | +0.011 |
bors | +0.010 |
ilies | +0.009 |
Neg logit contributions | |
burn | -0.015 |
waving | -0.014 |
blowing | -0.014 |
my | -0.014 |
daddy | -0.013 |
Token | eros |
Token ID | 27498 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
ounces | +0.115 |
izards | +0.101 |
ils | +0.100 |
bors | +0.098 |
hell | +0.096 |
Neg logit contributions | |
burn | -0.188 |
blowing | -0.175 |
waving | -0.174 |
crying | -0.159 |
neighborhood | -0.159 |
Token | . |
Token ID | 13 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
ounces | +0.024 |
bors | +0.022 |
izards | +0.022 |
ils | +0.021 |
hell | +0.020 |
Neg logit contributions | |
burn | -0.015 |
waving | -0.013 |
blowing | -0.013 |
my | -0.012 |
crying | -0.012 |
Token | It |
Token ID | 632 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
burn | +0.024 |
waving | +0.023 |
daddy | +0.021 |
crying | +0.021 |
blowing | +0.021 |
Neg logit contributions | |
ils | -0.030 |
ounces | -0.030 |
bors | -0.028 |
hell | -0.027 |
isy | -0.027 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
burn | +0.002 |
waving | +0.002 |
blowing | +0.002 |
crying | +0.002 |
spinning | +0.002 |
Neg logit contributions | |
ounces | -0.005 |
izards | -0.004 |
ils | -0.004 |
bors | -0.004 |
affe | -0.004 |
Token | so |
Token ID | 523 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ounces | +0.009 |
affe | +0.008 |
ils | +0.008 |
bors | +0.008 |
izards | +0.008 |
Neg logit contributions | |
burn | -0.005 |
waving | -0.005 |
blowing | -0.005 |
crying | -0.004 |
spinning | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
ounces | +0.020 |
ils | +0.018 |
izards | +0.018 |
affe | +0.018 |
bors | +0.018 |
Neg logit contributions | |
burn | -0.014 |
blowing | -0.013 |
waving | -0.013 |
driveway | -0.011 |
neighborhood | -0.011 |
Token | sign |
Token ID | 1051 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
burn | +0.015 |
blowing | +0.013 |
waving | +0.012 |
driveway | +0.011 |
leaning | +0.011 |
Neg logit contributions | |
ounces | -0.021 |
affe | -0.019 |
hell | -0.019 |
bors | -0.018 |
isy | -0.018 |
Token | that |
Token ID | 326 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
ounces | +0.067 |
affe | +0.062 |
ils | +0.060 |
hell | +0.060 |
izards | +0.060 |
Neg logit contributions | |
burn | -0.076 |
blowing | -0.066 |
waving | -0.063 |
neighborhood | -0.061 |
driveway | -0.060 |
Token | said |
Token ID | 531 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ounces | +0.029 |
affe | +0.026 |
bors | +0.026 |
ils | +0.026 |
hell | +0.026 |
Neg logit contributions | |
burn | -0.017 |
waving | -0.016 |
blowing | -0.016 |
daddy | -0.014 |
spinning | -0.013 |
Token | " |
Token ID | 366 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
ounces | +0.092 |
ils | +0.087 |
bors | +0.082 |
izards | +0.081 |
affe | +0.081 |
Neg logit contributions | |
waving | -0.033 |
blowing | -0.029 |
spinning | -0.026 |
burn | -0.026 |
daddy | -0.025 |
Token | P |
Token ID | 47 |
Feature activation | +6.44e+00 |
Pos logit contributions | |
ounces | +0.023 |
ils | +0.021 |
izards | +0.021 |
bors | +0.020 |
hell | +0.020 |
Neg logit contributions | |
burn | -0.019 |
blowing | -0.017 |
waving | -0.016 |
my | -0.015 |
neighborhood | -0.014 |
Token | engu |
Token ID | 13561 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
bors | +0.173 |
ounces | +0.172 |
ils | +0.171 |
isy | +0.159 |
izards | +0.155 |
Neg logit contributions | |
burn | -0.159 |
waving | -0.137 |
my | -0.136 |
rou | -0.132 |
blowing | -0.132 |
Token | ins |
Token ID | 1040 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
burn | +0.026 |
blowing | +0.024 |
waving | +0.022 |
my | +0.022 |
m | +0.019 |
Neg logit contributions | |
ounces | -0.039 |
bors | -0.036 |
affe | -0.036 |
ger | -0.035 |
nic | -0.034 |
Token | are |
Token ID | 389 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
ounces | +0.049 |
bors | +0.044 |
hell | +0.041 |
izards | +0.041 |
isy | +0.041 |
Neg logit contributions | |
burn | -0.047 |
blowing | -0.044 |
waving | -0.044 |
my | -0.040 |
daddy | -0.039 |
Token | sleeping |
Token ID | 11029 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
ounces | +0.021 |
izards | +0.019 |
hell | +0.019 |
affe | +0.019 |
ils | +0.019 |
Neg logit contributions | |
waving | -0.011 |
blowing | -0.011 |
burn | -0.010 |
spinning | -0.009 |
leaning | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
burn | +0.015 |
blowing | +0.015 |
waving | +0.014 |
daddy | +0.013 |
window | +0.013 |
Neg logit contributions | |
ounces | -0.018 |
bors | -0.016 |
izards | -0.016 |
hell | -0.016 |
affe | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
ounces | +0.014 |
affe | +0.013 |
izards | +0.013 |
hell | +0.013 |
bors | +0.013 |
Neg logit contributions | |
burn | -0.006 |
blowing | -0.006 |
waving | -0.006 |
daddy | -0.005 |
neighborhood | -0.005 |
Token | getting |
Token ID | 1972 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
burn | +0.017 |
blowing | +0.014 |
waving | +0.014 |
driveway | +0.013 |
neighborhood | +0.013 |
Neg logit contributions | |
ounces | -0.027 |
ils | -0.024 |
izards | -0.024 |
bors | -0.024 |
affe | -0.023 |
Token | ready |
Token ID | 3492 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
ounces | +0.012 |
ils | +0.011 |
izards | +0.011 |
bors | +0.011 |
hell | +0.011 |
Neg logit contributions | |
burn | -0.008 |
waving | -0.007 |
blowing | -0.007 |
driveway | -0.006 |
neighborhood | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
ounces | +0.032 |
ils | +0.030 |
affe | +0.030 |
izards | +0.030 |
bors | +0.029 |
Neg logit contributions | |
burn | -0.014 |
blowing | -0.012 |
waving | -0.012 |
spinning | -0.010 |
daddy | -0.010 |
Token | make |
Token ID | 787 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
burn | +0.000 |
blowing | +0.000 |
waving | +0.000 |
daddy | +0.000 |
spinning | +0.000 |
Neg logit contributions | |
ounces | -0.001 |
affe | -0.001 |
izards | -0.001 |
ils | -0.001 |
bors | -0.001 |
Token | por |
Token ID | 16964 |
Feature activation | +6.51e+00 |
Pos logit contributions | |
affe | +0.052 |
ounces | +0.052 |
izards | +0.047 |
hell | +0.047 |
bors | +0.047 |
Neg logit contributions | |
burn | -0.031 |
blowing | -0.030 |
daddy | -0.029 |
waving | -0.029 |
spinning | -0.026 |
Token | ridge |
Token ID | 12818 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ounces | +0.153 |
izards | +0.137 |
hell | +0.136 |
affe | +0.135 |
bors | +0.128 |
Neg logit contributions | |
burn | -0.218 |
blowing | -0.203 |
waving | -0.194 |
spinning | -0.180 |
ticking | -0.180 |
Token | and |
Token ID | 290 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ounces | +0.075 |
affe | +0.070 |
bors | +0.069 |
izards | +0.068 |
ils | +0.067 |
Neg logit contributions | |
burn | -0.040 |
blowing | -0.037 |
waving | -0.035 |
daddy | -0.031 |
spinning | -0.030 |
Token | pancakes |
Token ID | 47008 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ounces | +0.007 |
affe | +0.007 |
izards | +0.006 |
ils | +0.006 |
hell | +0.006 |
Neg logit contributions | |
burn | -0.005 |
blowing | -0.005 |
waving | -0.005 |
daddy | -0.004 |
spinning | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e-03 |
Pos logit contributions | |
ounces | +0.064 |
affe | +0.059 |
bors | +0.058 |
izards | +0.058 |
ils | +0.056 |
Neg logit contributions | |
burn | -0.036 |
blowing | -0.035 |
waving | -0.033 |
daddy | -0.028 |
spinning | -0.028 |
Token | He |
Token ID | 679 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
ounces | +0.000 |
ils | +0.000 |
izards | +0.000 |
bors | +0.000 |
affe | +0.000 |
Neg logit contributions | |
burn | -0.000 |
waving | -0.000 |
blowing | -0.000 |
driveway | -0.000 |
neighborhood | -0.000 |
Token | got |
Token ID | 1392 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
burn | +0.024 |
blowing | +0.022 |
waving | +0.021 |
spinning | +0.019 |
driveway | +0.018 |
Neg logit contributions | |
ounces | -0.030 |
ils | -0.028 |
affe | -0.027 |
izards | -0.027 |
bors | -0.027 |
Token | out |
Token ID | 503 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ounces | +0.004 |
ils | +0.003 |
izards | +0.003 |
ily | +0.003 |
imes | +0.003 |
Neg logit contributions | |
burn | -0.003 |
waving | -0.003 |
blowing | -0.002 |
driveway | -0.002 |
neighborhood | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
ounces | +0.004 |
ils | +0.004 |
izards | +0.004 |
ily | +0.003 |
hell | +0.003 |
Neg logit contributions | |
burn | -0.004 |
waving | -0.004 |
driveway | -0.003 |
blowing | -0.003 |
neighborhood | -0.003 |
Token | bed |
Token ID | 3996 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
ounces | +0.001 |
mushrooms | +0.001 |
izards | +0.001 |
ils | +0.001 |
bananas | +0.001 |
Neg logit contributions | |
burn | -0.001 |
itating | -0.001 |
neighborhood | -0.001 |
rou | -0.001 |
rolling | -0.001 |
Token | at |
Token ID | 379 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
ounces | +0.024 |
ils | +0.023 |
hell | +0.022 |
affe | +0.022 |
izards | +0.022 |
Neg logit contributions | |
burn | -0.016 |
waving | -0.013 |
blowing | -0.013 |
driveway | -0.012 |
spinning | -0.011 |
Token | 7 |
Token ID | 767 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
ounces | +0.013 |
ily | +0.011 |
ils | +0.011 |
mushrooms | +0.011 |
izards | +0.010 |
Neg logit contributions | |
burn | -0.014 |
blowing | -0.012 |
waving | -0.012 |
rou | -0.011 |
rolling | -0.011 |
Token | am |
Token ID | 321 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ounces | +0.182 |
affe | +0.172 |
bors | +0.167 |
izards | +0.166 |
hell | +0.166 |
Neg logit contributions | |
burn | -0.122 |
waving | -0.115 |
blowing | -0.114 |
spinning | -0.104 |
neighborhood | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
burn | +0.045 |
blowing | +0.040 |
waving | +0.039 |
spinning | +0.034 |
driveway | +0.034 |
Neg logit contributions | |
ounces | -0.068 |
ils | -0.062 |
izards | -0.061 |
affe | -0.061 |
hell | -0.060 |
Token | went |
Token ID | 1816 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
ounces | +0.030 |
ils | +0.027 |
izards | +0.027 |
bors | +0.027 |
affe | +0.026 |
Neg logit contributions | |
burn | -0.020 |
blowing | -0.018 |
waving | -0.018 |
neighborhood | -0.016 |
spinning | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
burn | +0.012 |
blowing | +0.010 |
waving | +0.010 |
neighborhood | +0.009 |
daddy | +0.009 |
Neg logit contributions | |
ounces | -0.021 |
ils | -0.020 |
izards | -0.019 |
bors | -0.019 |
hell | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
ounces | +0.039 |
izards | +0.035 |
ils | +0.034 |
bors | +0.034 |
nic | +0.032 |
Neg logit contributions | |
burn | -0.036 |
blowing | -0.031 |
waving | -0.028 |
neighborhood | -0.026 |
leaning | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ounces | +0.010 |
affe | +0.010 |
bors | +0.009 |
izards | +0.009 |
ils | +0.009 |
Neg logit contributions | |
burn | -0.005 |
blowing | -0.004 |
waving | -0.004 |
daddy | -0.004 |
spinning | -0.004 |
Token | bottle |
Token ID | 9294 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ounces | +0.004 |
izards | +0.004 |
ils | +0.004 |
bors | +0.004 |
affe | +0.004 |
Neg logit contributions | |
burn | -0.002 |
blowing | -0.002 |
waving | -0.002 |
spinning | -0.002 |
crying | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
ounces | +0.136 |
bors | +0.126 |
ils | +0.124 |
izards | +0.124 |
affe | +0.123 |
Neg logit contributions | |
burn | -0.047 |
blowing | -0.041 |
waving | -0.039 |
spinning | -0.032 |
my | -0.031 |
Token | it |
Token ID | 340 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
ounces | +0.032 |
ils | +0.029 |
izards | +0.029 |
affe | +0.029 |
bors | +0.029 |
Neg logit contributions | |
burn | -0.020 |
blowing | -0.018 |
waving | -0.018 |
spinning | -0.016 |
neighborhood | -0.016 |
Token | broke |
Token ID | 6265 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
ounces | +0.087 |
affe | +0.079 |
bors | +0.078 |
izards | +0.078 |
ils | +0.077 |
Neg logit contributions | |
burn | -0.045 |
blowing | -0.041 |
waving | -0.040 |
spinning | -0.035 |
crying | -0.034 |
Token | on |
Token ID | 319 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
burn | +0.025 |
blowing | +0.022 |
waving | +0.022 |
neighborhood | +0.019 |
driveway | +0.019 |
Neg logit contributions | |
ounces | -0.032 |
ils | -0.028 |
izards | -0.028 |
affe | -0.028 |
bors | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ounces | +0.056 |
izards | +0.052 |
affe | +0.052 |
ils | +0.051 |
bors | +0.051 |
Neg logit contributions | |
burn | -0.029 |
blowing | -0.026 |
waving | -0.025 |
daddy | -0.022 |
spinning | -0.021 |
Token | floor |
Token ID | 4314 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
burn | +0.003 |
blowing | +0.002 |
waving | +0.002 |
driveway | +0.002 |
window | +0.002 |
Neg logit contributions | |
ounces | -0.005 |
izards | -0.004 |
bors | -0.004 |
affe | -0.004 |
ils | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
ounces | +0.008 |
ils | +0.008 |
affe | +0.008 |
bors | +0.008 |
izards | +0.008 |
Neg logit contributions | |
burn | -0.006 |
blowing | -0.005 |
waving | -0.005 |
spinning | -0.005 |
crying | -0.005 |
Token | The |
Token ID | 383 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
burn | +0.015 |
blowing | +0.014 |
waving | +0.014 |
spinning | +0.012 |
neighborhood | +0.012 |
Neg logit contributions | |
ounces | -0.028 |
ils | -0.026 |
affe | -0.025 |
izards | -0.025 |
bors | -0.025 |
Token | wine |
Token ID | 8237 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
burn | +0.032 |
blowing | +0.028 |
waving | +0.028 |
spinning | +0.024 |
driveway | +0.024 |
Neg logit contributions | |
ounces | -0.043 |
ils | -0.039 |
affe | -0.039 |
izards | -0.038 |
bors | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
ounces | +0.036 |
affe | +0.034 |
izards | +0.033 |
bors | +0.032 |
isy | +0.031 |
Neg logit contributions | |
blowing | -0.015 |
burn | -0.015 |
daddy | -0.014 |
waving | -0.014 |
window | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
burn | +0.011 |
my | +0.010 |
daddy | +0.009 |
waving | +0.009 |
Grand | +0.009 |
Neg logit contributions | |
ils | -0.028 |
ounces | -0.027 |
isy | -0.026 |
hell | -0.026 |
bors | -0.026 |
Token | does |
Token ID | 857 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ounces | +0.030 |
bors | +0.027 |
affe | +0.027 |
hell | +0.027 |
izards | +0.027 |
Neg logit contributions | |
burn | -0.016 |
blowing | -0.015 |
waving | -0.014 |
crying | -0.012 |
my | -0.012 |
Token | not |
Token ID | 407 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ounces | +0.053 |
affe | +0.051 |
ils | +0.049 |
izards | +0.049 |
bors | +0.048 |
Neg logit contributions | |
burn | -0.010 |
blowing | -0.010 |
waving | -0.010 |
spinning | -0.007 |
frown | -0.007 |
Token | permit |
Token ID | 8749 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
burn | +0.031 |
blowing | +0.026 |
waving | +0.026 |
my | +0.025 |
frown | +0.024 |
Neg logit contributions | |
ounces | -0.056 |
bors | -0.051 |
ils | -0.050 |
izards | -0.050 |
affe | -0.049 |
Token | us |
Token ID | 514 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ounces | +0.033 |
affe | +0.031 |
bridge | +0.030 |
hell | +0.029 |
bors | +0.029 |
Neg logit contributions | |
burn | -0.019 |
blowing | -0.018 |
waving | -0.018 |
daddy | -0.018 |
crying | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
ounces | +0.101 |
affe | +0.094 |
bors | +0.092 |
izards | +0.090 |
hell | +0.089 |
Neg logit contributions | |
burn | -0.020 |
blowing | -0.014 |
waving | -0.013 |
my | -0.009 |
crying | -0.009 |
Token | touch |
Token ID | 3638 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
burn | +0.016 |
blowing | +0.015 |
waving | +0.015 |
spinning | +0.013 |
neighborhood | +0.013 |
Neg logit contributions | |
ounces | -0.021 |
ils | -0.019 |
izards | -0.019 |
affe | -0.019 |
bors | -0.019 |
Token | them |
Token ID | 606 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
burn | +0.011 |
blowing | +0.009 |
my | +0.009 |
daddy | +0.009 |
waving | +0.009 |
Neg logit contributions | |
ounces | -0.023 |
affe | -0.023 |
isy | -0.021 |
izards | -0.021 |
nic | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
ounces | +0.066 |
bors | +0.062 |
affe | +0.060 |
izards | +0.059 |
ils | +0.058 |
Neg logit contributions | |
burn | -0.041 |
blowing | -0.036 |
waving | -0.034 |
my | -0.032 |
daddy | -0.032 |
Token | They |
Token ID | 1119 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
burn | +0.014 |
my | +0.013 |
daddy | +0.012 |
waving | +0.012 |
grandma | +0.011 |
Neg logit contributions | |
ils | -0.033 |
ounces | -0.033 |
isy | -0.032 |
bors | -0.031 |
hell | -0.031 |
Token | there |
Token ID | 612 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
burn | +0.001 |
blowing | +0.001 |
waving | +0.001 |
spinning | +0.001 |
daddy | +0.001 |
Neg logit contributions | |
ounces | -0.004 |
ils | -0.004 |
affe | -0.004 |
izards | -0.004 |
bors | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
burn | +0.033 |
blowing | +0.029 |
waving | +0.028 |
spinning | +0.023 |
neighborhood | +0.023 |
Neg logit contributions | |
ounces | -0.078 |
ils | -0.072 |
izards | -0.071 |
affe | -0.071 |
bors | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ounces | +0.052 |
izards | +0.047 |
ils | +0.046 |
bors | +0.046 |
affe | +0.046 |
Neg logit contributions | |
burn | -0.040 |
blowing | -0.035 |
waving | -0.034 |
driveway | -0.031 |
neighborhood | -0.030 |
Token | little |
Token ID | 1310 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
burn | +0.015 |
blowing | +0.013 |
waving | +0.012 |
driveway | +0.011 |
my | +0.011 |
Neg logit contributions | |
ounces | -0.018 |
affe | -0.017 |
isy | -0.016 |
bors | -0.016 |
hell | -0.016 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
burn | +0.009 |
blowing | +0.008 |
waving | +0.008 |
driveway | +0.007 |
neighborhood | +0.007 |
Neg logit contributions | |
ounces | -0.015 |
affe | -0.014 |
izards | -0.013 |
ils | -0.013 |
bors | -0.013 |
Token | called |
Token ID | 1444 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
ounces | +0.079 |
ils | +0.071 |
affe | +0.070 |
izards | +0.070 |
bors | +0.069 |
Neg logit contributions | |
burn | -0.076 |
blowing | -0.069 |
waving | -0.067 |
driveway | -0.062 |
spinning | -0.061 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
ounces | +0.067 |
affe | +0.059 |
hell | +0.058 |
ils | +0.058 |
bors | +0.057 |
Neg logit contributions | |
burn | -0.051 |
waving | -0.047 |
blowing | -0.046 |
daddy | -0.043 |
crying | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
ounces | +0.033 |
ils | +0.030 |
bors | +0.030 |
izards | +0.030 |
affe | +0.029 |
Neg logit contributions | |
burn | -0.021 |
waving | -0.019 |
blowing | -0.019 |
daddy | -0.017 |
spinning | -0.017 |
Token | Daisy |
Token ID | 40355 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
burn | +0.000 |
waving | +0.000 |
blowing | +0.000 |
neighborhood | +0.000 |
spinning | +0.000 |
Neg logit contributions | |
ounces | -0.000 |
ils | -0.000 |
izards | -0.000 |
bors | -0.000 |
affe | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
burn | +0.002 |
blowing | +0.002 |
waving | +0.002 |
spinning | +0.001 |
neighborhood | +0.001 |
Neg logit contributions | |
ounces | -0.004 |
ils | -0.004 |
izards | -0.004 |
affe | -0.004 |
bors | -0.004 |
Token | very |
Token ID | 845 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
burn | +0.019 |
driveway | +0.016 |
blowing | +0.015 |
seat | +0.015 |
waving | +0.014 |
Neg logit contributions | |
ounces | -0.021 |
izards | -0.019 |
ily | -0.019 |
ils | -0.018 |
bors | -0.018 |
Token | Every |
Token ID | 3887 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
ounces | +0.010 |
affe | +0.008 |
hell | +0.008 |
izards | +0.008 |
bors | +0.008 |
Neg logit contributions | |
burn | -0.014 |
blowing | -0.012 |
waving | -0.012 |
crying | -0.011 |
spinning | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
burn | +0.055 |
waving | +0.050 |
blowing | +0.047 |
typing | +0.046 |
crying | +0.043 |
Neg logit contributions | |
ounces | -0.073 |
affe | -0.070 |
hell | -0.067 |
isy | -0.067 |
ger | -0.065 |
Token | he |
Token ID | 339 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ounces | +0.005 |
ils | +0.005 |
affe | +0.005 |
izards | +0.005 |
bors | +0.005 |
Neg logit contributions | |
burn | -0.005 |
blowing | -0.004 |
waving | -0.004 |
neighborhood | -0.004 |
driveway | -0.004 |
Token | would |
Token ID | 561 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ounces | +0.057 |
ils | +0.053 |
izards | +0.052 |
affe | +0.052 |
bors | +0.051 |
Neg logit contributions | |
burn | -0.031 |
waving | -0.027 |
blowing | -0.027 |
crying | -0.022 |
driveway | -0.022 |
Token | take |
Token ID | 1011 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
burn | +0.031 |
blowing | +0.027 |
waving | +0.026 |
neighborhood | +0.024 |
crying | +0.023 |
Neg logit contributions | |
ounces | -0.045 |
ils | -0.041 |
affe | -0.040 |
bors | -0.040 |
izards | -0.040 |
Token | it |
Token ID | 340 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ounces | +0.090 |
izards | +0.082 |
ils | +0.081 |
affe | +0.081 |
bors | +0.079 |
Neg logit contributions | |
burn | -0.060 |
waving | -0.055 |
blowing | -0.055 |
spinning | -0.050 |
daddy | -0.048 |
Token | to |
Token ID | 284 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ounces | +0.092 |
ils | +0.086 |
izards | +0.086 |
hell | +0.086 |
affe | +0.085 |
Neg logit contributions | |
burn | -0.059 |
blowing | -0.051 |
waving | -0.051 |
neighborhood | -0.044 |
driveway | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ounces | +0.043 |
bors | +0.038 |
izards | +0.038 |
ils | +0.038 |
affe | +0.037 |
Neg logit contributions | |
burn | -0.035 |
blowing | -0.030 |
waving | -0.029 |
driveway | -0.027 |
neighborhood | -0.027 |
Token | park |
Token ID | 3952 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
ounces | +0.044 |
affe | +0.042 |
ils | +0.041 |
izards | +0.040 |
mushrooms | +0.040 |
Neg logit contributions | |
burn | -0.025 |
blowing | -0.022 |
waving | -0.019 |
crying | -0.016 |
spinning | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
ounces | +0.017 |
ils | +0.016 |
affe | +0.016 |
izards | +0.016 |
hell | +0.016 |
Neg logit contributions | |
burn | -0.009 |
blowing | -0.008 |
waving | -0.007 |
spinning | -0.006 |
driveway | -0.006 |
Token | kick |
Token ID | 4829 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
ounces | +0.021 |
ils | +0.019 |
affe | +0.019 |
bors | +0.019 |
izards | +0.019 |
Neg logit contributions | |
burn | -0.012 |
blowing | -0.010 |
waving | -0.010 |
neighborhood | -0.009 |
leaning | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
burn | +0.003 |
blowing | +0.003 |
waving | +0.003 |
driveway | +0.003 |
neighborhood | +0.003 |
Neg logit contributions | |
ounces | -0.005 |
izards | -0.005 |
ils | -0.004 |
bors | -0.004 |
hell | -0.004 |
Token | high |
Token ID | 1029 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
burn | +0.030 |
blowing | +0.026 |
waving | +0.026 |
driveway | +0.023 |
neighborhood | +0.023 |
Neg logit contributions | |
ounces | -0.038 |
affe | -0.034 |
hell | -0.033 |
bors | -0.033 |
ils | -0.033 |
Token | rat |
Token ID | 4227 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ounces | +0.018 |
affe | +0.017 |
ils | +0.016 |
hell | +0.016 |
bors | +0.016 |
Neg logit contributions | |
burn | -0.015 |
blowing | -0.014 |
waving | -0.013 |
neighborhood | -0.012 |
daddy | -0.012 |
Token | � |
Token ID | 6184 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
ounces | +0.060 |
ils | +0.053 |
izards | +0.053 |
bors | +0.053 |
affe | +0.052 |
Neg logit contributions | |
burn | -0.041 |
waving | -0.039 |
blowing | -0.038 |
spinning | -0.034 |
crying | -0.033 |
Token | � |
Token ID | 95 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ounces | +0.123 |
hell | +0.116 |
bors | +0.115 |
ils | +0.114 |
izards | +0.111 |
Neg logit contributions | |
burn | -0.103 |
waving | -0.099 |
leaning | -0.094 |
blowing | -0.093 |
spinning | -0.089 |
Token | € |
Token ID | 26391 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
izards | +0.080 |
ilies | +0.075 |
hell | +0.075 |
ounces | +0.074 |
ils | +0.072 |
Neg logit contributions | |
burn | -0.073 |
driveway | -0.070 |
leaning | -0.069 |
waving | -0.068 |
neighborhood | -0.067 |
Token | � |
Token ID | 447 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
ounces | +0.096 |
ils | +0.087 |
izards | +0.085 |
bors | +0.084 |
affe | +0.083 |
Neg logit contributions | |
burn | -0.086 |
waving | -0.078 |
blowing | -0.077 |
neighborhood | -0.071 |
driveway | -0.069 |
Token | � |
Token ID | 250 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
burn | +0.015 |
blowing | +0.014 |
waving | +0.013 |
spinning | +0.012 |
neighborhood | +0.011 |
Neg logit contributions | |
ounces | -0.025 |
ils | -0.023 |
izards | -0.023 |
affe | -0.023 |
bors | -0.023 |
Token | much |
Token ID | 881 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
ounces | +0.055 |
ils | +0.052 |
izards | +0.051 |
affe | +0.050 |
bors | +0.050 |
Neg logit contributions | |
burn | -0.040 |
blowing | -0.036 |
waving | -0.035 |
my | -0.031 |
spinning | -0.031 |
Token | bigger |
Token ID | 5749 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
ounces | +0.012 |
ils | +0.011 |
izards | +0.011 |
affe | +0.011 |
bors | +0.010 |
Neg logit contributions | |
burn | -0.008 |
blowing | -0.008 |
waving | -0.008 |
spinning | -0.007 |
crying | -0.007 |
Token | than |
Token ID | 621 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
burn | +0.018 |
waving | +0.017 |
blowing | +0.017 |
leaning | +0.015 |
spinning | +0.015 |
Neg logit contributions | |
ounces | -0.020 |
ils | -0.019 |
hell | -0.019 |
izards | -0.019 |
bors | -0.019 |
Token | special |
Token ID | 2041 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
ounces | +0.130 |
izards | +0.117 |
ils | +0.117 |
bors | +0.116 |
affe | +0.116 |
Neg logit contributions | |
burn | -0.072 |
waving | -0.067 |
blowing | -0.066 |
daddy | -0.059 |
neighborhood | -0.059 |
Token | frame |
Token ID | 5739 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
ounces | +0.009 |
affe | +0.009 |
ils | +0.008 |
hell | +0.008 |
isy | +0.008 |
Neg logit contributions | |
burn | -0.007 |
blowing | -0.006 |
waving | -0.006 |
leaning | -0.006 |
my | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
ounces | +0.023 |
bors | +0.021 |
ils | +0.021 |
izards | +0.021 |
affe | +0.020 |
Neg logit contributions | |
burn | -0.015 |
blowing | -0.014 |
waving | -0.014 |
spinning | -0.012 |
crying | -0.012 |
Token | It |
Token ID | 632 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
ounces | +0.022 |
ils | +0.021 |
bors | +0.020 |
izards | +0.020 |
hell | +0.020 |
Neg logit contributions | |
burn | -0.012 |
blowing | -0.011 |
waving | -0.011 |
driveway | -0.009 |
neighborhood | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
ounces | +0.007 |
ils | +0.006 |
izards | +0.006 |
affe | +0.006 |
bors | +0.006 |
Neg logit contributions | |
burn | -0.003 |
blowing | -0.003 |
waving | -0.003 |
spinning | -0.002 |
neighborhood | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
burn | +0.002 |
waving | +0.001 |
blowing | +0.001 |
neighborhood | +0.001 |
driveway | +0.001 |
Neg logit contributions | |
ounces | -0.002 |
ils | -0.002 |
izards | -0.002 |
hell | -0.002 |
bors | -0.002 |
Token | colorful |
Token ID | 20239 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
burn | +0.034 |
blowing | +0.028 |
waving | +0.026 |
my | +0.025 |
seat | +0.025 |
Neg logit contributions | |
ounces | -0.034 |
affe | -0.032 |
isy | -0.032 |
hell | -0.031 |
ocket | -0.029 |
Token | frame |
Token ID | 5739 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
burn | +0.008 |
blowing | +0.007 |
waving | +0.007 |
driveway | +0.006 |
neighborhood | +0.006 |
Neg logit contributions | |
ounces | -0.007 |
affe | -0.007 |
ils | -0.006 |
hell | -0.006 |
izards | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ounces | +0.014 |
ils | +0.013 |
affe | +0.013 |
izards | +0.013 |
bors | +0.013 |
Neg logit contributions | |
burn | -0.010 |
blowing | -0.009 |
waving | -0.009 |
spinning | -0.008 |
neighborhood | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
ounces | +0.047 |
affe | +0.042 |
izards | +0.042 |
ils | +0.042 |
bors | +0.042 |
Neg logit contributions | |
burn | -0.030 |
blowing | -0.028 |
waving | -0.028 |
spinning | -0.025 |
daddy | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ounces | +0.015 |
ils | +0.013 |
izards | +0.013 |
affe | +0.013 |
bors | +0.013 |
Neg logit contributions | |
burn | -0.009 |
blowing | -0.008 |
waving | -0.008 |
driveway | -0.006 |
neighborhood | -0.006 |
Token | time |
Token ID | 640 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
burn | +0.032 |
waving | +0.028 |
blowing | +0.028 |
driveway | +0.025 |
spinning | +0.025 |
Neg logit contributions | |
ounces | -0.037 |
hell | -0.034 |
affe | -0.033 |
ils | -0.033 |
bors | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
burn | +0.050 |
blowing | +0.045 |
waving | +0.045 |
spinning | +0.038 |
daddy | +0.038 |
Neg logit contributions | |
ounces | -0.091 |
ils | -0.082 |
affe | -0.082 |
izards | -0.082 |
bors | -0.081 |
Token | please |
Token ID | 3387 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
burn | +0.029 |
blowing | +0.027 |
waving | +0.026 |
driveway | +0.024 |
neighborhood | +0.024 |
Neg logit contributions | |
ounces | -0.027 |
ils | -0.024 |
izards | -0.024 |
affe | -0.024 |
bors | -0.024 |
Token | listen |
Token ID | 6004 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
ounces | +0.049 |
ils | +0.043 |
affe | +0.043 |
bors | +0.043 |
izards | +0.042 |
Neg logit contributions | |
burn | -0.039 |
blowing | -0.035 |
waving | -0.035 |
driveway | -0.031 |
neighborhood | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
burn | +0.008 |
blowing | +0.007 |
waving | +0.006 |
spinning | +0.005 |
daddy | +0.005 |
Neg logit contributions | |
ounces | -0.024 |
izards | -0.022 |
ils | -0.022 |
affe | -0.022 |
bors | -0.022 |
Token | me |
Token ID | 502 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ounces | +0.016 |
izards | +0.014 |
affe | +0.014 |
hell | +0.014 |
ils | +0.014 |
Neg logit contributions | |
burn | -0.012 |
blowing | -0.011 |
waving | -0.011 |
daddy | -0.010 |
spinning | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
ounces | +0.041 |
izards | +0.037 |
bors | +0.037 |
affe | +0.037 |
ils | +0.037 |
Neg logit contributions | |
burn | -0.019 |
blowing | -0.017 |
waving | -0.016 |
daddy | -0.014 |
my | -0.014 |
Token | wait |
Token ID | 4043 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
burn | +0.018 |
blowing | +0.016 |
waving | +0.016 |
spinning | +0.014 |
neighborhood | +0.014 |
Neg logit contributions | |
ounces | -0.025 |
ils | -0.023 |
izards | -0.022 |
affe | -0.022 |
bors | -0.022 |
Token | until |
Token ID | 1566 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
ounces | +0.027 |
ils | +0.024 |
affe | +0.024 |
izards | +0.024 |
bors | +0.023 |
Neg logit contributions | |
burn | -0.021 |
blowing | -0.019 |
waving | -0.019 |
spinning | -0.017 |
daddy | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
ounces | +0.006 |
affe | +0.005 |
ils | +0.005 |
izards | +0.005 |
bors | +0.005 |
Neg logit contributions | |
burn | -0.005 |
blowing | -0.005 |
waving | -0.005 |
spinning | -0.004 |
daddy | -0.004 |
Token | pie |
Token ID | 2508 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
burn | +0.033 |
blowing | +0.030 |
waving | +0.030 |
spinning | +0.028 |
daddy | +0.027 |
Neg logit contributions | |
ounces | -0.022 |
ils | -0.019 |
affe | -0.018 |
bors | -0.018 |
izards | -0.018 |
Token | going |
Token ID | 1016 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
burn | +0.051 |
blowing | +0.043 |
waving | +0.042 |
daddy | +0.040 |
neighborhood | +0.040 |
Neg logit contributions | |
ounces | -0.063 |
hell | -0.057 |
ils | -0.057 |
izards | -0.057 |
affe | -0.056 |
Token | by |
Token ID | 416 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
burn | +0.033 |
blowing | +0.028 |
waving | +0.028 |
daddy | +0.025 |
neighborhood | +0.024 |
Neg logit contributions | |
ounces | -0.056 |
ils | -0.050 |
izards | -0.050 |
bors | -0.050 |
hell | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
ounces | +0.012 |
ils | +0.010 |
izards | +0.010 |
affe | +0.010 |
bors | +0.010 |
Neg logit contributions | |
burn | -0.009 |
blowing | -0.008 |
waving | -0.008 |
spinning | -0.007 |
neighborhood | -0.007 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +4.89e-03 |
Pos logit contributions | |
burn | +0.010 |
waving | +0.010 |
blowing | +0.009 |
neighborhood | +0.009 |
driveway | +0.009 |
Neg logit contributions | |
ounces | -0.023 |
ils | -0.022 |
hell | -0.021 |
izards | -0.021 |
bors | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ounces | +0.000 |
ils | +0.000 |
hell | +0.000 |
affe | +0.000 |
izards | +0.000 |
Neg logit contributions | |
waving | -0.000 |
burn | -0.000 |
blowing | -0.000 |
daddy | -0.000 |
spinning | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
burn | +0.003 |
waving | +0.003 |
blowing | +0.003 |
daddy | +0.003 |
spinning | +0.003 |
Neg logit contributions | |
ounces | -0.005 |
ils | -0.004 |
affe | -0.004 |
hell | -0.004 |
bors | -0.004 |
Token | train |
Token ID | 4512 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
burn | +0.028 |
waving | +0.026 |
blowing | +0.026 |
spinning | +0.023 |
neighborhood | +0.023 |
Neg logit contributions | |
ounces | -0.042 |
ils | -0.038 |
izards | -0.038 |
bors | -0.037 |
affe | -0.037 |
Token | made |
Token ID | 925 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ounces | +0.023 |
ils | +0.021 |
affe | +0.021 |
bors | +0.021 |
izards | +0.020 |
Neg logit contributions | |
burn | -0.015 |
blowing | -0.013 |
waving | -0.013 |
spinning | -0.011 |
neighborhood | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ounces | +0.044 |
ils | +0.040 |
izards | +0.040 |
affe | +0.039 |
hell | +0.038 |
Neg logit contributions | |
burn | -0.026 |
blowing | -0.025 |
waving | -0.024 |
spinning | -0.021 |
daddy | -0.021 |
Token | bad |
Token ID | 2089 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
burn | +0.009 |
blowing | +0.008 |
waving | +0.007 |
neighborhood | +0.007 |
my | +0.007 |
Neg logit contributions | |
ounces | -0.011 |
affe | -0.010 |
hell | -0.010 |
bors | -0.010 |
isy | -0.010 |
Token | noise |
Token ID | 7838 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
ounces | +0.041 |
ils | +0.037 |
affe | +0.037 |
izards | +0.037 |
bors | +0.036 |
Neg logit contributions | |
burn | -0.034 |
blowing | -0.030 |
waving | -0.030 |
neighborhood | -0.027 |
spinning | -0.027 |
Token | lying |
Token ID | 9105 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
waving | +0.023 |
burn | +0.022 |
blowing | +0.022 |
crying | +0.020 |
spinning | +0.020 |
Neg logit contributions | |
ounces | -0.055 |
affe | -0.051 |
bors | -0.049 |
ils | -0.048 |
hell | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
burn | +0.050 |
blowing | +0.045 |
waving | +0.044 |
crying | +0.038 |
spinning | +0.037 |
Neg logit contributions | |
ounces | -0.113 |
bors | -0.104 |
izards | -0.103 |
affe | -0.102 |
ils | -0.101 |
Token | " |
Token ID | 366 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
ounces | +0.007 |
ils | +0.006 |
izards | +0.006 |
bors | +0.006 |
hell | +0.006 |
Neg logit contributions | |
burn | -0.002 |
waving | -0.002 |
my | -0.002 |
window | -0.002 |
daddy | -0.002 |
Token | L |
Token ID | 43 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ounces | +0.023 |
ils | +0.021 |
izards | +0.021 |
affe | +0.021 |
bors | +0.021 |
Neg logit contributions | |
burn | -0.014 |
blowing | -0.012 |
waving | -0.012 |
spinning | -0.011 |
neighborhood | -0.011 |
Token | ily |
Token ID | 813 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
ounces | +0.042 |
bors | +0.031 |
ns | +0.030 |
affe | +0.030 |
keys | +0.028 |
Neg logit contributions | |
my | -0.085 |
burn | -0.085 |
blowing | -0.079 |
crying | -0.079 |
spinning | -0.078 |
Token | , |
Token ID | 11 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
burn | +0.011 |
waving | +0.010 |
blowing | +0.010 |
crying | +0.009 |
my | +0.009 |
Neg logit contributions | |
ounces | -0.027 |
izards | -0.024 |
bors | -0.024 |
ils | -0.024 |
affe | -0.024 |
Token | I |
Token ID | 314 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
burn | +0.025 |
blowing | +0.023 |
waving | +0.023 |
daddy | +0.022 |
spinning | +0.022 |
Neg logit contributions | |
ounces | -0.028 |
ils | -0.025 |
affe | -0.025 |
bors | -0.025 |
izards | -0.024 |
Token | know |
Token ID | 760 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
burn | +0.035 |
blowing | +0.032 |
waving | +0.031 |
driveway | +0.028 |
leaning | +0.028 |
Neg logit contributions | |
ounces | -0.042 |
izards | -0.038 |
ils | -0.038 |
hell | -0.037 |
affe | -0.037 |
Token | you |
Token ID | 345 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
ounces | +0.032 |
affe | +0.030 |
bors | +0.028 |
hell | +0.028 |
ils | +0.028 |
Neg logit contributions | |
waving | -0.021 |
burn | -0.020 |
blowing | -0.020 |
daddy | -0.020 |
spinning | -0.019 |
Token | hid |
Token ID | 24519 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
ounces | +0.077 |
bors | +0.070 |
affe | +0.070 |
isy | +0.065 |
ils | +0.065 |
Neg logit contributions | |
burn | -0.038 |
waving | -0.036 |
my | -0.035 |
blowing | -0.035 |
daddy | -0.032 |
Token | it |
Token ID | 340 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
burn | +0.013 |
blowing | +0.013 |
waving | +0.013 |
spinning | +0.012 |
daddy | +0.012 |
Neg logit contributions | |
ounces | -0.029 |
affe | -0.028 |
bors | -0.027 |
hell | -0.026 |
isy | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
ounces | +0.054 |
ils | +0.048 |
izards | +0.048 |
affe | +0.048 |
bors | +0.048 |
Neg logit contributions | |
burn | -0.033 |
blowing | -0.030 |
waving | -0.030 |
spinning | -0.026 |
leaning | -0.025 |
Token | She |
Token ID | 1375 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
burn | +0.001 |
blowing | +0.001 |
waving | +0.001 |
spinning | +0.001 |
neighborhood | +0.001 |
Neg logit contributions | |
ounces | -0.002 |
ils | -0.001 |
izards | -0.001 |
affe | -0.001 |
bors | -0.001 |
Token | wished |
Token ID | 16555 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
ounces | +0.038 |
ils | +0.035 |
affe | +0.034 |
izards | +0.034 |
bors | +0.034 |
Neg logit contributions | |
burn | -0.026 |
blowing | -0.023 |
waving | -0.023 |
spinning | -0.020 |
driveway | -0.020 |
Token | they |
Token ID | 484 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ounces | +0.026 |
izards | +0.023 |
ils | +0.023 |
bors | +0.023 |
affe | +0.023 |
Neg logit contributions | |
burn | -0.023 |
blowing | -0.020 |
waving | -0.020 |
driveway | -0.018 |
neighborhood | -0.018 |
Token | could |
Token ID | 714 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
ounces | +0.055 |
affe | +0.050 |
bors | +0.050 |
izards | +0.049 |
ils | +0.048 |
Neg logit contributions | |
burn | -0.030 |
waving | -0.028 |
blowing | -0.027 |
my | -0.024 |
spinning | -0.024 |
Token | stay |
Token ID | 2652 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
burn | +0.068 |
blowing | +0.063 |
waving | +0.060 |
crying | +0.054 |
neighborhood | +0.053 |
Neg logit contributions | |
ounces | -0.094 |
affe | -0.085 |
izards | -0.084 |
ils | -0.083 |
hell | -0.083 |
Token | forever |
Token ID | 8097 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
burn | +0.010 |
blowing | +0.009 |
waving | +0.009 |
driveway | +0.008 |
crying | +0.008 |
Neg logit contributions | |
ounces | -0.015 |
ils | -0.014 |
izards | -0.014 |
bors | -0.014 |
hell | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
ounces | +0.020 |
ils | +0.019 |
affe | +0.018 |
izards | +0.018 |
bors | +0.018 |
Neg logit contributions | |
burn | -0.013 |
blowing | -0.012 |
waving | -0.012 |
spinning | -0.010 |
neighborhood | -0.010 |
Token | But |
Token ID | 887 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ounces | +0.017 |
ils | +0.016 |
izards | +0.016 |
bors | +0.016 |
affe | +0.016 |
Neg logit contributions | |
burn | -0.012 |
waving | -0.011 |
blowing | -0.011 |
neighborhood | -0.010 |
daddy | -0.010 |
Token | Molly |
Token ID | 30236 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
ounces | +0.040 |
ils | +0.036 |
izards | +0.036 |
bors | +0.036 |
affe | +0.035 |
Neg logit contributions | |
burn | -0.033 |
blowing | -0.029 |
waving | -0.029 |
driveway | -0.026 |
neighborhood | -0.026 |
Token | 's |
Token ID | 338 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
ounces | +0.023 |
izards | +0.021 |
hell | +0.020 |
ils | +0.020 |
bors | +0.020 |
Neg logit contributions | |
burn | -0.011 |
waving | -0.010 |
blowing | -0.010 |
neighborhood | -0.008 |
crying | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
ounces | +0.002 |
bors | +0.002 |
hell | +0.002 |
affe | +0.002 |
ils | +0.002 |
Neg logit contributions | |
burn | -0.001 |
blowing | -0.001 |
waving | -0.001 |
spinning | -0.001 |
crying | -0.001 |
Token | We |
Token ID | 775 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
burn | +0.016 |
waving | +0.014 |
blowing | +0.014 |
my | +0.013 |
daddy | +0.013 |
Neg logit contributions | |
ils | -0.022 |
ounces | -0.021 |
hell | -0.020 |
izards | -0.019 |
isy | -0.019 |
Token | should |
Token ID | 815 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
burn | +0.000 |
blowing | +0.000 |
waving | +0.000 |
my | +0.000 |
frown | +0.000 |
Neg logit contributions | |
ounces | -0.001 |
bors | -0.001 |
affe | -0.001 |
hell | -0.001 |
izards | -0.001 |
Token | respect |
Token ID | 2461 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
burn | +0.027 |
blowing | +0.024 |
waving | +0.024 |
spinning | +0.021 |
neighborhood | +0.020 |
Neg logit contributions | |
ounces | -0.044 |
ils | -0.040 |
izards | -0.039 |
affe | -0.039 |
bors | -0.039 |
Token | all |
Token ID | 477 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
burn | +0.049 |
blowing | +0.047 |
waving | +0.045 |
daddy | +0.040 |
my | +0.039 |
Neg logit contributions | |
ounces | -0.082 |
affe | -0.074 |
izards | -0.074 |
hell | -0.074 |
bors | -0.073 |
Token | living |
Token ID | 2877 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
blowing | +0.030 |
burn | +0.028 |
waving | +0.028 |
my | +0.025 |
spinning | +0.024 |
Neg logit contributions | |
ounces | -0.050 |
izards | -0.045 |
affe | -0.045 |
ils | -0.044 |
hell | -0.044 |
Token | things |
Token ID | 1243 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
burn | +0.087 |
blowing | +0.086 |
waving | +0.084 |
crying | +0.076 |
daddy | +0.076 |
Neg logit contributions | |
ounces | -0.126 |
affe | -0.121 |
hell | -0.113 |
izards | -0.113 |
isy | -0.111 |
Token | ." |
Token ID | 526 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
burn | +0.018 |
blowing | +0.018 |
waving | +0.017 |
spinning | +0.014 |
daddy | +0.014 |
Neg logit contributions | |
ounces | -0.032 |
affe | -0.029 |
bors | -0.029 |
izards | -0.028 |
ils | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
ounces | +0.073 |
ils | +0.071 |
izards | +0.069 |
bors | +0.068 |
affe | +0.066 |
Neg logit contributions | |
burn | -0.012 |
my | -0.009 |
daddy | -0.009 |
waving | -0.009 |
crying | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ounces | +0.021 |
ils | +0.020 |
izards | +0.019 |
affe | +0.019 |
bors | +0.019 |
Neg logit contributions | |
burn | -0.006 |
blowing | -0.005 |
waving | -0.005 |
neighborhood | -0.004 |
daddy | -0.004 |
Token | L |
Token ID | 43 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ounces | +0.045 |
izards | +0.045 |
ocket | +0.042 |
ils | +0.042 |
imes | +0.041 |
Neg logit contributions | |
my | -0.016 |
burn | -0.015 |
neighborhood | -0.014 |
daddy | -0.014 |
blowing | -0.013 |
Token | knock |
Token ID | 10643 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
burn | +0.024 |
blowing | +0.021 |
waving | +0.021 |
neighborhood | +0.019 |
driveway | +0.019 |
Neg logit contributions | |
ounces | -0.039 |
affe | -0.035 |
ils | -0.035 |
hell | -0.035 |
bors | -0.035 |
Token | him |
Token ID | 683 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
burn | +0.004 |
waving | +0.004 |
blowing | +0.004 |
spinning | +0.004 |
daddy | +0.004 |
Neg logit contributions | |
ounces | -0.006 |
affe | -0.006 |
bors | -0.005 |
ils | -0.005 |
izards | -0.005 |
Token | down |
Token ID | 866 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
ounces | +0.079 |
bors | +0.074 |
ils | +0.073 |
affe | +0.073 |
izards | +0.072 |
Neg logit contributions | |
burn | -0.025 |
waving | -0.020 |
blowing | -0.019 |
my | -0.015 |
spinning | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ounces | +0.037 |
bors | +0.035 |
isy | +0.034 |
ils | +0.034 |
affe | +0.033 |
Neg logit contributions | |
burn | -0.018 |
waving | -0.017 |
window | -0.016 |
blowing | -0.015 |
asleep | -0.015 |
Token | How |
Token ID | 1374 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
burn | +0.031 |
waving | +0.029 |
blowing | +0.027 |
daddy | +0.027 |
crying | +0.026 |
Neg logit contributions | |
ounces | -0.039 |
ils | -0.039 |
bors | -0.036 |
izards | -0.036 |
hell | -0.036 |
Token | about |
Token ID | 546 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
ounces | +0.156 |
bors | +0.141 |
ils | +0.141 |
affe | +0.134 |
izards | +0.133 |
Neg logit contributions | |
burn | -0.089 |
blowing | -0.081 |
waving | -0.079 |
daddy | -0.075 |
my | -0.075 |
Token | I |
Token ID | 314 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
burn | +0.067 |
waving | +0.063 |
blowing | +0.062 |
daddy | +0.060 |
crying | +0.056 |
Neg logit contributions | |
ounces | -0.089 |
hell | -0.084 |
ils | -0.083 |
affe | -0.082 |
izards | -0.080 |
Token | move |
Token ID | 1445 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
burn | +0.004 |
blowing | +0.004 |
waving | +0.004 |
neighborhood | +0.003 |
driveway | +0.003 |
Neg logit contributions | |
ounces | -0.006 |
ils | -0.005 |
izards | -0.005 |
affe | -0.005 |
hell | -0.005 |
Token | him |
Token ID | 683 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
burn | +0.032 |
blowing | +0.028 |
waving | +0.028 |
daddy | +0.024 |
spinning | +0.024 |
Neg logit contributions | |
ounces | -0.062 |
ils | -0.056 |
affe | -0.056 |
bors | -0.056 |
izards | -0.056 |
Token | to |
Token ID | 284 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
ounces | +0.001 |
ils | +0.001 |
izards | +0.001 |
affe | +0.001 |
bors | +0.001 |
Neg logit contributions | |
burn | -0.000 |
blowing | -0.000 |
waving | -0.000 |
spinning | -0.000 |
driveway | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
ounces | +0.014 |
ils | +0.013 |
izards | +0.013 |
affe | +0.013 |
bors | +0.013 |
Neg logit contributions | |
burn | -0.010 |
waving | -0.009 |
blowing | -0.009 |
spinning | -0.008 |
daddy | -0.008 |
Token | well |
Token ID | 880 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
burn | +0.031 |
blowing | +0.029 |
waving | +0.028 |
spinning | +0.025 |
crying | +0.024 |
Neg logit contributions | |
ounces | -0.048 |
affe | -0.043 |
bors | -0.043 |
ils | -0.043 |
izards | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
ounces | +0.048 |
affe | +0.044 |
bors | +0.044 |
ils | +0.043 |
izards | +0.043 |
Neg logit contributions | |
burn | -0.030 |
blowing | -0.027 |
waving | -0.026 |
spinning | -0.023 |
crying | -0.023 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
burn | +0.011 |
blowing | +0.010 |
waving | +0.010 |
spinning | +0.008 |
daddy | +0.008 |
Neg logit contributions | |
ounces | -0.019 |
affe | -0.018 |
hell | -0.017 |
izards | -0.017 |
bors | -0.017 |
Token | my |
Token ID | 1820 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
burn | +0.032 |
waving | +0.031 |
blowing | +0.029 |
spinning | +0.024 |
typing | +0.024 |
Neg logit contributions | |
ounces | -0.088 |
ils | -0.086 |
affe | -0.085 |
isy | -0.083 |
hell | -0.083 |
Token | 's |
Token ID | 338 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
burn | +0.068 |
blowing | +0.061 |
waving | +0.061 |
spinning | +0.053 |
driveway | +0.053 |
Neg logit contributions | |
ounces | -0.096 |
ils | -0.087 |
affe | -0.086 |
bors | -0.086 |
izards | -0.086 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
burn | +0.054 |
blowing | +0.047 |
leaning | +0.043 |
my | +0.042 |
typing | +0.040 |
Neg logit contributions | |
ounces | -0.060 |
affe | -0.058 |
ily | -0.055 |
izards | -0.055 |
isy | -0.055 |
Token | was |
Token ID | 373 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
burn | +0.105 |
waving | +0.091 |
blowing | +0.088 |
driveway | +0.087 |
seat | +0.084 |
Neg logit contributions | |
ils | -0.132 |
ounces | -0.132 |
isy | -0.128 |
affe | -0.126 |
bors | -0.124 |
Token | not |
Token ID | 407 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
burn | +0.029 |
driveway | +0.025 |
seat | +0.023 |
blowing | +0.022 |
my | +0.022 |
Neg logit contributions | |
ounces | -0.036 |
izards | -0.034 |
ily | -0.034 |
ils | -0.034 |
bors | -0.033 |
Token | around |
Token ID | 1088 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
burn | +0.086 |
blowing | +0.074 |
waving | +0.073 |
driveway | +0.069 |
neighborhood | +0.067 |
Neg logit contributions | |
ounces | -0.120 |
izards | -0.109 |
ils | -0.108 |
hell | -0.107 |
bors | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
burn | +0.076 |
blowing | +0.066 |
waving | +0.066 |
driveway | +0.060 |
neighborhood | +0.059 |
Neg logit contributions | |
ounces | -0.096 |
izards | -0.086 |
ils | -0.085 |
bors | -0.084 |
hell | -0.084 |
Token | so |
Token ID | 523 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
burn | +0.031 |
blowing | +0.028 |
waving | +0.028 |
spinning | +0.025 |
crying | +0.024 |
Neg logit contributions | |
ounces | -0.044 |
ils | -0.040 |
izards | -0.039 |
affe | -0.039 |
bors | -0.039 |
Token | my |
Token ID | 1820 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
waving | +0.036 |
burn | +0.035 |
blowing | +0.034 |
spinning | +0.028 |
cheering | +0.027 |
Neg logit contributions | |
ounces | -0.088 |
affe | -0.087 |
ils | -0.085 |
hell | -0.084 |
isy | -0.083 |
Token | realized |
Token ID | 6939 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
burn | +0.073 |
blowing | +0.066 |
waving | +0.065 |
spinning | +0.058 |
driveway | +0.056 |
Neg logit contributions | |
ounces | -0.083 |
ils | -0.077 |
affe | -0.075 |
bors | -0.074 |
izards | -0.073 |
Token | he |
Token ID | 339 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
ounces | +0.052 |
ils | +0.046 |
affe | +0.045 |
izards | +0.045 |
bors | +0.045 |
Neg logit contributions | |
burn | -0.050 |
blowing | -0.046 |
waving | -0.046 |
spinning | -0.041 |
daddy | -0.041 |
Token | lost |
Token ID | 2626 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ounces | +0.012 |
ils | +0.011 |
izards | +0.011 |
affe | +0.011 |
bors | +0.011 |
Neg logit contributions | |
burn | -0.008 |
blowing | -0.007 |
waving | -0.007 |
spinning | -0.006 |
driveway | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
burn | +0.041 |
blowing | +0.037 |
waving | +0.036 |
spinning | +0.032 |
neighborhood | +0.031 |
Neg logit contributions | |
ounces | -0.057 |
ils | -0.051 |
affe | -0.051 |
izards | -0.051 |
bors | -0.051 |
Token | favorite |
Token ID | 4004 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
burn | +0.034 |
blowing | +0.029 |
waving | +0.028 |
cheering | +0.026 |
my | +0.026 |
Neg logit contributions | |
ounces | -0.040 |
hell | -0.034 |
affe | -0.034 |
aces | -0.033 |
ger | -0.032 |
Token | toy |
Token ID | 13373 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
burn | +0.059 |
blowing | +0.053 |
waving | +0.051 |
spinning | +0.043 |
driveway | +0.043 |
Neg logit contributions | |
ounces | -0.108 |
ils | -0.098 |
affe | -0.097 |
hell | -0.096 |
izards | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
burn | +0.018 |
blowing | +0.016 |
waving | +0.016 |
spinning | +0.014 |
daddy | +0.014 |
Neg logit contributions | |
ounces | -0.028 |
ils | -0.025 |
bors | -0.025 |
izards | -0.025 |
affe | -0.025 |
Token | He |
Token ID | 679 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
burn | +0.002 |
waving | +0.002 |
blowing | +0.002 |
daddy | +0.002 |
crying | +0.002 |
Neg logit contributions | |
ounces | -0.004 |
ils | -0.004 |
izards | -0.003 |
bors | -0.003 |
isy | -0.003 |
Token | looked |
Token ID | 3114 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
burn | +0.000 |
blowing | +0.000 |
waving | +0.000 |
spinning | +0.000 |
neighborhood | +0.000 |
Neg logit contributions | |
ounces | -0.000 |
ils | -0.000 |
izards | -0.000 |
affe | -0.000 |
bors | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
burn | +0.009 |
blowing | +0.008 |
waving | +0.008 |
driveway | +0.007 |
neighborhood | +0.007 |
Neg logit contributions | |
ounces | -0.017 |
ils | -0.016 |
izards | -0.015 |
hell | -0.015 |
affe | -0.015 |
Token | sees |
Token ID | 7224 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
burn | +0.019 |
blowing | +0.016 |
waving | +0.014 |
neighborhood | +0.012 |
driveway | +0.012 |
Neg logit contributions | |
ounces | -0.034 |
izards | -0.031 |
ils | -0.031 |
bors | -0.031 |
affe | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
ounces | +0.056 |
ils | +0.051 |
bors | +0.051 |
affe | +0.050 |
izards | +0.050 |
Neg logit contributions | |
burn | -0.031 |
blowing | -0.028 |
waving | -0.028 |
crying | -0.025 |
daddy | -0.024 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
burn | +0.019 |
blowing | +0.017 |
waving | +0.016 |
driveway | +0.015 |
vac | +0.015 |
Neg logit contributions | |
ounces | -0.021 |
affe | -0.020 |
hell | -0.019 |
isy | -0.018 |
bors | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
ounces | +0.007 |
ils | +0.006 |
bors | +0.006 |
affe | +0.006 |
izards | +0.006 |
Neg logit contributions | |
burn | -0.005 |
waving | -0.004 |
blowing | -0.004 |
spinning | -0.004 |
crying | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
burn | +0.016 |
waving | +0.015 |
blowing | +0.014 |
crying | +0.013 |
daddy | +0.013 |
Neg logit contributions | |
ounces | -0.031 |
ils | -0.030 |
bors | -0.029 |
isy | -0.028 |
izards | -0.028 |
Token | smiles |
Token ID | 21845 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
ounces | +0.035 |
izards | +0.033 |
affe | +0.032 |
ils | +0.031 |
bors | +0.031 |
Neg logit contributions | |
burn | -0.031 |
blowing | -0.026 |
driveway | -0.023 |
waving | -0.023 |
daddy | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
burn | +0.098 |
blowing | +0.085 |
driveway | +0.084 |
waving | +0.080 |
neighborhood | +0.077 |
Neg logit contributions | |
ounces | -0.102 |
izards | -0.097 |
ils | -0.096 |
affe | -0.096 |
hell | -0.093 |
Token | says |
Token ID | 1139 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
burn | +0.016 |
blowing | +0.014 |
waving | +0.013 |
driveway | +0.013 |
neighborhood | +0.013 |
Neg logit contributions | |
ounces | -0.019 |
izards | -0.017 |
ils | -0.017 |
affe | -0.017 |
bors | -0.016 |
Token | hello |
Token ID | 23748 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
ounces | +0.098 |
ils | +0.088 |
bors | +0.087 |
affe | +0.084 |
ns | +0.084 |
Neg logit contributions | |
waving | -0.041 |
burn | -0.038 |
blowing | -0.036 |
crying | -0.035 |
spinning | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
ounces | +0.015 |
ils | +0.013 |
bors | +0.013 |
izards | +0.013 |
affe | +0.013 |
Neg logit contributions | |
burn | -0.009 |
waving | -0.008 |
blowing | -0.007 |
crying | -0.007 |
daddy | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ounces | +0.023 |
ils | +0.021 |
hell | +0.021 |
izards | +0.020 |
bors | +0.020 |
Neg logit contributions | |
burn | -0.011 |
waving | -0.010 |
blowing | -0.010 |
crying | -0.009 |
daddy | -0.009 |