Token | frightened |
Token ID | 24776 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
kiss | +0.102 |
welcome | +0.100 |
luck | +0.099 |
bye | +0.096 |
payoff | +0.093 |
Neg logit contributions | |
ts | -0.168 |
opes | -0.160 |
od | -0.158 |
ptions | -0.158 |
tered | -0.158 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
opes | +0.068 |
ts | +0.068 |
ants | +0.067 |
ivating | +0.067 |
od | +0.066 |
Neg logit contributions | |
kiss | -0.028 |
welcome | -0.024 |
helper | -0.023 |
bless | -0.022 |
payoff | -0.022 |
Token | said |
Token ID | 531 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
kiss | +0.014 |
welcome | +0.013 |
helper | +0.012 |
payoff | +0.012 |
bless | +0.012 |
Neg logit contributions | |
ts | -0.016 |
opes | -0.016 |
ivating | -0.016 |
ants | -0.016 |
tered | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
kiss | +0.027 |
welcome | +0.022 |
helper | +0.020 |
payoff | +0.020 |
bless | +0.020 |
Neg logit contributions | |
ts | -0.093 |
opes | -0.093 |
ants | -0.092 |
ivating | -0.092 |
od | -0.091 |
Token | " |
Token ID | 366 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
kiss | +0.033 |
welcome | +0.030 |
bless | +0.029 |
thanks | +0.029 |
helper | +0.028 |
Neg logit contributions | |
ts | -0.030 |
opes | -0.029 |
ivating | -0.029 |
ants | -0.029 |
od | -0.028 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ts | +0.053 |
opes | +0.053 |
ants | +0.052 |
ivating | +0.052 |
od | +0.051 |
Neg logit contributions | |
kiss | -0.045 |
welcome | -0.041 |
helper | -0.039 |
luck | -0.039 |
bless | -0.039 |
Token | my |
Token ID | 1820 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
guard | +0.195 |
distance | +0.195 |
masse | +0.180 |
payoff | +0.172 |
bye | +0.166 |
Neg logit contributions | |
od | -0.254 |
opes | -0.245 |
ants | -0.241 |
assed | -0.231 |
rave | -0.230 |
Token | , |
Token ID | 11 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
distance | +0.069 |
someday | +0.058 |
guard | +0.058 |
seat | +0.057 |
payoff | +0.056 |
Neg logit contributions | |
od | -0.114 |
assed | -0.109 |
opes | -0.109 |
ts | -0.108 |
ving | -0.108 |
Token | there |
Token ID | 612 |
Feature activation | -7.66e-03 |
Pos logit contributions | |
bye | +0.054 |
kiss | +0.054 |
distance | +0.050 |
eye | +0.049 |
payoff | +0.049 |
Neg logit contributions | |
ts | -0.074 |
nam | -0.068 |
od | -0.068 |
ants | -0.067 |
assed | -0.067 |
Token | 's |
Token ID | 338 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
od | +0.011 |
ts | +0.011 |
ggies | +0.011 |
opes | +0.011 |
like | +0.011 |
Neg logit contributions | |
kiss | -0.011 |
helper | -0.010 |
payoff | -0.010 |
bye | -0.010 |
bless | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +4.75e-03 |
Pos logit contributions | |
kiss | +0.036 |
welcome | +0.033 |
helper | +0.033 |
bless | +0.033 |
payoff | +0.032 |
Neg logit contributions | |
ts | -0.032 |
opes | -0.031 |
ivating | -0.031 |
ants | -0.030 |
tered | -0.030 |
Token | surprised |
Token ID | 6655 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
ts | +0.138 |
opes | +0.138 |
nam | +0.133 |
tered | +0.131 |
ptions | +0.131 |
Neg logit contributions | |
kiss | -0.062 |
? | -0.059 |
welcome | -0.058 |
girl | -0.057 |
, | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
ts | +0.050 |
opes | +0.050 |
ants | +0.050 |
od | +0.050 |
ivating | +0.049 |
Neg logit contributions | |
kiss | -0.029 |
welcome | -0.026 |
bless | -0.026 |
helper | -0.026 |
shines | -0.026 |
Token | shouted |
Token ID | 17293 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
kiss | +0.017 |
helper | +0.016 |
welcome | +0.016 |
payoff | +0.015 |
bless | +0.015 |
Neg logit contributions | |
ts | -0.022 |
opes | -0.021 |
ivating | -0.021 |
tered | -0.020 |
like | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +7.81e-03 |
Pos logit contributions | |
kiss | +0.017 |
welcome | +0.015 |
helper | +0.014 |
payoff | +0.014 |
bless | +0.014 |
Neg logit contributions | |
opes | -0.033 |
ts | -0.033 |
ants | -0.033 |
ivating | -0.033 |
od | -0.032 |
Token | " |
Token ID | 366 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
kiss | +0.013 |
welcome | +0.012 |
payoff | +0.011 |
thanks | +0.011 |
helper | +0.011 |
Neg logit contributions | |
ts | -0.011 |
opes | -0.011 |
ants | -0.011 |
ivating | -0.011 |
od | -0.010 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ts | +0.059 |
opes | +0.059 |
ants | +0.057 |
ivating | +0.056 |
od | +0.055 |
Neg logit contributions | |
kiss | -0.047 |
welcome | -0.042 |
payoff | -0.041 |
bless | -0.040 |
helper | -0.040 |
Token | ! |
Token ID | 0 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
distance | +0.177 |
guard | +0.176 |
masse | +0.163 |
payoff | +0.159 |
bye | +0.157 |
Neg logit contributions | |
od | -0.268 |
opes | -0.259 |
ants | -0.255 |
assed | -0.249 |
rave | -0.241 |
Token | The |
Token ID | 383 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
kiss | +0.027 |
luck | +0.025 |
welcome | +0.024 |
payoff | +0.024 |
eye | +0.024 |
Neg logit contributions | |
ants | -0.037 |
opes | -0.036 |
ivating | -0.036 |
od | -0.036 |
ts | -0.036 |
Token | last |
Token ID | 938 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
kiss | +0.040 |
thanks | +0.036 |
welcome | +0.036 |
bless | +0.036 |
bye | +0.035 |
Neg logit contributions | |
opes | -0.057 |
ts | -0.056 |
ivating | -0.055 |
targets | -0.055 |
amus | -0.055 |
Token | flower |
Token ID | 15061 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
kiss | +0.075 |
bless | +0.072 |
bye | +0.069 |
helper | +0.068 |
luck | +0.068 |
Neg logit contributions | |
ggies | -0.108 |
opes | -0.101 |
ts | -0.101 |
od | -0.100 |
targets | -0.098 |
Token | is |
Token ID | 318 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
kiss | +0.016 |
payoff | +0.015 |
helper | +0.015 |
welcome | +0.015 |
luck | +0.015 |
Neg logit contributions | |
opes | -0.028 |
ts | -0.028 |
od | -0.028 |
webs | -0.027 |
ivating | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
kiss | +0.047 |
payoff | +0.042 |
welcome | +0.042 |
bye | +0.042 |
eye | +0.041 |
Neg logit contributions | |
ts | -0.043 |
opes | -0.041 |
ivating | -0.041 |
od | -0.040 |
tered | -0.040 |
Token | He |
Token ID | 679 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
kiss | +0.047 |
welcome | +0.043 |
helper | +0.041 |
luck | +0.041 |
payoff | +0.041 |
Neg logit contributions | |
opes | -0.054 |
ts | -0.053 |
ants | -0.053 |
ivating | -0.053 |
od | -0.051 |
Token | says |
Token ID | 1139 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
kiss | +0.016 |
welcome | +0.014 |
helper | +0.014 |
payoff | +0.013 |
bless | +0.013 |
Neg logit contributions | |
ts | -0.023 |
opes | -0.023 |
ants | -0.023 |
ivating | -0.023 |
od | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
kiss | +0.039 |
welcome | +0.034 |
helper | +0.032 |
eye | +0.032 |
payoff | +0.031 |
Neg logit contributions | |
ts | -0.093 |
opes | -0.091 |
ants | -0.091 |
od | -0.090 |
tered | -0.089 |
Token | " |
Token ID | 366 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
kiss | +0.027 |
welcome | +0.025 |
bless | +0.024 |
helper | +0.024 |
thanks | +0.024 |
Neg logit contributions | |
ts | -0.023 |
opes | -0.023 |
ivating | -0.022 |
ants | -0.022 |
od | -0.021 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ivating | +0.041 |
like | +0.041 |
tered | +0.041 |
ts | +0.041 |
ants | +0.041 |
Neg logit contributions | |
kiss | -0.041 |
welcome | -0.038 |
luck | -0.038 |
helper | -0.037 |
eye | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
distance | +0.185 |
guard | +0.172 |
masse | +0.168 |
payoff | +0.153 |
repay | +0.152 |
Neg logit contributions | |
od | -0.270 |
opes | -0.267 |
ants | -0.258 |
ts | -0.249 |
assed | -0.247 |
Token | can |
Token ID | 460 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
bye | +0.053 |
kiss | +0.051 |
distance | +0.049 |
eye | +0.047 |
payoff | +0.047 |
Neg logit contributions | |
ts | -0.081 |
od | -0.076 |
nam | -0.075 |
assed | -0.074 |
IT | -0.074 |
Token | we |
Token ID | 356 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
luck | +0.055 |
eye | +0.054 |
distance | +0.052 |
payoff | +0.051 |
helper | +0.050 |
Neg logit contributions | |
ts | -0.087 |
Whoever | -0.084 |
ants | -0.083 |
hardly | -0.082 |
nam | -0.082 |
Token | watch |
Token ID | 2342 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
payoff | +0.048 |
luck | +0.047 |
shines | +0.046 |
ment | +0.045 |
thanks | +0.045 |
Neg logit contributions | |
ivating | -0.057 |
Whoever | -0.056 |
tered | -0.056 |
ts | -0.056 |
od | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | -8.20e-03 |
Pos logit contributions | |
kiss | +0.056 |
? | +0.052 |
, | +0.051 |
welcome | +0.050 |
thanks | +0.047 |
Neg logit contributions | |
opes | -0.086 |
tered | -0.085 |
ts | -0.085 |
ivating | -0.085 |
ants | -0.083 |
Token | my |
Token ID | 1820 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
kiss | +0.130 |
payoff | +0.127 |
welcome | +0.126 |
luck | +0.124 |
bye | +0.124 |
Neg logit contributions | |
ts | -0.246 |
opes | -0.243 |
ants | -0.243 |
od | -0.238 |
tered | -0.235 |
Token | and |
Token ID | 290 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
kiss | +0.065 |
payoff | +0.062 |
welcome | +0.062 |
bye | +0.059 |
luck | +0.059 |
Neg logit contributions | |
ts | -0.123 |
opes | -0.123 |
ants | -0.121 |
tered | -0.118 |
od | -0.118 |
Token | said |
Token ID | 531 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
kiss | +0.040 |
welcome | +0.038 |
eye | +0.036 |
luck | +0.036 |
bye | +0.035 |
Neg logit contributions | |
ts | -0.069 |
nam | -0.066 |
opes | -0.066 |
tered | -0.065 |
ants | -0.065 |
Token | , |
Token ID | 11 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
kiss | +0.032 |
welcome | +0.028 |
helper | +0.027 |
payoff | +0.026 |
eye | +0.026 |
Neg logit contributions | |
ts | -0.074 |
opes | -0.074 |
ants | -0.073 |
ivating | -0.073 |
tered | -0.072 |
Token | " |
Token ID | 366 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
kiss | +0.037 |
welcome | +0.034 |
helper | +0.032 |
bless | +0.032 |
thanks | +0.032 |
Neg logit contributions | |
ts | -0.032 |
opes | -0.032 |
ivating | -0.031 |
ants | -0.031 |
od | -0.030 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
opes | +0.053 |
ts | +0.053 |
ants | +0.051 |
ivating | +0.051 |
od | +0.050 |
Neg logit contributions | |
kiss | -0.039 |
welcome | -0.035 |
payoff | -0.033 |
helper | -0.033 |
bless | -0.033 |
Token | my |
Token ID | 1820 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
distance | +0.200 |
guard | +0.193 |
masse | +0.178 |
payoff | +0.177 |
kiss | +0.175 |
Neg logit contributions | |
ants | -0.253 |
od | -0.249 |
opes | -0.245 |
ptions | -0.235 |
rave | -0.231 |
Token | , |
Token ID | 11 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
distance | +0.070 |
seat | +0.056 |
guard | +0.055 |
cottage | +0.054 |
kiss | +0.053 |
Neg logit contributions | |
ts | -0.102 |
od | -0.101 |
ants | -0.099 |
ving | -0.098 |
opes | -0.097 |
Token | look |
Token ID | 804 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
kiss | +0.043 |
distance | +0.043 |
bye | +0.043 |
eye | +0.040 |
payoff | +0.040 |
Neg logit contributions | |
ts | -0.071 |
nam | -0.068 |
ants | -0.067 |
Whoever | -0.066 |
od | -0.066 |
Token | ! |
Token ID | 0 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
kiss | +0.086 |
welcome | +0.077 |
payoff | +0.076 |
helper | +0.075 |
bless | +0.075 |
Neg logit contributions | |
ts | -0.089 |
opes | -0.089 |
ants | -0.087 |
ivating | -0.087 |
od | -0.085 |
Token | An |
Token ID | 1052 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
kiss | +0.022 |
luck | +0.022 |
payoff | +0.020 |
eye | +0.020 |
wave | +0.020 |
Neg logit contributions | |
ants | -0.032 |
ivating | -0.031 |
opes | -0.031 |
od | -0.031 |
like | -0.031 |
Token | them |
Token ID | 606 |
Feature activation | -5.99e-03 |
Pos logit contributions | |
opes | +0.028 |
ts | +0.028 |
issors | +0.027 |
ivating | +0.027 |
ination | +0.027 |
Neg logit contributions | |
kiss | -0.024 |
, | -0.023 |
welcome | -0.023 |
girl | -0.023 |
luck | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +2.54e-04 |
Pos logit contributions | |
ts | +0.008 |
opes | +0.008 |
ants | +0.007 |
ivating | +0.007 |
od | +0.007 |
Neg logit contributions | |
kiss | -0.010 |
welcome | -0.010 |
helper | -0.009 |
payoff | -0.009 |
bless | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
welcome | +0.000 |
kiss | +0.000 |
bye | +0.000 |
luck | +0.000 |
payoff | +0.000 |
Neg logit contributions | |
ts | -0.000 |
opes | -0.000 |
tered | -0.000 |
nam | -0.000 |
ants | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -2.67e-03 |
Pos logit contributions | |
kiss | +0.009 |
welcome | +0.007 |
luck | +0.005 |
helper | +0.005 |
thanks | +0.005 |
Neg logit contributions | |
opes | -0.064 |
ts | -0.063 |
ivating | -0.063 |
ants | -0.062 |
like | -0.061 |
Token | " |
Token ID | 366 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
ts | +0.005 |
opes | +0.004 |
targets | +0.004 |
ivating | +0.004 |
ants | +0.004 |
Neg logit contributions | |
kiss | -0.004 |
welcome | -0.003 |
, | -0.003 |
thanks | -0.003 |
prayer | -0.003 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
opes | +0.064 |
ts | +0.064 |
ants | +0.063 |
ivating | +0.063 |
od | +0.061 |
Neg logit contributions | |
kiss | -0.064 |
welcome | -0.059 |
helper | -0.056 |
luck | -0.056 |
bless | -0.056 |
Token | my |
Token ID | 1820 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
kiss | +0.163 |
guard | +0.161 |
distance | +0.159 |
payoff | +0.151 |
bye | +0.147 |
Neg logit contributions | |
od | -0.292 |
ants | -0.289 |
opes | -0.286 |
ptions | -0.272 |
bles | -0.257 |
Token | , |
Token ID | 11 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
distance | +0.064 |
kiss | +0.057 |
guard | +0.056 |
payoff | +0.053 |
eye | +0.052 |
Neg logit contributions | |
od | -0.117 |
ants | -0.113 |
opes | -0.112 |
assed | -0.108 |
ts | -0.108 |
Token | let |
Token ID | 1309 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
kiss | +0.052 |
bye | +0.048 |
payoff | +0.046 |
distance | +0.046 |
welcome | +0.045 |
Neg logit contributions | |
ts | -0.072 |
od | -0.071 |
nam | -0.070 |
ants | -0.070 |
opes | -0.069 |
Token | 's |
Token ID | 338 |
Feature activation | +2.99e-03 |
Pos logit contributions | |
kiss | +0.066 |
welcome | +0.060 |
luck | +0.057 |
payoff | +0.057 |
helper | +0.057 |
Neg logit contributions | |
ts | -0.090 |
opes | -0.090 |
ants | -0.089 |
ivating | -0.088 |
od | -0.087 |
Token | wrap |
Token ID | 14441 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
kiss | +0.003 |
payoff | +0.003 |
luck | +0.003 |
bye | +0.003 |
girl | +0.003 |
Neg logit contributions | |
ts | -0.005 |
ivating | -0.005 |
opes | -0.005 |
ants | -0.005 |
od | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
ants | +0.004 |
opes | +0.004 |
od | +0.004 |
ivating | +0.004 |
ts | +0.004 |
Neg logit contributions | |
kiss | -0.003 |
welcome | -0.003 |
wave | -0.002 |
return | -0.002 |
thanks | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +7.99e-03 |
Pos logit contributions | |
kiss | +0.033 |
payoff | +0.031 |
welcome | +0.030 |
bless | +0.029 |
bye | +0.029 |
Neg logit contributions | |
opes | -0.066 |
targets | -0.064 |
ts | -0.063 |
amus | -0.062 |
ants | -0.062 |
Token | say |
Token ID | 910 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
kiss | +0.009 |
luck | +0.009 |
eye | +0.009 |
helper | +0.009 |
payoff | +0.009 |
Neg logit contributions | |
ts | -0.013 |
nam | -0.013 |
like | -0.013 |
assed | -0.013 |
tered | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
kiss | +0.058 |
welcome | +0.053 |
luck | +0.048 |
thanks | +0.047 |
bless | +0.046 |
Neg logit contributions | |
opes | -0.122 |
ts | -0.121 |
ants | -0.120 |
ivating | -0.120 |
like | -0.116 |
Token | " |
Token ID | 366 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
kiss | +0.020 |
welcome | +0.019 |
thanks | +0.018 |
bless | +0.018 |
helper | +0.018 |
Neg logit contributions | |
ts | -0.018 |
opes | -0.018 |
ants | -0.017 |
ivating | -0.017 |
od | -0.017 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ivating | +0.051 |
tered | +0.050 |
opes | +0.050 |
ts | +0.050 |
like | +0.050 |
Neg logit contributions | |
kiss | -0.044 |
welcome | -0.042 |
luck | -0.042 |
helper | -0.041 |
eye | -0.041 |
Token | my |
Token ID | 1820 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
distance | +0.192 |
guard | +0.188 |
masse | +0.181 |
payoff | +0.176 |
kiss | +0.166 |
Neg logit contributions | |
od | -0.251 |
opes | -0.239 |
ants | -0.236 |
having | -0.224 |
assed | -0.224 |
Token | , |
Token ID | 11 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
distance | +0.071 |
payoff | +0.058 |
masse | +0.058 |
cottage | +0.057 |
guard | +0.056 |
Neg logit contributions | |
od | -0.104 |
ts | -0.101 |
assed | -0.100 |
scored | -0.099 |
opes | -0.099 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
kiss | +0.046 |
bye | +0.044 |
distance | +0.043 |
eye | +0.042 |
payoff | +0.042 |
Neg logit contributions | |
ts | -0.074 |
nam | -0.072 |
od | -0.071 |
viol | -0.070 |
ants | -0.070 |
Token | my |
Token ID | 1820 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
distance | +0.202 |
reward | +0.189 |
payoff | +0.189 |
masse | +0.187 |
guard | +0.184 |
Neg logit contributions | |
od | -0.205 |
ants | -0.196 |
opes | -0.195 |
having | -0.188 |
ts | -0.187 |
Token | , |
Token ID | 11 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
distance | +0.062 |
kiss | +0.053 |
payoff | +0.052 |
cottage | +0.052 |
masse | +0.051 |
Neg logit contributions | |
ts | -0.080 |
od | -0.078 |
opes | -0.075 |
assed | -0.074 |
ving | -0.073 |
Token | sky |
Token ID | 6766 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
kiss | +0.021 |
repay | +0.021 |
helper | +0.021 |
someday | +0.021 |
guard | +0.021 |
Neg logit contributions | |
targets | -0.030 |
opes | -0.029 |
webs | -0.029 |
ination | -0.029 |
nam | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +3.39e-03 |
Pos logit contributions | |
helper | +0.055 |
kiss | +0.054 |
payoff | +0.051 |
reward | +0.050 |
bless | +0.050 |
Neg logit contributions | |
opes | -0.091 |
od | -0.090 |
ts | -0.089 |
like | -0.088 |
ants | -0.087 |
Token | said |
Token ID | 531 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
kiss | +0.005 |
welcome | +0.004 |
helper | +0.004 |
payoff | +0.004 |
bless | +0.004 |
Neg logit contributions | |
ts | -0.005 |
opes | -0.005 |
tered | -0.005 |
od | -0.005 |
like | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
kiss | +0.021 |
welcome | +0.018 |
helper | +0.016 |
luck | +0.016 |
payoff | +0.016 |
Neg logit contributions | |
opes | -0.059 |
ts | -0.059 |
ants | -0.059 |
ivating | -0.058 |
od | -0.057 |
Token | " |
Token ID | 366 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
kiss | +0.019 |
welcome | +0.018 |
bless | +0.017 |
helper | +0.017 |
thanks | +0.017 |
Neg logit contributions | |
ts | -0.016 |
opes | -0.016 |
ants | -0.016 |
ivating | -0.016 |
od | -0.015 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ivating | +0.058 |
ants | +0.057 |
od | +0.056 |
like | +0.056 |
opes | +0.056 |
Neg logit contributions | |
kiss | -0.054 |
welcome | -0.051 |
luck | -0.050 |
helper | -0.049 |
eye | -0.048 |
Token | my |
Token ID | 1820 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
guard | +0.196 |
distance | +0.192 |
masse | +0.181 |
payoff | +0.169 |
repay | +0.164 |
Neg logit contributions | |
od | -0.262 |
ants | -0.243 |
opes | -0.242 |
ptions | -0.227 |
having | -0.227 |
Token | , |
Token ID | 11 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
distance | +0.070 |
guard | +0.060 |
masse | +0.058 |
payoff | +0.056 |
seat | +0.056 |
Neg logit contributions | |
od | -0.112 |
ts | -0.104 |
opes | -0.103 |
ants | -0.101 |
assed | -0.100 |
Token | look |
Token ID | 804 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
kiss | +0.049 |
bye | +0.047 |
distance | +0.046 |
payoff | +0.045 |
eye | +0.044 |
Neg logit contributions | |
ts | -0.070 |
nam | -0.069 |
od | -0.069 |
ants | -0.066 |
viol | -0.065 |
Token | ! |
Token ID | 0 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
kiss | +0.083 |
welcome | +0.075 |
payoff | +0.073 |
helper | +0.072 |
bless | +0.072 |
Neg logit contributions | |
ts | -0.094 |
opes | -0.094 |
ants | -0.092 |
ivating | -0.092 |
od | -0.091 |
Token | A |
Token ID | 317 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
kiss | +0.025 |
luck | +0.024 |
payoff | +0.023 |
helper | +0.023 |
welcome | +0.022 |
Neg logit contributions | |
ants | -0.029 |
ivating | -0.028 |
opes | -0.028 |
od | -0.028 |
ination | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
kiss | +0.037 |
welcome | +0.034 |
surprise | +0.032 |
thanks | +0.032 |
girl | +0.032 |
Neg logit contributions | |
ivating | -0.050 |
opes | -0.050 |
ants | -0.050 |
ts | -0.048 |
tered | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
kiss | +0.012 |
welcome | +0.011 |
helper | +0.010 |
payoff | +0.010 |
bless | +0.010 |
Neg logit contributions | |
opes | -0.018 |
ts | -0.018 |
ants | -0.018 |
ivating | -0.018 |
tered | -0.018 |
Token | shouted |
Token ID | 17293 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
kiss | +0.012 |
welcome | +0.012 |
helper | +0.011 |
bless | +0.011 |
luck | +0.011 |
Neg logit contributions | |
ts | -0.021 |
opes | -0.021 |
tered | -0.020 |
od | -0.020 |
ants | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +3.56e-03 |
Pos logit contributions | |
kiss | +0.014 |
welcome | +0.013 |
luck | +0.011 |
thanks | +0.011 |
helper | +0.011 |
Neg logit contributions | |
ts | -0.037 |
opes | -0.036 |
ivating | -0.036 |
ants | -0.036 |
like | -0.035 |
Token | " |
Token ID | 366 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
kiss | +0.005 |
welcome | +0.005 |
wave | +0.005 |
thanks | +0.005 |
, | +0.005 |
Neg logit contributions | |
ts | -0.005 |
opes | -0.005 |
ants | -0.005 |
ivating | -0.005 |
targets | -0.005 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ts | +0.067 |
opes | +0.066 |
ants | +0.063 |
ivating | +0.061 |
od | +0.060 |
Neg logit contributions | |
kiss | -0.053 |
payoff | -0.046 |
welcome | -0.046 |
bye | -0.046 |
girl | -0.045 |
Token | my |
Token ID | 1820 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
distance | +0.157 |
kiss | +0.152 |
guard | +0.151 |
payoff | +0.145 |
masse | +0.142 |
Neg logit contributions | |
od | -0.296 |
opes | -0.288 |
ants | -0.287 |
ptions | -0.269 |
assed | -0.265 |
Token | , |
Token ID | 11 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
distance | +0.060 |
kiss | +0.051 |
cleaner | +0.050 |
payoff | +0.049 |
guard | +0.047 |
Neg logit contributions | |
od | -0.122 |
opes | -0.117 |
ants | -0.115 |
assed | -0.114 |
ving | -0.114 |
Token | look |
Token ID | 804 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
kiss | +0.052 |
bye | +0.050 |
distance | +0.047 |
payoff | +0.047 |
welcome | +0.046 |
Neg logit contributions | |
ts | -0.075 |
od | -0.072 |
ants | -0.071 |
opes | -0.070 |
nam | -0.069 |
Token | ! |
Token ID | 0 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
kiss | +0.063 |
welcome | +0.055 |
payoff | +0.054 |
helper | +0.054 |
bless | +0.053 |
Neg logit contributions | |
ts | -0.110 |
opes | -0.110 |
ants | -0.108 |
ivating | -0.108 |
od | -0.107 |
Token | A |
Token ID | 317 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
kiss | +0.026 |
welcome | +0.024 |
luck | +0.023 |
payoff | +0.023 |
helper | +0.023 |
Neg logit contributions | |
opes | -0.033 |
ants | -0.033 |
ivating | -0.032 |
ts | -0.032 |
od | -0.032 |
Token | mom |
Token ID | 1995 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
bye | +0.028 |
payoff | +0.027 |
kiss | +0.027 |
welcome | +0.026 |
luck | +0.025 |
Neg logit contributions | |
opes | -0.049 |
nam | -0.048 |
targets | -0.048 |
ts | -0.047 |
viol | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | +8.77e-03 |
Pos logit contributions | |
payoff | +0.119 |
bye | +0.117 |
luck | +0.113 |
guard | +0.105 |
kiss | +0.105 |
Neg logit contributions | |
ants | -0.124 |
od | -0.123 |
opes | -0.120 |
like | -0.118 |
issors | -0.116 |
Token | said |
Token ID | 531 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
bye | +0.012 |
luck | +0.012 |
eye | +0.011 |
umm | +0.011 |
welcome | +0.011 |
Neg logit contributions | |
nam | -0.015 |
ts | -0.014 |
assed | -0.012 |
viol | -0.012 |
ved | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +9.91e-03 |
Pos logit contributions | |
kiss | +0.014 |
helper | +0.011 |
eye | +0.011 |
payoff | +0.011 |
welcome | +0.011 |
Neg logit contributions | |
ts | -0.058 |
ants | -0.057 |
tered | -0.057 |
od | -0.057 |
opes | -0.057 |
Token | ' |
Token ID | 705 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
kiss | +0.017 |
welcome | +0.016 |
helper | +0.015 |
payoff | +0.015 |
luck | +0.015 |
Neg logit contributions | |
opes | -0.013 |
ts | -0.013 |
ants | -0.012 |
ivating | -0.012 |
od | -0.012 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
like | +0.019 |
nam | +0.018 |
ivating | +0.018 |
tered | +0.018 |
Whoever | +0.017 |
Neg logit contributions | |
eye | -0.017 |
luck | -0.016 |
prayer | -0.016 |
thanks | -0.016 |
welcome | -0.016 |
Token | my |
Token ID | 1820 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
distance | +0.132 |
guard | +0.121 |
payoff | +0.114 |
kiss | +0.112 |
cleaner | +0.104 |
Neg logit contributions | |
ants | -0.312 |
od | -0.310 |
opes | -0.303 |
rave | -0.294 |
tered | -0.293 |
Token | , |
Token ID | 11 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
distance | +0.051 |
kiss | +0.043 |
cleaner | +0.042 |
guard | +0.041 |
payoff | +0.041 |
Neg logit contributions | |
od | -0.120 |
ants | -0.119 |
assed | -0.118 |
tered | -0.118 |
opes | -0.118 |
Token | look |
Token ID | 804 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
bye | +0.048 |
distance | +0.047 |
kiss | +0.047 |
payoff | +0.044 |
eye | +0.044 |
Neg logit contributions | |
ts | -0.070 |
od | -0.070 |
ants | -0.069 |
nam | -0.069 |
assed | -0.068 |
Token | what |
Token ID | 644 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
kiss | +0.087 |
welcome | +0.079 |
payoff | +0.079 |
helper | +0.078 |
bless | +0.076 |
Neg logit contributions | |
opes | -0.092 |
ts | -0.092 |
ants | -0.092 |
ivating | -0.091 |
od | -0.089 |
Token | I |
Token ID | 314 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
eye | +0.029 |
distance | +0.028 |
kiss | +0.028 |
bye | +0.026 |
payoff | +0.026 |
Neg logit contributions | |
od | -0.040 |
ts | -0.038 |
nam | -0.038 |
ggies | -0.037 |
viol | -0.037 |
Token | car |
Token ID | 1097 |
Feature activation | +4.60e-03 |
Pos logit contributions | |
opes | +0.009 |
targets | +0.009 |
ts | +0.009 |
od | +0.009 |
ants | +0.009 |
Neg logit contributions | |
kiss | -0.005 |
welcome | -0.005 |
payoff | -0.005 |
bless | -0.005 |
prayer | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +2.34e-03 |
Pos logit contributions | |
kiss | +0.005 |
welcome | +0.004 |
payoff | +0.004 |
helper | +0.004 |
bless | +0.004 |
Neg logit contributions | |
opes | -0.009 |
ts | -0.009 |
tered | -0.009 |
like | -0.009 |
ivating | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
kiss | +0.003 |
welcome | +0.003 |
helper | +0.003 |
bless | +0.003 |
payoff | +0.003 |
Neg logit contributions | |
ts | -0.004 |
opes | -0.004 |
tered | -0.004 |
ants | -0.004 |
targets | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
kiss | +0.026 |
welcome | +0.023 |
helper | +0.021 |
payoff | +0.021 |
bless | +0.021 |
Neg logit contributions | |
ts | -0.058 |
opes | -0.058 |
ants | -0.057 |
ivating | -0.057 |
od | -0.056 |
Token | " |
Token ID | 366 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
kiss | +0.021 |
welcome | +0.019 |
thanks | +0.018 |
bless | +0.018 |
helper | +0.018 |
Neg logit contributions | |
ts | -0.020 |
opes | -0.019 |
ivating | -0.019 |
ants | -0.019 |
like | -0.018 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ts | +0.064 |
opes | +0.064 |
ants | +0.063 |
ivating | +0.062 |
od | +0.061 |
Neg logit contributions | |
kiss | -0.053 |
welcome | -0.048 |
helper | -0.046 |
payoff | -0.046 |
luck | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
distance | +0.189 |
guard | +0.175 |
masse | +0.170 |
payoff | +0.163 |
cal | +0.158 |
Neg logit contributions | |
od | -0.264 |
opes | -0.250 |
ants | -0.246 |
rave | -0.237 |
having | -0.236 |
Token | can |
Token ID | 460 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
kiss | +0.044 |
bye | +0.039 |
payoff | +0.039 |
welcome | +0.039 |
distance | +0.039 |
Neg logit contributions | |
ts | -0.076 |
nam | -0.073 |
od | -0.073 |
ants | -0.072 |
opes | -0.072 |
Token | I |
Token ID | 314 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
luck | +0.047 |
eye | +0.046 |
distance | +0.046 |
kiss | +0.044 |
payoff | +0.044 |
Neg logit contributions | |
ts | -0.086 |
Whoever | -0.084 |
ants | -0.083 |
nam | -0.083 |
ivating | -0.081 |
Token | have |
Token ID | 423 |
Feature activation | +8.27e-03 |
Pos logit contributions | |
payoff | +0.067 |
luck | +0.063 |
ment | +0.062 |
shines | +0.062 |
thanks | +0.062 |
Neg logit contributions | |
Whoever | -0.071 |
hardly | -0.066 |
ving | -0.064 |
like | -0.064 |
tered | -0.064 |
Token | that |
Token ID | 326 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
kiss | +0.013 |
welcome | +0.013 |
eye | +0.012 |
prayer | +0.012 |
bless | +0.012 |
Neg logit contributions | |
ts | -0.011 |
opes | -0.011 |
targets | -0.011 |
viol | -0.011 |
ants | -0.011 |
Token | my |
Token ID | 1820 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
payoff | +0.119 |
luck | +0.118 |
bye | +0.118 |
relief | +0.109 |
guard | +0.108 |
Neg logit contributions | |
od | -0.124 |
ptions | -0.119 |
having | -0.117 |
ants | -0.117 |
Whoever | -0.117 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
kiss | +0.016 |
luck | +0.015 |
welcome | +0.015 |
payoff | +0.015 |
bye | +0.015 |
Neg logit contributions | |
opes | -0.022 |
ts | -0.021 |
ants | -0.021 |
od | -0.021 |
tered | -0.021 |
Token | said |
Token ID | 531 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
kiss | +0.013 |
luck | +0.012 |
welcome | +0.012 |
payoff | +0.012 |
bye | +0.012 |
Neg logit contributions | |
ts | -0.017 |
nam | -0.017 |
tered | -0.016 |
ants | -0.016 |
opes | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
kiss | +0.013 |
welcome | +0.009 |
helper | +0.008 |
payoff | +0.008 |
eye | +0.008 |
Neg logit contributions | |
ts | -0.077 |
opes | -0.077 |
ants | -0.077 |
tered | -0.076 |
od | -0.075 |
Token | " |
Token ID | 366 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
kiss | +0.015 |
, | +0.014 |
welcome | +0.014 |
prayer | +0.013 |
girl | +0.013 |
Neg logit contributions | |
ts | -0.019 |
opes | -0.019 |
targets | -0.019 |
ivating | -0.018 |
amus | -0.018 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
tered | +0.065 |
like | +0.062 |
ivating | +0.061 |
ptions | +0.059 |
nam | +0.059 |
Neg logit contributions | |
luck | -0.042 |
welcome | -0.039 |
thanks | -0.037 |
prayer | -0.036 |
kiss | -0.036 |
Token | my |
Token ID | 1820 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
guard | +0.237 |
service | +0.219 |
payoff | +0.217 |
ment | +0.213 |
distance | +0.213 |
Neg logit contributions | |
opes | -0.212 |
od | -0.208 |
ptions | -0.207 |
ants | -0.201 |
having | -0.185 |
Token | , |
Token ID | 11 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
guard | +0.082 |
distance | +0.080 |
ment | +0.076 |
masse | +0.072 |
seat | +0.072 |
Neg logit contributions | |
od | -0.078 |
assed | -0.078 |
opes | -0.077 |
ts | -0.074 |
everywhere | -0.074 |
Token | I |
Token ID | 314 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
kiss | +0.049 |
payoff | +0.048 |
bye | +0.047 |
distance | +0.047 |
luck | +0.046 |
Neg logit contributions | |
ts | -0.068 |
nam | -0.067 |
od | -0.064 |
tered | -0.063 |
viol | -0.063 |
Token | am |
Token ID | 716 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
payoff | +0.104 |
service | +0.098 |
keeper | +0.095 |
guard | +0.095 |
lady | +0.094 |
Neg logit contributions | |
tered | -0.087 |
tant | -0.085 |
hardly | -0.085 |
like | -0.083 |
ts | -0.080 |
Token | so |
Token ID | 523 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
kiss | +0.017 |
welcome | +0.015 |
helper | +0.014 |
payoff | +0.014 |
bless | +0.014 |
Neg logit contributions | |
opes | -0.026 |
ts | -0.026 |
ants | -0.025 |
ivating | -0.025 |
od | -0.025 |
Token | her |
Token ID | 607 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
kiss | +0.056 |
welcome | +0.052 |
helper | +0.047 |
bless | +0.047 |
luck | +0.047 |
Neg logit contributions | |
opes | -0.083 |
ivating | -0.083 |
ts | -0.083 |
ants | -0.081 |
like | -0.080 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
kiss | +0.041 |
bye | +0.040 |
payoff | +0.040 |
shines | +0.040 |
distance | +0.040 |
Neg logit contributions | |
od | -0.069 |
ants | -0.068 |
opes | -0.067 |
ts | -0.067 |
nam | -0.065 |
Token | my |
Token ID | 1820 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
kiss | +0.112 |
payoff | +0.105 |
bye | +0.103 |
wave | +0.098 |
distance | +0.094 |
Neg logit contributions | |
ants | -0.202 |
od | -0.201 |
ts | -0.191 |
opes | -0.191 |
like | -0.189 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
kiss | +0.035 |
welcome | +0.030 |
payoff | +0.029 |
bye | +0.028 |
luck | +0.028 |
Neg logit contributions | |
ants | -0.070 |
ts | -0.069 |
opes | -0.069 |
od | -0.068 |
ivating | -0.067 |
Token | " |
Token ID | 366 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
kiss | +0.018 |
welcome | +0.017 |
payoff | +0.017 |
luck | +0.017 |
helper | +0.016 |
Neg logit contributions | |
ts | -0.013 |
opes | -0.013 |
ants | -0.013 |
ivating | -0.012 |
od | -0.012 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ts | +0.058 |
opes | +0.058 |
ants | +0.058 |
ivating | +0.057 |
tered | +0.057 |
Neg logit contributions | |
kiss | -0.046 |
welcome | -0.043 |
luck | -0.041 |
thanks | -0.041 |
wave | -0.040 |
Token | my |
Token ID | 1820 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
kiss | +0.182 |
payoff | +0.180 |
guard | +0.179 |
service | +0.170 |
distance | +0.167 |
Neg logit contributions | |
opes | -0.260 |
ants | -0.259 |
od | -0.256 |
ptions | -0.247 |
ts | -0.242 |
Token | , |
Token ID | 11 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
distance | +0.064 |
kiss | +0.056 |
seat | +0.056 |
guard | +0.056 |
payoff | +0.055 |
Neg logit contributions | |
ts | -0.105 |
od | -0.104 |
opes | -0.104 |
ants | -0.101 |
assed | -0.097 |
Token | can |
Token ID | 460 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
kiss | +0.053 |
bye | +0.049 |
payoff | +0.048 |
luck | +0.046 |
distance | +0.045 |
Neg logit contributions | |
ts | -0.073 |
ants | -0.070 |
nam | -0.070 |
od | -0.069 |
opes | -0.068 |
Token | I |
Token ID | 314 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
luck | +0.054 |
eye | +0.051 |
payoff | +0.050 |
kiss | +0.049 |
distance | +0.049 |
Neg logit contributions | |
ts | -0.090 |
ants | -0.085 |
nam | -0.085 |
hardly | -0.083 |
opes | -0.083 |
Token | have |
Token ID | 423 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
payoff | +0.080 |
shines | +0.076 |
ment | +0.076 |
luck | +0.076 |
seat | +0.075 |
Neg logit contributions | |
hardly | -0.048 |
tered | -0.042 |
Whoever | -0.041 |
't | -0.041 |
all | -0.040 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.04e-03 |
Pos logit contributions | |
kiss | +0.014 |
welcome | +0.013 |
girl | +0.013 |
eye | +0.012 |
promise | +0.012 |
Neg logit contributions | |
ants | -0.023 |
opes | -0.022 |
ivating | -0.022 |
ts | -0.022 |
od | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -2.71e-03 |
Pos logit contributions | |
ts | +0.005 |
opes | +0.005 |
tered | +0.005 |
like | +0.005 |
od | +0.005 |
Neg logit contributions | |
kiss | -0.004 |
welcome | -0.004 |
bless | -0.004 |
helper | -0.004 |
wave | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
ts | +0.005 |
opes | +0.005 |
ants | +0.005 |
ivating | +0.005 |
od | +0.005 |
Neg logit contributions | |
kiss | -0.003 |
welcome | -0.003 |
helper | -0.003 |
payoff | -0.003 |
bless | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -9.17e-05 |
Pos logit contributions | |
kiss | +0.013 |
welcome | +0.011 |
helper | +0.010 |
payoff | +0.010 |
bless | +0.010 |
Neg logit contributions | |
ts | -0.038 |
opes | -0.038 |
ants | -0.037 |
ivating | -0.037 |
od | -0.037 |
Token | " |
Token ID | 366 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
ts | +0.000 |
opes | +0.000 |
ivating | +0.000 |
targets | +0.000 |
ants | +0.000 |
Neg logit contributions | |
kiss | -0.000 |
, | -0.000 |
welcome | -0.000 |
girl | -0.000 |
wave | -0.000 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
opes | +0.069 |
ts | +0.069 |
ants | +0.069 |
ivating | +0.068 |
od | +0.067 |
Neg logit contributions | |
kiss | -0.050 |
welcome | -0.046 |
helper | -0.043 |
luck | -0.043 |
bless | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
distance | +0.191 |
guard | +0.189 |
kiss | +0.179 |
masse | +0.171 |
payoff | +0.171 |
Neg logit contributions | |
od | -0.265 |
opes | -0.251 |
ants | -0.249 |
ptions | -0.241 |
issors | -0.233 |
Token | can |
Token ID | 460 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
kiss | +0.044 |
bye | +0.040 |
payoff | +0.039 |
distance | +0.038 |
welcome | +0.038 |
Neg logit contributions | |
ts | -0.073 |
od | -0.070 |
ants | -0.070 |
nam | -0.070 |
opes | -0.069 |
Token | we |
Token ID | 356 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
luck | +0.052 |
distance | +0.050 |
eye | +0.049 |
payoff | +0.049 |
kiss | +0.048 |
Neg logit contributions | |
nam | -0.091 |
ts | -0.089 |
ants | -0.088 |
Whoever | -0.087 |
ivating | -0.085 |
Token | buy |
Token ID | 2822 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
kiss | +0.050 |
payoff | +0.049 |
luck | +0.047 |
shines | +0.047 |
prayer | +0.047 |
Neg logit contributions | |
ivating | -0.059 |
ts | -0.058 |
tered | -0.058 |
Whoever | -0.058 |
issors | -0.058 |
Token | it |
Token ID | 340 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
kiss | +0.025 |
welcome | +0.023 |
helper | +0.022 |
payoff | +0.022 |
bless | +0.022 |
Neg logit contributions | |
ts | -0.023 |
opes | -0.023 |
ants | -0.022 |
ivating | -0.022 |
od | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +5.04e-03 |
Pos logit contributions | |
kiss | +0.029 |
welcome | +0.027 |
bless | +0.026 |
helper | +0.025 |
luck | +0.025 |
Neg logit contributions | |
opes | -0.045 |
ts | -0.045 |
tered | -0.045 |
od | -0.045 |
like | -0.045 |
Token | She |
Token ID | 1375 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
kiss | +0.007 |
welcome | +0.007 |
helper | +0.006 |
payoff | +0.006 |
bless | +0.006 |
Neg logit contributions | |
ts | -0.008 |
opes | -0.008 |
ants | -0.008 |
ivating | -0.008 |
od | -0.008 |
Token | says |
Token ID | 1139 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
kiss | +0.028 |
welcome | +0.025 |
helper | +0.024 |
payoff | +0.024 |
bless | +0.024 |
Neg logit contributions | |
ts | -0.042 |
opes | -0.042 |
ants | -0.042 |
ivating | -0.042 |
od | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +6.24e-03 |
Pos logit contributions | |
kiss | +0.032 |
welcome | +0.028 |
helper | +0.026 |
payoff | +0.025 |
bless | +0.025 |
Neg logit contributions | |
ts | -0.082 |
opes | -0.082 |
ants | -0.081 |
ivating | -0.080 |
od | -0.079 |
Token | " |
Token ID | 366 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
kiss | +0.010 |
welcome | +0.009 |
bless | +0.009 |
thanks | +0.009 |
helper | +0.009 |
Neg logit contributions | |
ts | -0.009 |
opes | -0.009 |
ivating | -0.009 |
ants | -0.009 |
like | -0.009 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ivating | +0.053 |
opes | +0.053 |
ts | +0.053 |
ants | +0.053 |
like | +0.052 |
Neg logit contributions | |
kiss | -0.049 |
welcome | -0.046 |
luck | -0.045 |
eye | -0.045 |
helper | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
distance | +0.186 |
guard | +0.183 |
masse | +0.166 |
repay | +0.155 |
kiss | +0.152 |
Neg logit contributions | |
od | -0.269 |
opes | -0.259 |
ants | -0.250 |
assed | -0.243 |
ptions | -0.243 |
Token | I |
Token ID | 314 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
kiss | +0.044 |
bye | +0.043 |
distance | +0.042 |
eye | +0.039 |
payoff | +0.039 |
Neg logit contributions | |
ts | -0.073 |
od | -0.072 |
nam | -0.072 |
viol | -0.069 |
ants | -0.069 |
Token | want |
Token ID | 765 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
payoff | +0.101 |
kiss | +0.100 |
distance | +0.100 |
bye | +0.099 |
prayer | +0.098 |
Neg logit contributions | |
ts | -0.106 |
od | -0.105 |
tered | -0.103 |
scored | -0.100 |
like | -0.100 |
Token | to |
Token ID | 284 |
Feature activation | -8.08e-03 |
Pos logit contributions | |
kiss | +0.044 |
welcome | +0.041 |
eye | +0.040 |
helper | +0.039 |
bless | +0.039 |
Neg logit contributions | |
ts | -0.049 |
opes | -0.049 |
ants | -0.048 |
od | -0.047 |
like | -0.047 |
Token | spin |
Token ID | 7906 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ts | +0.013 |
od | +0.013 |
ivating | +0.012 |
tered | +0.012 |
ants | +0.012 |
Neg logit contributions | |
luck | -0.010 |
payoff | -0.010 |
kiss | -0.010 |
girl | -0.010 |
thanks | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +4.48e-03 |
Pos logit contributions | |
ivating | +0.037 |
like | +0.037 |
od | +0.036 |
tered | +0.036 |
ants | +0.035 |
Neg logit contributions | |
kiss | -0.030 |
bless | -0.030 |
payoff | -0.029 |
repay | -0.029 |
shines | -0.029 |
Token | She |
Token ID | 1375 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
kiss | +0.005 |
welcome | +0.004 |
thanks | +0.004 |
girl | +0.004 |
helper | +0.004 |
Neg logit contributions | |
ts | -0.009 |
opes | -0.009 |
ants | -0.009 |
ivating | -0.009 |
od | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
kiss | +0.028 |
welcome | +0.024 |
wave | +0.023 |
eye | +0.023 |
thanks | +0.023 |
Neg logit contributions | |
ants | -0.044 |
opes | -0.044 |
ivating | -0.044 |
ts | -0.043 |
od | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | +5.50e-03 |
Pos logit contributions | |
kiss | +0.018 |
welcome | +0.014 |
helper | +0.014 |
payoff | +0.014 |
eye | +0.013 |
Neg logit contributions | |
ts | -0.068 |
ants | -0.068 |
opes | -0.068 |
od | -0.068 |
tered | -0.067 |
Token | " |
Token ID | 366 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
kiss | +0.008 |
welcome | +0.007 |
, | +0.007 |
prayer | +0.007 |
girl | +0.007 |
Neg logit contributions | |
ts | -0.010 |
opes | -0.009 |
ivating | -0.009 |
targets | -0.009 |
ants | -0.009 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
opes | +0.063 |
ts | +0.063 |
ants | +0.062 |
ivating | +0.061 |
od | +0.060 |
Neg logit contributions | |
kiss | -0.049 |
welcome | -0.044 |
helper | -0.042 |
payoff | -0.042 |
bless | -0.042 |
Token | my |
Token ID | 1820 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
distance | +0.201 |
guard | +0.199 |
masse | +0.192 |
payoff | +0.181 |
kiss | +0.179 |
Neg logit contributions | |
od | -0.247 |
opes | -0.241 |
ants | -0.237 |
ptions | -0.226 |
assed | -0.219 |
Token | , |
Token ID | 11 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
distance | +0.073 |
guard | +0.063 |
seat | +0.062 |
cleaner | +0.062 |
masse | +0.062 |
Neg logit contributions | |
od | -0.099 |
assed | -0.096 |
opes | -0.095 |
ts | -0.095 |
ants | -0.092 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
bye | +0.050 |
kiss | +0.049 |
distance | +0.047 |
payoff | +0.046 |
luck | +0.046 |
Neg logit contributions | |
ts | -0.069 |
nam | -0.065 |
od | -0.063 |
ants | -0.063 |
assed | -0.062 |
Token | my |
Token ID | 1820 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
distance | +0.205 |
masse | +0.191 |
guard | +0.189 |
reward | +0.187 |
payoff | +0.185 |
Neg logit contributions | |
od | -0.206 |
opes | -0.197 |
ants | -0.193 |
ts | -0.192 |
having | -0.184 |
Token | , |
Token ID | 11 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
distance | +0.063 |
seat | +0.055 |
kiss | +0.054 |
masse | +0.053 |
payoff | +0.053 |
Neg logit contributions | |
ts | -0.082 |
od | -0.082 |
opes | -0.079 |
assed | -0.078 |
scored | -0.075 |
Token | He |
Token ID | 679 |
Feature activation | -6.08e-04 |
Pos logit contributions | |
kiss | +0.007 |
welcome | +0.007 |
, | +0.006 |
girl | +0.006 |
? | +0.006 |
Neg logit contributions | |
ts | -0.013 |
ants | -0.012 |
opes | -0.012 |
targets | -0.012 |
ivating | -0.012 |
Token | called |
Token ID | 1444 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
ivating | +0.001 |
ants | +0.001 |
opes | +0.001 |
ts | +0.001 |
od | +0.001 |
Neg logit contributions | |
kiss | -0.001 |
welcome | -0.001 |
girl | -0.001 |
eye | -0.001 |
wave | -0.001 |
Token | out |
Token ID | 503 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
kiss | +0.028 |
welcome | +0.027 |
, | +0.024 |
thanks | +0.024 |
surprise | +0.024 |
Neg logit contributions | |
opes | -0.034 |
ants | -0.034 |
ivating | -0.034 |
od | -0.033 |
ts | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +8.07e-03 |
Pos logit contributions | |
kiss | +0.026 |
welcome | +0.023 |
helper | +0.021 |
luck | +0.021 |
bless | +0.021 |
Neg logit contributions | |
opes | -0.048 |
ts | -0.048 |
ivating | -0.047 |
ants | -0.047 |
od | -0.045 |
Token | " |
Token ID | 366 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
kiss | +0.012 |
welcome | +0.011 |
, | +0.011 |
girl | +0.010 |
thanks | +0.010 |
Neg logit contributions | |
ts | -0.013 |
opes | -0.013 |
ants | -0.013 |
ivating | -0.012 |
targets | -0.012 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ts | +0.059 |
opes | +0.059 |
ants | +0.059 |
ivating | +0.058 |
od | +0.057 |
Neg logit contributions | |
kiss | -0.035 |
welcome | -0.031 |
helper | -0.029 |
payoff | -0.029 |
bless | -0.029 |
Token | my |
Token ID | 1820 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
guard | +0.196 |
kiss | +0.191 |
payoff | +0.189 |
service | +0.180 |
cal | +0.179 |
Neg logit contributions | |
od | -0.243 |
opes | -0.242 |
ants | -0.237 |
ptions | -0.233 |
amus | -0.219 |
Token | , |
Token ID | 11 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
distance | +0.060 |
guard | +0.059 |
payoff | +0.058 |
kiss | +0.058 |
cleaner | +0.057 |
Neg logit contributions | |
od | -0.097 |
opes | -0.094 |
assed | -0.094 |
ants | -0.092 |
ts | -0.089 |
Token | I |
Token ID | 314 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
kiss | +0.052 |
payoff | +0.049 |
bye | +0.048 |
luck | +0.046 |
distance | +0.045 |
Neg logit contributions | |
ts | -0.067 |
nam | -0.062 |
od | -0.060 |
assed | -0.060 |
tered | -0.060 |
Token | 'm |
Token ID | 1101 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
payoff | +0.117 |
umm | +0.108 |
service | +0.106 |
luck | +0.104 |
wiser | +0.104 |
Neg logit contributions | |
like | -0.083 |
assed | -0.082 |
ts | -0.082 |
hardly | -0.081 |
tant | -0.080 |
Token | scared |
Token ID | 12008 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
kiss | +0.043 |
welcome | +0.040 |
helper | +0.038 |
bless | +0.037 |
luck | +0.037 |
Neg logit contributions | |
opes | -0.058 |
ts | -0.058 |
ants | -0.057 |
ivating | -0.056 |
od | -0.055 |
Token | stopped |
Token ID | 5025 |
Feature activation | -4.63e-03 |
Pos logit contributions | |
ts | +0.007 |
opes | +0.007 |
od | +0.007 |
ants | +0.007 |
tered | +0.007 |
Neg logit contributions | |
kiss | -0.005 |
welcome | -0.005 |
luck | -0.004 |
payoff | -0.004 |
bless | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
opes | +0.007 |
ts | +0.007 |
ivating | +0.007 |
od | +0.007 |
ants | +0.007 |
Neg logit contributions | |
kiss | -0.006 |
bye | -0.006 |
welcome | -0.006 |
payoff | -0.006 |
helper | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
welcome | +0.016 |
luck | +0.015 |
kiss | +0.015 |
eye | +0.015 |
helper | +0.015 |
Neg logit contributions | |
ts | -0.021 |
tered | -0.020 |
ivating | -0.019 |
nam | -0.019 |
od | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
kiss | +0.023 |
welcome | +0.019 |
helper | +0.018 |
payoff | +0.017 |
bless | +0.017 |
Neg logit contributions | |
ts | -0.083 |
opes | -0.083 |
ants | -0.082 |
ivating | -0.082 |
od | -0.081 |
Token | " |
Token ID | 366 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
kiss | +0.017 |
welcome | +0.016 |
helper | +0.015 |
payoff | +0.015 |
bless | +0.015 |
Neg logit contributions | |
ts | -0.013 |
opes | -0.013 |
ants | -0.013 |
ivating | -0.013 |
od | -0.012 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
tered | +0.057 |
like | +0.057 |
ivating | +0.056 |
ants | +0.056 |
opes | +0.055 |
Neg logit contributions | |
luck | -0.040 |
welcome | -0.039 |
kiss | -0.038 |
helper | -0.038 |
prayer | -0.037 |
Token | my |
Token ID | 1820 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
guard | +0.201 |
distance | +0.199 |
payoff | +0.193 |
kiss | +0.190 |
masse | +0.188 |
Neg logit contributions | |
od | -0.237 |
ants | -0.233 |
opes | -0.232 |
ptions | -0.219 |
rave | -0.214 |
Token | , |
Token ID | 11 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
distance | +0.070 |
masse | +0.060 |
kiss | +0.060 |
guard | +0.059 |
payoff | +0.058 |
Neg logit contributions | |
od | -0.097 |
assed | -0.095 |
rave | -0.092 |
scored | -0.092 |
opes | -0.091 |
Token | what |
Token ID | 644 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
kiss | +0.050 |
bye | +0.047 |
distance | +0.047 |
payoff | +0.046 |
eye | +0.045 |
Neg logit contributions | |
ts | -0.060 |
nam | -0.060 |
od | -0.059 |
Whoever | -0.057 |
viol | -0.057 |
Token | is |
Token ID | 318 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
payoff | +0.017 |
kiss | +0.017 |
distance | +0.016 |
helper | +0.015 |
bye | +0.015 |
Neg logit contributions | |
od | -0.020 |
ts | -0.019 |
like | -0.019 |
opes | -0.019 |
ggies | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
kiss | +0.073 |
welcome | +0.069 |
luck | +0.066 |
helper | +0.065 |
? | +0.065 |
Neg logit contributions | |
opes | -0.117 |
ants | -0.116 |
ts | -0.115 |
od | -0.112 |
ivating | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ts | +0.063 |
opes | +0.063 |
ants | +0.062 |
ivating | +0.061 |
od | +0.060 |
Neg logit contributions | |
kiss | -0.028 |
welcome | -0.025 |
helper | -0.023 |
payoff | -0.022 |
bless | -0.022 |
Token | Jessie |
Token ID | 43425 |
Feature activation | -6.17e-03 |
Pos logit contributions | |
kiss | +0.021 |
welcome | +0.019 |
luck | +0.019 |
bless | +0.019 |
helper | +0.019 |
Neg logit contributions | |
opes | -0.018 |
ants | -0.017 |
ivating | -0.017 |
ts | -0.017 |
tered | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
opes | +0.009 |
ts | +0.009 |
ants | +0.009 |
od | +0.009 |
like | +0.009 |
Neg logit contributions | |
kiss | -0.009 |
welcome | -0.009 |
payoff | -0.008 |
luck | -0.008 |
bye | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +7.13e-03 |
Pos logit contributions | |
kiss | +0.014 |
welcome | +0.011 |
helper | +0.010 |
payoff | +0.009 |
bless | +0.009 |
Neg logit contributions | |
ts | -0.061 |
opes | -0.061 |
ants | -0.061 |
ivating | -0.060 |
od | -0.060 |
Token | " |
Token ID | 366 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
kiss | +0.011 |
welcome | +0.010 |
, | +0.009 |
girl | +0.009 |
prayer | +0.009 |
Neg logit contributions | |
ts | -0.012 |
opes | -0.011 |
ants | -0.011 |
ivating | -0.011 |
targets | -0.011 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ivating | +0.065 |
ants | +0.065 |
opes | +0.065 |
like | +0.065 |
od | +0.064 |
Neg logit contributions | |
kiss | -0.039 |
welcome | -0.036 |
luck | -0.034 |
helper | -0.034 |
promise | -0.033 |
Token | my |
Token ID | 1820 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
guard | +0.186 |
payoff | +0.183 |
distance | +0.181 |
kiss | +0.177 |
service | +0.176 |
Neg logit contributions | |
opes | -0.259 |
ants | -0.258 |
od | -0.258 |
ptions | -0.238 |
bles | -0.231 |
Token | , |
Token ID | 11 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
distance | +0.067 |
guard | +0.058 |
payoff | +0.056 |
kiss | +0.054 |
service | +0.051 |
Neg logit contributions | |
od | -0.106 |
opes | -0.100 |
ants | -0.099 |
rave | -0.097 |
assed | -0.097 |
Token | I |
Token ID | 314 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
kiss | +0.049 |
payoff | +0.043 |
welcome | +0.043 |
bye | +0.042 |
luck | +0.042 |
Neg logit contributions | |
ts | -0.076 |
od | -0.074 |
ants | -0.074 |
opes | -0.074 |
ivating | -0.073 |
Token | want |
Token ID | 765 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
payoff | +0.101 |
luck | +0.097 |
kiss | +0.096 |
bye | +0.095 |
service | +0.095 |
Neg logit contributions | |
od | -0.090 |
tant | -0.088 |
assed | -0.088 |
like | -0.086 |
Whoever | -0.086 |
Token | to |
Token ID | 284 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
kiss | +0.043 |
welcome | +0.040 |
eye | +0.038 |
promise | +0.038 |
helper | +0.038 |
Neg logit contributions | |
opes | -0.047 |
ts | -0.047 |
ants | -0.046 |
like | -0.045 |
ivating | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
kiss | +0.006 |
welcome | +0.005 |
, | +0.005 |
? | +0.005 |
ma | +0.005 |
Neg logit contributions | |
opes | -0.019 |
ts | -0.019 |
ants | -0.018 |
ivating | -0.018 |
amus | -0.018 |
Token | L |
Token ID | 43 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
kiss | +0.021 |
welcome | +0.019 |
girl | +0.018 |
, | +0.017 |
bye | +0.017 |
Neg logit contributions | |
opes | -0.036 |
ts | -0.036 |
ants | -0.035 |
od | -0.035 |
targets | -0.034 |
Token | ily |
Token ID | 813 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
opes | +0.022 |
ts | +0.021 |
ants | +0.021 |
nam | +0.021 |
ivating | +0.021 |
Neg logit contributions | |
kiss | -0.025 |
welcome | -0.025 |
ma | -0.024 |
? | -0.024 |
eye | -0.024 |
Token | : |
Token ID | 25 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
kiss | +0.012 |
welcome | +0.011 |
helper | +0.010 |
payoff | +0.010 |
bless | +0.010 |
Neg logit contributions | |
ts | -0.019 |
opes | -0.019 |
ants | -0.019 |
ivating | -0.019 |
od | -0.019 |
Token | " |
Token ID | 366 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
ts | +0.005 |
opes | +0.005 |
ants | +0.005 |
ivating | +0.005 |
tered | +0.005 |
Neg logit contributions | |
kiss | -0.006 |
welcome | -0.006 |
girl | -0.005 |
helper | -0.005 |
thanks | -0.005 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ts | +0.060 |
opes | +0.060 |
ants | +0.059 |
ivating | +0.058 |
od | +0.057 |
Neg logit contributions | |
kiss | -0.040 |
welcome | -0.035 |
helper | -0.033 |
bless | -0.033 |
girl | -0.033 |
Token | my |
Token ID | 1820 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
guard | +0.198 |
kiss | +0.189 |
payoff | +0.188 |
service | +0.183 |
distance | +0.182 |
Neg logit contributions | |
od | -0.254 |
opes | -0.242 |
ants | -0.235 |
ptions | -0.231 |
amus | -0.219 |
Token | , |
Token ID | 11 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
guard | +0.067 |
distance | +0.066 |
payoff | +0.064 |
cleaner | +0.063 |
kiss | +0.061 |
Neg logit contributions | |
od | -0.099 |
opes | -0.093 |
assed | -0.090 |
ants | -0.089 |
ts | -0.086 |
Token | look |
Token ID | 804 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
kiss | +0.055 |
payoff | +0.050 |
bye | +0.047 |
welcome | +0.047 |
luck | +0.047 |
Neg logit contributions | |
ts | -0.073 |
od | -0.071 |
opes | -0.070 |
nam | -0.069 |
ants | -0.069 |
Token | at |
Token ID | 379 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
kiss | +0.075 |
welcome | +0.074 |
, | +0.072 |
? | +0.071 |
girl | +0.068 |
Neg logit contributions | |
opes | -0.116 |
ts | -0.115 |
tered | -0.114 |
ants | -0.111 |
ggies | -0.110 |
Token | the |
Token ID | 262 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
kiss | +0.027 |
welcome | +0.025 |
? | +0.025 |
thanks | +0.024 |
, | +0.024 |
Neg logit contributions | |
tered | -0.050 |
opes | -0.050 |
ants | -0.049 |
issors | -0.049 |
ts | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
kiss | +0.006 |
welcome | +0.006 |
, | +0.005 |
ma | +0.005 |
girl | +0.005 |
Neg logit contributions | |
opes | -0.020 |
ts | -0.020 |
ants | -0.019 |
ivating | -0.019 |
amus | -0.019 |
Token | L |
Token ID | 43 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
kiss | +0.020 |
welcome | +0.018 |
girl | +0.018 |
, | +0.016 |
bye | +0.016 |
Neg logit contributions | |
opes | -0.038 |
ts | -0.038 |
ants | -0.037 |
od | -0.036 |
targets | -0.036 |
Token | ily |
Token ID | 813 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
opes | +0.020 |
ts | +0.019 |
ants | +0.019 |
nam | +0.019 |
ivating | +0.019 |
Neg logit contributions | |
kiss | -0.023 |
welcome | -0.022 |
? | -0.021 |
ma | -0.021 |
eye | -0.021 |
Token | : |
Token ID | 25 |
Feature activation | -2.43e-03 |
Pos logit contributions | |
kiss | +0.013 |
welcome | +0.012 |
helper | +0.011 |
payoff | +0.011 |
bless | +0.011 |
Neg logit contributions | |
ts | -0.022 |
opes | -0.022 |
ants | -0.021 |
ivating | -0.021 |
od | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
ts | +0.003 |
opes | +0.003 |
ants | +0.003 |
ivating | +0.003 |
od | +0.003 |
Neg logit contributions | |
kiss | -0.004 |
welcome | -0.004 |
helper | -0.004 |
bless | -0.003 |
girl | -0.003 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ts | +0.052 |
opes | +0.052 |
ants | +0.051 |
ivating | +0.049 |
od | +0.049 |
Neg logit contributions | |
kiss | -0.047 |
welcome | -0.043 |
girl | -0.040 |
payoff | -0.040 |
helper | -0.040 |
Token | my |
Token ID | 1820 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
guard | +0.198 |
kiss | +0.189 |
payoff | +0.187 |
distance | +0.182 |
service | +0.181 |
Neg logit contributions | |
od | -0.255 |
opes | -0.247 |
ants | -0.238 |
ptions | -0.232 |
amus | -0.219 |
Token | , |
Token ID | 11 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
guard | +0.068 |
distance | +0.067 |
payoff | +0.064 |
cleaner | +0.063 |
kiss | +0.062 |
Neg logit contributions | |
od | -0.098 |
opes | -0.094 |
ants | -0.090 |
assed | -0.090 |
ts | -0.087 |
Token | look |
Token ID | 804 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
kiss | +0.052 |
payoff | +0.046 |
welcome | +0.045 |
helper | +0.044 |
luck | +0.044 |
Neg logit contributions | |
ts | -0.074 |
od | -0.072 |
opes | -0.072 |
ants | -0.071 |
ivating | -0.071 |
Token | ! |
Token ID | 0 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
kiss | +0.073 |
welcome | +0.073 |
, | +0.071 |
? | +0.070 |
girl | +0.066 |
Neg logit contributions | |
opes | -0.115 |
ts | -0.114 |
tered | -0.113 |
ants | -0.110 |
ggies | -0.110 |
Token | A |
Token ID | 317 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
kiss | +0.037 |
welcome | +0.034 |
helper | +0.032 |
bless | +0.032 |
payoff | +0.031 |
Neg logit contributions | |
ts | -0.045 |
opes | -0.045 |
ants | -0.044 |
ivating | -0.043 |
tered | -0.042 |
Token | his |
Token ID | 465 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
opes | +0.024 |
ivating | +0.023 |
ants | +0.023 |
ts | +0.023 |
od | +0.022 |
Neg logit contributions | |
kiss | -0.018 |
welcome | -0.017 |
, | -0.016 |
girl | -0.016 |
luck | -0.016 |
Token | feet |
Token ID | 3625 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
opes | +0.028 |
ts | +0.027 |
ants | +0.026 |
amus | +0.026 |
like | +0.026 |
Neg logit contributions | |
kiss | -0.022 |
welcome | -0.021 |
bless | -0.020 |
payoff | -0.020 |
helper | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
kiss | +0.032 |
welcome | +0.028 |
helper | +0.025 |
payoff | +0.025 |
luck | +0.025 |
Neg logit contributions | |
ts | -0.072 |
opes | -0.072 |
ants | -0.071 |
ivating | -0.071 |
od | -0.070 |
Token | threw |
Token ID | 9617 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
ts | +0.021 |
opes | +0.020 |
tered | +0.019 |
ivating | +0.019 |
nam | +0.019 |
Neg logit contributions | |
kiss | -0.021 |
welcome | -0.020 |
helper | -0.019 |
bless | -0.019 |
bye | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
opes | +0.046 |
ants | +0.045 |
ts | +0.045 |
od | +0.045 |
ivating | +0.045 |
Neg logit contributions | |
kiss | -0.041 |
welcome | -0.038 |
luck | -0.036 |
thanks | -0.036 |
payoff | -0.035 |
Token | tant |
Token ID | 24246 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ts | +0.015 |
opes | +0.015 |
ants | +0.015 |
ivating | +0.015 |
like | +0.014 |
Neg logit contributions | |
kiss | -0.016 |
welcome | -0.015 |
payoff | -0.015 |
helper | -0.015 |
bless | -0.015 |
Token | rum |
Token ID | 6582 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
ivating | +0.232 |
ination | +0.221 |
nam | +0.220 |
opes | +0.219 |
Whoever | +0.216 |
Neg logit contributions | |
kiss | -0.258 |
ma | -0.255 |
welcome | -0.243 |
bye | -0.242 |
luck | -0.242 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
opes | +0.080 |
ts | +0.080 |
ants | +0.079 |
tered | +0.078 |
ivating | +0.077 |
Neg logit contributions | |
kiss | -0.029 |
welcome | -0.025 |
helper | -0.023 |
payoff | -0.023 |
bless | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
ts | +0.025 |
opes | +0.024 |
ants | +0.023 |
ivating | +0.023 |
ptions | +0.023 |
Neg logit contributions | |
kiss | -0.010 |
welcome | -0.009 |
, | -0.009 |
? | -0.008 |
thanks | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
kiss | +0.002 |
welcome | +0.001 |
? | +0.001 |
ma | +0.001 |
thanks | +0.001 |
Neg logit contributions | |
opes | -0.004 |
ts | -0.004 |
ivating | -0.003 |
ants | -0.003 |
od | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | +8.88e-03 |
Pos logit contributions | |
kiss | +0.016 |
welcome | +0.014 |
luck | +0.014 |
helper | +0.014 |
bless | +0.013 |
Neg logit contributions | |
ts | -0.024 |
ants | -0.024 |
opes | -0.024 |
ivating | -0.024 |
tered | -0.024 |
Token | them |
Token ID | 606 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
ts | +0.052 |
opes | +0.052 |
ants | +0.051 |
ivating | +0.050 |
od | +0.049 |
Neg logit contributions | |
kiss | -0.047 |
welcome | -0.043 |
helper | -0.041 |
payoff | -0.041 |
bless | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +8.45e-04 |
Pos logit contributions | |
ts | +0.053 |
opes | +0.051 |
ants | +0.050 |
tered | +0.050 |
like | +0.050 |
Neg logit contributions | |
kiss | -0.037 |
payoff | -0.034 |
welcome | -0.033 |
wave | -0.033 |
girl | -0.033 |
Token | never |
Token ID | 1239 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
kiss | +0.001 |
welcome | +0.001 |
luck | +0.001 |
eye | +0.001 |
bye | +0.001 |
Neg logit contributions | |
ts | -0.001 |
opes | -0.001 |
nam | -0.001 |
tered | -0.001 |
ants | -0.001 |
Token | threw |
Token ID | 9617 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
ma | +0.047 |
kiss | +0.043 |
ama | +0.043 |
helper | +0.042 |
handy | +0.042 |
Neg logit contributions | |
ts | -0.054 |
nam | -0.053 |
tered | -0.052 |
od | -0.051 |
scored | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | -8.65e-03 |
Pos logit contributions | |
opes | +0.043 |
ts | +0.043 |
ants | +0.042 |
ivating | +0.042 |
od | +0.040 |
Neg logit contributions | |
kiss | -0.064 |
welcome | -0.060 |
helper | -0.058 |
luck | -0.058 |
payoff | -0.057 |
Token | tant |
Token ID | 24246 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
tant | +0.013 |
ts | +0.013 |
like | +0.012 |
ants | +0.012 |
ivating | +0.012 |
Neg logit contributions | |
kiss | -0.012 |
welcome | -0.012 |
payoff | -0.011 |
bye | -0.011 |
helper | -0.011 |
Token | rum |
Token ID | 6582 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
ivating | +0.208 |
ts | +0.197 |
opes | +0.197 |
ination | +0.196 |
Whoever | +0.195 |
Neg logit contributions | |
kiss | -0.274 |
ma | -0.266 |
welcome | -0.256 |
bye | -0.256 |
luck | -0.255 |
Token | again |
Token ID | 757 |
Feature activation | +9.33e-03 |
Pos logit contributions | |
opes | +0.069 |
tered | +0.069 |
ants | +0.068 |
ts | +0.068 |
od | +0.068 |
Neg logit contributions | |
kiss | -0.032 |
welcome | -0.028 |
payoff | -0.027 |
helper | -0.027 |
wave | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
kiss | +0.011 |
bless | +0.010 |
bye | +0.010 |
payoff | +0.010 |
welcome | +0.010 |
Neg logit contributions | |
opes | -0.016 |
ts | -0.016 |
od | -0.016 |
tered | -0.016 |
ants | -0.015 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
ts | +0.019 |
opes | +0.018 |
ants | +0.018 |
ivating | +0.018 |
od | +0.017 |
Neg logit contributions | |
kiss | -0.013 |
welcome | -0.012 |
thanks | -0.011 |
girl | -0.011 |
helper | -0.011 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
kiss | +0.014 |
welcome | +0.013 |
thanks | +0.011 |
payoff | +0.011 |
helper | +0.011 |
Neg logit contributions | |
opes | -0.025 |
ts | -0.024 |
ants | -0.024 |
ivating | -0.024 |
tered | -0.023 |
Token | of |
Token ID | 286 |
Feature activation | +6.34e-03 |
Pos logit contributions | |
kiss | +0.053 |
welcome | +0.048 |
bless | +0.048 |
payoff | +0.047 |
helper | +0.047 |
Neg logit contributions | |
od | -0.066 |
like | -0.065 |
ants | -0.065 |
ts | -0.065 |
tered | -0.064 |
Token | a |
Token ID | 257 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
kiss | +0.009 |
welcome | +0.008 |
helper | +0.008 |
bless | +0.008 |
payoff | +0.008 |
Neg logit contributions | |
ts | -0.010 |
opes | -0.010 |
ants | -0.010 |
ivating | -0.010 |
od | -0.009 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
tant | +0.024 |
like | +0.024 |
viol | +0.024 |
ggies | +0.024 |
ts | +0.024 |
Neg logit contributions | |
kiss | -0.023 |
shines | -0.022 |
ma | -0.022 |
bless | -0.022 |
thanks | -0.021 |
Token | life |
Token ID | 1204 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
tant | +0.018 |
ggies | +0.018 |
tered | +0.018 |
viol | +0.017 |
ts | +0.017 |
Neg logit contributions | |
bless | -0.011 |
ma | -0.011 |
shines | -0.011 |
use | -0.011 |
Dear | -0.011 |
Token | for |
Token ID | 329 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
kiss | +0.057 |
bless | +0.051 |
eye | +0.051 |
ara | +0.050 |
welcome | +0.049 |
Neg logit contributions | |
tered | -0.076 |
ts | -0.076 |
od | -0.075 |
like | -0.074 |
ivating | -0.072 |
Token | Fro |
Token ID | 9734 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
opes | +0.049 |
ts | +0.048 |
ants | +0.048 |
ivating | +0.048 |
od | +0.047 |
Neg logit contributions | |
kiss | -0.047 |
welcome | -0.044 |
helper | -0.041 |
luck | -0.041 |
bless | -0.041 |
Token | ggy |
Token ID | 19970 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
nam | +0.203 |
opes | +0.198 |
ts | +0.192 |
ivating | +0.191 |
ants | +0.191 |
Neg logit contributions | |
kiss | -0.286 |
welcome | -0.266 |
promise | -0.262 |
? | -0.257 |
wave | -0.254 |
Token | . |
Token ID | 13 |
Feature activation | -3.27e-03 |
Pos logit contributions | |
opes | +0.151 |
od | +0.151 |
ts | +0.151 |
tered | +0.149 |
ants | +0.149 |
Neg logit contributions | |
kiss | -0.069 |
welcome | -0.062 |
payoff | -0.058 |
bless | -0.057 |
shines | -0.056 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +9.42e-03 |
Pos logit contributions | |
ants | +0.005 |
opes | +0.005 |
ivating | +0.005 |
od | +0.005 |
like | +0.005 |
Neg logit contributions | |
kiss | -0.005 |
luck | -0.004 |
welcome | -0.004 |
helper | -0.004 |
payoff | -0.004 |
Token | Once |
Token ID | 7454 |
Feature activation | -7.97e-04 |
Pos logit contributions | |
kiss | +0.010 |
welcome | +0.009 |
helper | +0.009 |
bless | +0.008 |
payoff | +0.008 |
Neg logit contributions | |
ts | -0.018 |
opes | -0.018 |
ivating | -0.018 |
ants | -0.018 |
od | -0.018 |
Token | there |
Token ID | 612 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
opes | +0.001 |
ts | +0.001 |
ivating | +0.001 |
ants | +0.001 |
tered | +0.001 |
Neg logit contributions | |
kiss | -0.001 |
welcome | -0.001 |
ma | -0.001 |
, | -0.001 |
girl | -0.001 |
Token | surface |
Token ID | 4417 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
kiss | +0.012 |
bless | +0.011 |
welcome | +0.011 |
ma | +0.011 |
helper | +0.011 |
Neg logit contributions | |
opes | -0.016 |
targets | -0.016 |
ts | -0.015 |
ivating | -0.015 |
like | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -4.94e-03 |
Pos logit contributions | |
kiss | +0.028 |
bless | +0.026 |
shines | +0.025 |
use | +0.025 |
payoff | +0.025 |
Neg logit contributions | |
od | -0.038 |
like | -0.037 |
ants | -0.037 |
ts | -0.037 |
tered | -0.036 |
Token | showed |
Token ID | 3751 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ts | +0.009 |
opes | +0.008 |
tered | +0.008 |
ants | +0.008 |
like | +0.008 |
Neg logit contributions | |
kiss | -0.006 |
welcome | -0.006 |
bless | -0.006 |
luck | -0.005 |
helper | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
opes | +0.021 |
ivating | +0.020 |
ts | +0.020 |
ants | +0.020 |
ptions | +0.019 |
Neg logit contributions | |
kiss | -0.018 |
welcome | -0.017 |
luck | -0.016 |
thanks | -0.016 |
wave | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
opes | +0.048 |
ts | +0.048 |
ivating | +0.047 |
ants | +0.047 |
tered | +0.045 |
Neg logit contributions | |
kiss | -0.025 |
welcome | -0.022 |
luck | -0.022 |
thanks | -0.021 |
wave | -0.020 |
Token | Fro |
Token ID | 9734 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ants | +0.022 |
opes | +0.022 |
ivating | +0.022 |
ptions | +0.022 |
ts | +0.021 |
Neg logit contributions | |
kiss | -0.016 |
welcome | -0.016 |
wave | -0.015 |
thanks | -0.015 |
return | -0.014 |
Token | ggy |
Token ID | 19970 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
nam | +0.235 |
opes | +0.221 |
ivating | +0.218 |
targets | +0.215 |
ts | +0.215 |
Neg logit contributions | |
kiss | -0.264 |
promise | -0.252 |
? | -0.245 |
welcome | -0.245 |
, | -0.240 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e-03 |
Pos logit contributions | |
opes | +0.179 |
ts | +0.178 |
ivating | +0.176 |
ants | +0.175 |
ination | +0.171 |
Neg logit contributions | |
kiss | -0.038 |
welcome | -0.029 |
thanks | -0.025 |
helper | -0.024 |
luck | -0.023 |
Token | " |
Token ID | 366 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
ts | +0.003 |
opes | +0.003 |
ptions | +0.003 |
ivating | +0.003 |
ants | +0.003 |
Neg logit contributions | |
kiss | -0.001 |
welcome | -0.001 |
thanks | -0.001 |
, | -0.001 |
wave | -0.001 |
Token | Look |
Token ID | 8567 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
ts | +0.081 |
opes | +0.080 |
ants | +0.079 |
ivating | +0.077 |
od | +0.075 |
Neg logit contributions | |
kiss | -0.078 |
welcome | -0.072 |
payoff | -0.069 |
bless | -0.068 |
thanks | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
kiss | +0.018 |
welcome | +0.015 |
luck | +0.012 |
thanks | +0.011 |
helper | +0.011 |
Neg logit contributions | |
opes | -0.098 |
ts | -0.097 |
ivating | -0.097 |
ants | -0.096 |
tered | -0.095 |
Token | temper |
Token ID | 4124 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
ivating | +0.131 |
ants | +0.129 |
opes | +0.129 |
ts | +0.128 |
tered | +0.124 |
Neg logit contributions | |
kiss | -0.093 |
welcome | -0.083 |
luck | -0.081 |
eye | -0.081 |
helper | -0.080 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
opes | +0.060 |
ts | +0.060 |
ants | +0.058 |
ivating | +0.057 |
tered | +0.057 |
Neg logit contributions | |
kiss | -0.032 |
welcome | -0.029 |
payoff | -0.027 |
helper | -0.027 |
bless | -0.027 |
Token | often |
Token ID | 1690 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
ts | +0.024 |
opes | +0.024 |
ants | +0.023 |
ivating | +0.023 |
tered | +0.023 |
Neg logit contributions | |
kiss | -0.020 |
welcome | -0.019 |
bless | -0.018 |
payoff | -0.018 |
helper | -0.018 |
Token | threw |
Token ID | 9617 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
kiss | +0.054 |
welcome | +0.053 |
payoff | +0.050 |
helper | +0.049 |
eye | +0.049 |
Neg logit contributions | |
ts | -0.059 |
tered | -0.055 |
opes | -0.054 |
od | -0.053 |
scored | -0.051 |
Token | temper |
Token ID | 4124 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
ants | +0.046 |
ivating | +0.045 |
opes | +0.045 |
ts | +0.044 |
od | +0.043 |
Neg logit contributions | |
kiss | -0.037 |
luck | -0.035 |
welcome | -0.035 |
surprise | -0.034 |
girl | -0.033 |
Token | tant |
Token ID | 24246 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
ivating | +0.057 |
opes | +0.056 |
ts | +0.056 |
ants | +0.055 |
amus | +0.054 |
Neg logit contributions | |
kiss | -0.054 |
welcome | -0.048 |
luck | -0.048 |
thanks | -0.046 |
, | -0.046 |
Token | rums |
Token ID | 45241 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
ivating | +0.208 |
Whoever | +0.199 |
IT | +0.196 |
tered | +0.191 |
amus | +0.191 |
Neg logit contributions | |
ma | -0.251 |
kiss | -0.236 |
luck | -0.236 |
pa | -0.233 |
bye | -0.231 |
Token | . |
Token ID | 13 |
Feature activation | +3.69e-03 |
Pos logit contributions | |
ts | +0.022 |
opes | +0.022 |
ants | +0.021 |
ivating | +0.021 |
od | +0.021 |
Neg logit contributions | |
kiss | -0.011 |
welcome | -0.009 |
helper | -0.009 |
luck | -0.009 |
bless | -0.009 |
Token | One |
Token ID | 1881 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
kiss | +0.005 |
welcome | +0.005 |
thanks | +0.005 |
payoff | +0.004 |
helper | +0.004 |
Neg logit contributions | |
ts | -0.006 |
opes | -0.006 |
ants | -0.006 |
ivating | -0.006 |
od | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
kiss | +0.060 |
bless | +0.055 |
welcome | +0.055 |
payoff | +0.054 |
luck | +0.053 |
Neg logit contributions | |
like | -0.095 |
od | -0.095 |
tered | -0.095 |
ts | -0.094 |
ants | -0.093 |
Token | , |
Token ID | 11 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
kiss | +0.046 |
promise | +0.036 |
bless | +0.036 |
eye | +0.035 |
welcome | +0.035 |
Neg logit contributions | |
ts | -0.119 |
tered | -0.119 |
ants | -0.115 |
opes | -0.115 |
od | -0.114 |
Token | it |
Token ID | 340 |
Feature activation | -7.93e-03 |
Pos logit contributions | |
ts | +0.006 |
opes | +0.006 |
ants | +0.006 |
ivating | +0.006 |
od | +0.006 |
Neg logit contributions | |
kiss | -0.005 |
welcome | -0.004 |
helper | -0.004 |
payoff | -0.004 |
bless | -0.004 |
Token | makes |
Token ID | 1838 |
Feature activation | -2.14e-03 |
Pos logit contributions | |
ts | +0.014 |
opes | +0.014 |
ivating | +0.014 |
od | +0.014 |
ants | +0.014 |
Neg logit contributions | |
kiss | -0.009 |
welcome | -0.009 |
payoff | -0.008 |
eye | -0.008 |
bye | -0.008 |
Token | me |
Token ID | 502 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ving | +0.004 |
ivating | +0.004 |
opes | +0.004 |
ved | +0.004 |
ants | +0.004 |
Neg logit contributions | |
kiss | -0.002 |
welcome | -0.002 |
thanks | -0.002 |
surprise | -0.002 |
luck | -0.002 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
kiss | +0.015 |
welcome | +0.014 |
helper | +0.013 |
payoff | +0.013 |
bless | +0.013 |
Neg logit contributions | |
ts | -0.019 |
opes | -0.019 |
ants | -0.019 |
ivating | -0.019 |
od | -0.018 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
opes | +0.067 |
ts | +0.067 |
od | +0.066 |
ants | +0.065 |
ivating | +0.065 |
Neg logit contributions | |
kiss | -0.040 |
welcome | -0.035 |
eye | -0.034 |
bless | -0.034 |
payoff | -0.033 |
Token | Fro |
Token ID | 9734 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
opes | +0.084 |
ts | +0.083 |
ants | +0.083 |
ivating | +0.081 |
od | +0.080 |
Neg logit contributions | |
kiss | -0.074 |
welcome | -0.068 |
helper | -0.066 |
payoff | -0.065 |
bless | -0.065 |
Token | ggy |
Token ID | 19970 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
nam | +0.226 |
targets | +0.219 |
ptions | +0.218 |
ts | +0.217 |
opes | +0.216 |
Neg logit contributions | |
kiss | -0.255 |
promise | -0.235 |
welcome | -0.235 |
, | -0.233 |
? | -0.232 |
Token | replied |
Token ID | 8712 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
opes | +0.138 |
ts | +0.138 |
ants | +0.136 |
ivating | +0.136 |
like | +0.132 |
Neg logit contributions | |
kiss | -0.071 |
welcome | -0.061 |
helper | -0.057 |
thanks | -0.057 |
payoff | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ts | +0.056 |
opes | +0.056 |
ants | +0.055 |
ivating | +0.055 |
od | +0.054 |
Neg logit contributions | |
kiss | -0.007 |
welcome | -0.004 |
helper | -0.003 |
payoff | -0.003 |
bless | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
ts | +0.025 |
opes | +0.025 |
targets | +0.025 |
ants | +0.024 |
ivating | +0.024 |
Neg logit contributions | |
kiss | -0.022 |
welcome | -0.020 |
, | -0.019 |
wave | -0.019 |
thanks | -0.019 |
Token | I |
Token ID | 40 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
ts | +0.118 |
opes | +0.117 |
ants | +0.115 |
ivating | +0.113 |
od | +0.111 |
Neg logit contributions | |
kiss | -0.066 |
welcome | -0.059 |
payoff | -0.055 |
bye | -0.055 |
helper | -0.055 |
Token | so |
Token ID | 523 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
opes | +0.003 |
ts | +0.003 |
ants | +0.003 |
ivating | +0.003 |
tered | +0.003 |
Neg logit contributions | |
kiss | -0.003 |
welcome | -0.002 |
helper | -0.002 |
luck | -0.002 |
thanks | -0.002 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
ts | +0.032 |
od | +0.031 |
ivating | +0.031 |
ants | +0.031 |
like | +0.031 |
Neg logit contributions | |
kiss | -0.032 |
payoff | -0.030 |
welcome | -0.029 |
helper | -0.029 |
bless | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
opes | +0.024 |
od | +0.024 |
like | +0.024 |
ts | +0.023 |
ants | +0.023 |
Neg logit contributions | |
kiss | -0.019 |
welcome | -0.017 |
bless | -0.017 |
promise | -0.016 |
payoff | -0.016 |
Token | start |
Token ID | 923 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
opes | +0.020 |
ts | +0.020 |
ants | +0.020 |
ivating | +0.020 |
od | +0.019 |
Neg logit contributions | |
kiss | -0.013 |
welcome | -0.011 |
helper | -0.011 |
bless | -0.011 |
payoff | -0.011 |
Token | do |
Token ID | 466 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
kiss | +0.033 |
, | +0.032 |
surprise | +0.030 |
? | +0.030 |
thanks | +0.029 |
Neg logit contributions | |
ivating | -0.045 |
tered | -0.045 |
opes | -0.045 |
ts | -0.045 |
ants | -0.044 |
Token | od |
Token ID | 375 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ivating | +0.066 |
ants | +0.066 |
opes | +0.066 |
amus | +0.065 |
issors | +0.062 |
Neg logit contributions | |
kiss | -0.040 |
, | -0.037 |
luck | -0.037 |
? | -0.035 |
surprise | -0.035 |
Token | ling |
Token ID | 1359 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
ivating | +0.249 |
opes | +0.243 |
ination | +0.243 |
tered | +0.236 |
nam | +0.235 |
Neg logit contributions | |
kiss | -0.213 |
luck | -0.210 |
ma | -0.204 |
thanks | -0.199 |
? | -0.193 |
Token | with |
Token ID | 351 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
ants | +0.211 |
opes | +0.207 |
ivating | +0.206 |
ptions | +0.206 |
issors | +0.204 |
Neg logit contributions | |
kiss | -0.079 |
, | -0.073 |
thanks | -0.066 |
luck | -0.066 |
? | -0.064 |
Token | it |
Token ID | 340 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
opes | +0.046 |
ts | +0.045 |
ants | +0.045 |
ivating | +0.045 |
tered | +0.044 |
Neg logit contributions | |
kiss | -0.038 |
welcome | -0.035 |
thanks | -0.033 |
luck | -0.033 |
surprise | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +8.90e-03 |
Pos logit contributions | |
opes | +0.063 |
ts | +0.063 |
ivating | +0.062 |
od | +0.062 |
tered | +0.062 |
Neg logit contributions | |
kiss | -0.022 |
welcome | -0.019 |
bless | -0.018 |
payoff | -0.018 |
helper | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
kiss | +0.012 |
welcome | +0.010 |
helper | +0.010 |
luck | +0.010 |
payoff | +0.010 |
Neg logit contributions | |
opes | -0.015 |
ants | -0.015 |
ts | -0.015 |
ivating | -0.015 |
like | -0.014 |
Token | more |
Token ID | 517 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ts | +0.030 |
opes | +0.027 |
od | +0.027 |
targets | +0.026 |
tered | +0.026 |
Neg logit contributions | |
kiss | -0.031 |
bye | -0.028 |
shines | -0.028 |
helper | -0.028 |
welcome | -0.027 |
Token | of |
Token ID | 286 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
kiss | +0.024 |
bless | +0.023 |
bye | +0.022 |
payoff | +0.022 |
helper | +0.022 |
Neg logit contributions | |
od | -0.025 |
ts | -0.025 |
like | -0.025 |
webs | -0.025 |
targets | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -6.34e-03 |
Pos logit contributions | |
ts | +0.026 |
opes | +0.026 |
ants | +0.025 |
ivating | +0.025 |
od | +0.025 |
Neg logit contributions | |
kiss | -0.027 |
welcome | -0.025 |
helper | -0.024 |
bless | -0.024 |
payoff | -0.024 |
Token | hairy |
Token ID | 43873 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
opes | +0.011 |
ts | +0.011 |
ivating | +0.011 |
like | +0.011 |
targets | +0.011 |
Neg logit contributions | |
kiss | -0.008 |
bless | -0.007 |
welcome | -0.007 |
helper | -0.007 |
payoff | -0.006 |
Token | cater |
Token ID | 20825 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
opes | +0.060 |
webs | +0.056 |
targets | +0.056 |
od | +0.055 |
viol | +0.055 |
Neg logit contributions | |
kiss | -0.064 |
bless | -0.060 |
welcome | -0.057 |
guard | -0.057 |
payoff | -0.056 |
Token | pill |
Token ID | 27215 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ivating | +0.121 |
od | +0.119 |
like | +0.117 |
ants | +0.117 |
opes | +0.116 |
Neg logit contributions | |
kiss | -0.171 |
welcome | -0.157 |
prayer | -0.156 |
luck | -0.156 |
payoff | -0.156 |
Token | ars |
Token ID | 945 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
opes | +0.204 |
ants | +0.198 |
ts | +0.196 |
ivating | +0.194 |
od | +0.187 |
Neg logit contributions | |
kiss | -0.252 |
welcome | -0.240 |
thanks | -0.224 |
bless | -0.224 |
wave | -0.223 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e-03 |
Pos logit contributions | |
od | +0.032 |
ants | +0.032 |
ivating | +0.032 |
like | +0.031 |
opes | +0.031 |
Neg logit contributions | |
kiss | -0.017 |
welcome | -0.014 |
helper | -0.014 |
payoff | -0.014 |
bless | -0.014 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
kiss | +0.002 |
luck | +0.002 |
wave | +0.002 |
helper | +0.002 |
payoff | +0.002 |
Neg logit contributions | |
od | -0.002 |
ants | -0.002 |
opes | -0.002 |
ivating | -0.002 |
like | -0.002 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.24e-03 |
Pos logit contributions | |
kiss | +0.012 |
welcome | +0.010 |
helper | +0.010 |
bless | +0.010 |
payoff | +0.010 |
Neg logit contributions | |
opes | -0.020 |
ts | -0.020 |
ivating | -0.020 |
ants | -0.020 |
od | -0.020 |
Token | there |
Token ID | 612 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
opes | +0.003 |
ts | +0.003 |
ivating | +0.003 |
ants | +0.003 |
tered | +0.003 |
Neg logit contributions | |
kiss | -0.003 |
welcome | -0.003 |
ma | -0.003 |
thanks | -0.003 |
helper | -0.003 |
Token | ily |
Token ID | 813 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
ts | +0.017 |
opes | +0.017 |
ivating | +0.016 |
ants | +0.016 |
tered | +0.016 |
Neg logit contributions | |
kiss | -0.015 |
welcome | -0.014 |
helper | -0.013 |
luck | -0.013 |
eye | -0.013 |
Token | liked |
Token ID | 8288 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
cleaner | +0.027 |
kiss | +0.026 |
wiser | +0.025 |
reward | +0.025 |
reminder | +0.025 |
Neg logit contributions | |
opes | -0.026 |
ts | -0.024 |
scored | -0.024 |
ils | -0.024 |
targets | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
ts | +0.050 |
opes | +0.050 |
ants | +0.049 |
ivating | +0.049 |
tered | +0.048 |
Neg logit contributions | |
kiss | -0.030 |
welcome | -0.027 |
helper | -0.026 |
bless | -0.025 |
payoff | -0.025 |
Token | keep |
Token ID | 1394 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
ts | +0.020 |
opes | +0.019 |
ants | +0.019 |
od | +0.019 |
ivating | +0.019 |
Neg logit contributions | |
kiss | -0.014 |
welcome | -0.013 |
payoff | -0.013 |
luck | -0.012 |
helper | -0.012 |
Token | cater |
Token ID | 20825 |
Feature activation | -9.43e-02 |
Pos logit contributions | |
kiss | +0.044 |
welcome | +0.041 |
helper | +0.039 |
thanks | +0.039 |
luck | +0.039 |
Neg logit contributions | |
ivating | -0.046 |
ants | -0.046 |
tered | -0.045 |
opes | -0.045 |
ts | -0.045 |
Token | pill |
Token ID | 27215 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
opes | +0.094 |
ts | +0.094 |
ants | +0.091 |
ivating | +0.090 |
od | +0.087 |
Neg logit contributions | |
kiss | -0.191 |
welcome | -0.180 |
helper | -0.174 |
bless | -0.173 |
luck | -0.172 |
Token | ars |
Token ID | 945 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
opes | +0.210 |
ants | +0.203 |
ts | +0.199 |
ivating | +0.198 |
ination | +0.191 |
Neg logit contributions | |
kiss | -0.250 |
welcome | -0.238 |
thanks | -0.220 |
wave | -0.219 |
bless | -0.219 |
Token | in |
Token ID | 287 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
opes | +0.024 |
ts | +0.024 |
ants | +0.023 |
ivating | +0.023 |
od | +0.023 |
Neg logit contributions | |
kiss | -0.016 |
welcome | -0.015 |
helper | -0.014 |
luck | -0.014 |
bless | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
opes | +0.050 |
ts | +0.050 |
ants | +0.049 |
ivating | +0.049 |
od | +0.048 |
Neg logit contributions | |
kiss | -0.041 |
welcome | -0.038 |
helper | -0.036 |
payoff | -0.036 |
bless | -0.036 |
Token | jar |
Token ID | 17379 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
ts | +0.041 |
opes | +0.039 |
ivating | +0.039 |
targets | +0.038 |
tant | +0.038 |
Neg logit contributions | |
kiss | -0.031 |
payoff | -0.028 |
bless | -0.028 |
bye | -0.028 |
welcome | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ts | +0.077 |
tered | +0.075 |
opes | +0.074 |
ivating | +0.074 |
od | +0.074 |
Neg logit contributions | |
kiss | -0.039 |
payoff | -0.037 |
welcome | -0.034 |
bless | -0.034 |
luck | -0.033 |
Token | ball |
Token ID | 2613 |
Feature activation | -1.23e-03 |
Pos logit contributions | |
kiss | +0.020 |
welcome | +0.018 |
helper | +0.017 |
payoff | +0.017 |
bless | +0.017 |
Neg logit contributions | |
ts | -0.035 |
opes | -0.034 |
ants | -0.034 |
ivating | -0.034 |
like | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
opes | +0.002 |
ts | +0.002 |
ants | +0.002 |
ivating | +0.002 |
ination | +0.002 |
Neg logit contributions | |
kiss | -0.001 |
welcome | -0.001 |
luck | -0.001 |
thanks | -0.001 |
, | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
ts | +0.020 |
opes | +0.018 |
tered | +0.018 |
targets | +0.017 |
ivating | +0.017 |
Neg logit contributions | |
kiss | -0.019 |
welcome | -0.018 |
helper | -0.018 |
luck | -0.018 |
payoff | -0.018 |
Token | dog |
Token ID | 3290 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
kiss | +0.026 |
welcome | +0.024 |
helper | +0.024 |
payoff | +0.024 |
bless | +0.023 |
Neg logit contributions | |
ts | -0.031 |
opes | -0.030 |
like | -0.029 |
ivating | -0.029 |
targets | -0.029 |
Token | fet |
Token ID | 11351 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ts | +0.067 |
opes | +0.067 |
ants | +0.066 |
ivating | +0.066 |
od | +0.065 |
Neg logit contributions | |
kiss | -0.032 |
welcome | -0.028 |
helper | -0.026 |
payoff | -0.026 |
bless | -0.026 |
Token | ches |
Token ID | 2052 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
nam | +0.163 |
ivating | +0.143 |
ptions | +0.141 |
opes | +0.141 |
years | +0.132 |
Neg logit contributions | |
kiss | -0.217 |
hug | -0.192 |
, | -0.191 |
thanks | -0.185 |
welcome | -0.185 |
Token | it |
Token ID | 340 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
nam | +0.365 |
opes | +0.363 |
ptions | +0.352 |
years | +0.337 |
ants | +0.334 |
Neg logit contributions | |
, | -0.156 |
. | -0.133 |
kiss | -0.119 |
hug | -0.105 |
last | -0.104 |
Token | . |
Token ID | 13 |
Feature activation | +5.61e-04 |
Pos logit contributions | |
opes | +0.127 |
ts | +0.125 |
ants | +0.125 |
ivating | +0.123 |
ptions | +0.123 |
Neg logit contributions | |
kiss | -0.018 |
, | -0.012 |
welcome | -0.011 |
thanks | -0.009 |
luck | -0.008 |
Token | They |
Token ID | 1119 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
kiss | +0.001 |
welcome | +0.001 |
thanks | +0.001 |
prayer | +0.001 |
bye | +0.001 |
Neg logit contributions | |
ts | -0.001 |
opes | -0.001 |
ants | -0.001 |
ivating | -0.001 |
od | -0.001 |
Token | have |
Token ID | 423 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
opes | +0.007 |
ants | +0.007 |
ts | +0.007 |
ivating | +0.007 |
od | +0.006 |
Neg logit contributions | |
kiss | -0.005 |
welcome | -0.004 |
wave | -0.004 |
thanks | -0.004 |
bless | -0.004 |
Token | fun |
Token ID | 1257 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
kiss | +0.015 |
welcome | +0.013 |
bless | +0.013 |
helper | +0.013 |
eye | +0.013 |
Neg logit contributions | |
ts | -0.020 |
opes | -0.019 |
like | -0.019 |
ivating | -0.018 |
tered | -0.018 |
Token | had |
Token ID | 550 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
ts | +0.020 |
opes | +0.020 |
ants | +0.019 |
ivating | +0.019 |
tered | +0.019 |
Neg logit contributions | |
kiss | -0.015 |
welcome | -0.014 |
helper | -0.013 |
bless | -0.013 |
payoff | -0.013 |
Token | never |
Token ID | 1239 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
ts | +0.020 |
opes | +0.019 |
tered | +0.018 |
like | +0.018 |
od | +0.018 |
Neg logit contributions | |
kiss | -0.019 |
welcome | -0.018 |
eye | -0.017 |
helper | -0.017 |
bless | -0.017 |
Token | surrendered |
Token ID | 29209 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
kiss | +0.054 |
prayer | +0.050 |
ma | +0.050 |
ama | +0.049 |
bless | +0.048 |
Neg logit contributions | |
ts | -0.048 |
ptions | -0.045 |
like | -0.044 |
scored | -0.043 |
ved | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
ts | +0.019 |
opes | +0.018 |
like | +0.018 |
tered | +0.018 |
ants | +0.018 |
Neg logit contributions | |
kiss | -0.015 |
bless | -0.013 |
helper | -0.013 |
welcome | -0.013 |
payoff | -0.013 |
Token | Sy |
Token ID | 1632 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
ts | +0.016 |
opes | +0.016 |
ants | +0.016 |
ivating | +0.016 |
od | +0.015 |
Neg logit contributions | |
kiss | -0.017 |
welcome | -0.016 |
helper | -0.015 |
payoff | -0.015 |
bless | -0.015 |
Token | lves |
Token ID | 31018 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
opes | +0.070 |
ants | +0.067 |
ivating | +0.065 |
tered | +0.064 |
ts | +0.064 |
Neg logit contributions | |
kiss | -0.200 |
welcome | -0.193 |
luck | -0.191 |
helper | -0.190 |
girl | -0.190 |
Token | ter |
Token ID | 353 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
opes | +0.285 |
ants | +0.276 |
ts | +0.272 |
ivating | +0.272 |
ination | +0.267 |
Neg logit contributions | |
welcome | -0.162 |
kiss | -0.158 |
girl | -0.151 |
luck | -0.150 |
helper | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | -7.67e-03 |
Pos logit contributions | |
ts | +0.112 |
od | +0.112 |
opes | +0.111 |
ants | +0.111 |
ivating | +0.111 |
Neg logit contributions | |
kiss | -0.064 |
welcome | -0.056 |
payoff | -0.055 |
shines | -0.053 |
bless | -0.052 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.80e-03 |
Pos logit contributions | |
ts | +0.014 |
opes | +0.014 |
ants | +0.014 |
ivating | +0.013 |
od | +0.013 |
Neg logit contributions | |
kiss | -0.009 |
welcome | -0.009 |
thanks | -0.008 |
bye | -0.008 |
girl | -0.008 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.16e-03 |
Pos logit contributions | |
kiss | +0.007 |
welcome | +0.006 |
thanks | +0.006 |
? | +0.005 |
, | +0.005 |
Neg logit contributions | |
opes | -0.014 |
ants | -0.014 |
ts | -0.014 |
ivating | -0.014 |
tered | -0.013 |
Token | upon |
Token ID | 2402 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
opes | +0.003 |
ts | +0.003 |
ivating | +0.003 |
tered | +0.003 |
ants | +0.003 |
Neg logit contributions | |
kiss | -0.003 |
welcome | -0.003 |
, | -0.003 |
ma | -0.003 |
? | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-03 |
Pos logit contributions | |
helper | +0.041 |
payoff | +0.040 |
service | +0.038 |
shines | +0.038 |
reward | +0.037 |
Neg logit contributions | |
tered | -0.051 |
od | -0.050 |
int | -0.049 |
ts | -0.049 |
gging | -0.047 |
Token | She |
Token ID | 1375 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
kiss | +0.004 |
payoff | +0.004 |
bless | +0.004 |
helper | +0.004 |
promise | +0.004 |
Neg logit contributions | |
ivating | -0.005 |
opes | -0.005 |
ants | -0.005 |
od | -0.005 |
like | -0.005 |
Token | likes |
Token ID | 7832 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
kiss | +0.017 |
bye | +0.016 |
welcome | +0.016 |
distance | +0.016 |
payoff | +0.016 |
Neg logit contributions | |
opes | -0.022 |
ts | -0.022 |
od | -0.021 |
ants | -0.021 |
ivating | -0.020 |
Token | d |
Token ID | 288 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
opes | +0.023 |
ivating | +0.023 |
ts | +0.023 |
ants | +0.023 |
tered | +0.023 |
Neg logit contributions | |
kiss | -0.017 |
welcome | -0.015 |
helper | -0.014 |
thanks | -0.014 |
bless | -0.014 |
Token | aff |
Token ID | 2001 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ts | +0.044 |
opes | +0.042 |
nam | +0.040 |
ggies | +0.039 |
ination | +0.039 |
Neg logit contributions | |
kiss | -0.070 |
welcome | -0.065 |
eye | -0.064 |
luck | -0.063 |
bless | -0.062 |
Token | od |
Token ID | 375 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
tered | +0.102 |
tant | +0.102 |
ivating | +0.101 |
opes | +0.099 |
issors | +0.096 |
Neg logit contributions | |
kiss | -0.262 |
, | -0.256 |
welcome | -0.253 |
ma | -0.252 |
bless | -0.249 |
Token | ils |
Token ID | 4487 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
ivating | +0.226 |
tered | +0.216 |
nam | +0.216 |
opes | +0.215 |
ts | +0.212 |
Neg logit contributions | |
kiss | -0.223 |
luck | -0.204 |
thanks | -0.203 |
welcome | -0.203 |
ma | -0.202 |
Token | too |
Token ID | 1165 |
Feature activation | +1.15e-03 |
Pos logit contributions | |
ts | +0.130 |
opes | +0.130 |
ants | +0.129 |
ivating | +0.128 |
od | +0.126 |
Neg logit contributions | |
kiss | -0.046 |
welcome | -0.040 |
helper | -0.036 |
payoff | -0.035 |
bless | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +2.63e-03 |
Pos logit contributions | |
kiss | +0.001 |
bless | +0.001 |
payoff | +0.001 |
shines | +0.001 |
helper | +0.001 |
Neg logit contributions | |
od | -0.002 |
ts | -0.002 |
ants | -0.002 |
tered | -0.002 |
opes | -0.002 |
Token | But |
Token ID | 887 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
kiss | +0.004 |
payoff | +0.003 |
helper | +0.003 |
bless | +0.003 |
promise | +0.003 |
Neg logit contributions | |
ivating | -0.004 |
ants | -0.004 |
opes | -0.004 |
od | -0.004 |
like | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | +2.21e-03 |
Pos logit contributions | |
kiss | +0.032 |
welcome | +0.028 |
bless | +0.028 |
helper | +0.027 |
payoff | +0.027 |
Neg logit contributions | |
ts | -0.058 |
od | -0.057 |
ivating | -0.057 |
ants | -0.057 |
opes | -0.057 |
Token | stubborn |
Token ID | 24444 |
Feature activation | -9.10e-03 |
Pos logit contributions | |
kiss | +0.041 |
welcome | +0.040 |
thanks | +0.036 |
luck | +0.036 |
helper | +0.036 |
Neg logit contributions | |
opes | -0.048 |
ants | -0.048 |
ts | -0.046 |
ivating | -0.046 |
od | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +5.06e-03 |
Pos logit contributions | |
tered | +0.016 |
opes | +0.016 |
od | +0.016 |
ts | +0.015 |
like | +0.015 |
Neg logit contributions | |
kiss | -0.011 |
bless | -0.010 |
repay | -0.010 |
welcome | -0.010 |
shines | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
kiss | +0.006 |
welcome | +0.005 |
helper | +0.005 |
payoff | +0.005 |
luck | +0.005 |
Neg logit contributions | |
opes | -0.009 |
ivating | -0.009 |
ants | -0.009 |
ts | -0.009 |
od | -0.009 |
Token | throws |
Token ID | 12542 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
kiss | +0.026 |
welcome | +0.024 |
helper | +0.022 |
luck | +0.022 |
bless | +0.022 |
Neg logit contributions | |
opes | -0.037 |
ts | -0.037 |
ants | -0.036 |
ivating | -0.036 |
od | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
opes | +0.061 |
ants | +0.059 |
ivating | +0.058 |
od | +0.058 |
ts | +0.058 |
Neg logit contributions | |
kiss | -0.041 |
welcome | -0.037 |
girl | -0.035 |
luck | -0.034 |
thanks | -0.034 |
Token | tant |
Token ID | 24246 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
opes | +0.012 |
ts | +0.012 |
ants | +0.012 |
ivating | +0.012 |
od | +0.011 |
Neg logit contributions | |
kiss | -0.023 |
welcome | -0.022 |
helper | -0.021 |
payoff | -0.021 |
bless | -0.021 |
Token | rum |
Token ID | 6582 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
ivating | +0.210 |
opes | +0.200 |
targets | +0.197 |
ts | +0.197 |
IT | +0.196 |
Neg logit contributions | |
kiss | -0.228 |
ma | -0.224 |
welcome | -0.216 |
bye | -0.213 |
, | -0.209 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
opes | +0.054 |
ts | +0.053 |
ants | +0.053 |
ivating | +0.052 |
tered | +0.052 |
Neg logit contributions | |
kiss | -0.020 |
welcome | -0.017 |
helper | -0.016 |
payoff | -0.016 |
bless | -0.015 |
Token | She |
Token ID | 1375 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
ts | +0.006 |
opes | +0.006 |
ants | +0.005 |
amus | +0.005 |
ivating | +0.005 |
Neg logit contributions | |
kiss | -0.002 |
welcome | -0.002 |
, | -0.002 |
? | -0.002 |
thanks | -0.002 |
Token | kicks |
Token ID | 17364 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
kiss | +0.017 |
welcome | +0.015 |
thanks | +0.014 |
wave | +0.014 |
luck | +0.014 |
Neg logit contributions | |
ants | -0.027 |
opes | -0.026 |
ivating | -0.026 |
ts | -0.026 |
od | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
opes | +0.058 |
ggies | +0.056 |
ivating | +0.056 |
oving | +0.056 |
ination | +0.056 |
Neg logit contributions | |
kiss | -0.026 |
, | -0.026 |
girl | -0.023 |
welcome | -0.022 |
? | -0.021 |
Token | ball |
Token ID | 2613 |
Feature activation | +1.46e-03 |
Pos logit contributions | |
opes | +0.032 |
ts | +0.032 |
ants | +0.031 |
ivating | +0.031 |
od | +0.030 |
Neg logit contributions | |
kiss | -0.028 |
welcome | -0.025 |
girl | -0.024 |
helper | -0.024 |
wave | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
kiss | +0.001 |
welcome | +0.001 |
helper | +0.001 |
thanks | +0.001 |
luck | +0.001 |
Neg logit contributions | |
opes | -0.003 |
ts | -0.003 |
ants | -0.003 |
ivating | -0.003 |
od | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
ts | +0.014 |
opes | +0.013 |
tered | +0.013 |
targets | +0.013 |
nam | +0.012 |
Neg logit contributions | |
ma | -0.017 |
helper | -0.017 |
welcome | -0.017 |
kiss | -0.017 |
bless | -0.017 |
Token | dog |
Token ID | 3290 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
kiss | +0.028 |
welcome | +0.026 |
helper | +0.025 |
payoff | +0.025 |
bless | +0.025 |
Neg logit contributions | |
ts | -0.033 |
opes | -0.033 |
targets | -0.032 |
like | -0.032 |
ants | -0.031 |
Token | fet |
Token ID | 11351 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ts | +0.068 |
opes | +0.067 |
ants | +0.066 |
ivating | +0.066 |
like | +0.065 |
Neg logit contributions | |
kiss | -0.029 |
welcome | -0.026 |
helper | -0.025 |
payoff | -0.024 |
bless | -0.024 |
Token | ches |
Token ID | 2052 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
nam | +0.156 |
ptions | +0.135 |
opes | +0.135 |
ivating | +0.135 |
ts | +0.126 |
Neg logit contributions | |
kiss | -0.215 |
hug | -0.191 |
, | -0.190 |
welcome | -0.184 |
thanks | -0.184 |
Token | it |
Token ID | 340 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
nam | +0.385 |
opes | +0.380 |
ptions | +0.367 |
years | +0.354 |
ants | +0.348 |
Neg logit contributions | |
, | -0.143 |
. | -0.126 |
kiss | -0.095 |
last | -0.090 |
end | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +3.64e-03 |
Pos logit contributions | |
opes | +0.123 |
ts | +0.121 |
ants | +0.120 |
ptions | +0.118 |
ivating | +0.118 |
Neg logit contributions | |
kiss | -0.016 |
, | -0.011 |
welcome | -0.010 |
thanks | -0.007 |
luck | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
kiss | +0.005 |
welcome | +0.005 |
thanks | +0.005 |
bless | +0.004 |
helper | +0.004 |
Neg logit contributions | |
ts | -0.006 |
opes | -0.006 |
ants | -0.006 |
ivating | -0.006 |
od | -0.006 |
Token | hug |
Token ID | 16225 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
opes | +0.007 |
ants | +0.007 |
ts | +0.007 |
ivating | +0.007 |
od | +0.006 |
Neg logit contributions | |
kiss | -0.005 |
welcome | -0.004 |
wave | -0.004 |
thanks | -0.004 |
bless | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
kiss | +0.061 |
, | +0.054 |
girl | +0.052 |
welcome | +0.052 |
thanks | +0.051 |
Neg logit contributions | |
opes | -0.092 |
ivating | -0.092 |
ants | -0.091 |
ts | -0.090 |
od | -0.089 |
Token | rubber |
Token ID | 14239 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
kiss | +0.006 |
welcome | +0.006 |
helper | +0.005 |
luck | +0.005 |
payoff | +0.005 |
Neg logit contributions | |
opes | -0.010 |
ts | -0.010 |
ants | -0.010 |
ivating | -0.010 |
od | -0.010 |
Token | band |
Token ID | 4097 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
ts | +0.088 |
opes | +0.086 |
ants | +0.086 |
ivating | +0.084 |
like | +0.084 |
Neg logit contributions | |
kiss | -0.068 |
welcome | -0.063 |
payoff | -0.060 |
bless | -0.059 |
thanks | -0.059 |
Token | around |
Token ID | 1088 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
opes | +0.102 |
ivating | +0.101 |
ants | +0.100 |
ts | +0.099 |
ptions | +0.097 |
Neg logit contributions | |
kiss | -0.057 |
welcome | -0.049 |
bye | -0.048 |
, | -0.047 |
luck | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
ants | +0.194 |
opes | +0.191 |
ivating | +0.186 |
like | +0.184 |
anned | +0.184 |
Neg logit contributions | |
kiss | -0.105 |
, | -0.096 |
welcome | -0.093 |
girl | -0.091 |
thanks | -0.087 |
Token | sho |
Token ID | 7354 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
ts | +0.029 |
opes | +0.028 |
targets | +0.027 |
viol | +0.027 |
ivating | +0.027 |
Neg logit contributions | |
kiss | -0.019 |
welcome | -0.018 |
bye | -0.017 |
luck | -0.017 |
payoff | -0.017 |
Token | eb |
Token ID | 1765 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ants | +0.084 |
opes | +0.083 |
ts | +0.082 |
ivating | +0.082 |
od | +0.081 |
Neg logit contributions | |
kiss | -0.074 |
welcome | -0.069 |
payoff | -0.067 |
helper | -0.067 |
prayer | -0.066 |
Token | ox |
Token ID | 1140 |
Feature activation | -7.60e-02 |
Pos logit contributions | |
opes | +0.174 |
ts | +0.174 |
ants | +0.172 |
od | +0.164 |
ivating | +0.158 |
Neg logit contributions | |
kiss | -0.276 |
welcome | -0.263 |
payoff | -0.254 |
helper | -0.250 |
luck | -0.249 |
Token | and |
Token ID | 290 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
ants | +0.155 |
opes | +0.154 |
od | +0.154 |
ts | +0.154 |
ivating | +0.152 |
Neg logit contributions | |
kiss | -0.070 |
welcome | -0.065 |
payoff | -0.062 |
helper | -0.062 |
bless | -0.062 |
Token | pl |
Token ID | 458 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
ts | +0.050 |
opes | +0.048 |
tered | +0.046 |
like | +0.045 |
targets | +0.045 |
Neg logit contributions | |
welcome | -0.043 |
kiss | -0.042 |
bye | -0.041 |
helper | -0.041 |
ma | -0.041 |
Token | ucks |
Token ID | 6238 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
opes | +0.050 |
ts | +0.050 |
ants | +0.049 |
ivating | +0.048 |
tered | +0.047 |
Neg logit contributions | |
kiss | -0.057 |
welcome | -0.052 |
helper | -0.050 |
bless | -0.050 |
luck | -0.050 |
Token | it |
Token ID | 340 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
kiss | +0.054 |
helper | +0.051 |
promise | +0.050 |
bless | +0.050 |
payoff | +0.050 |
Neg logit contributions | |
ts | -0.041 |
tered | -0.040 |
like | -0.038 |
opes | -0.037 |
ivating | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -6.90e-04 |
Pos logit contributions | |
kiss | +0.031 |
welcome | +0.027 |
bless | +0.026 |
helper | +0.026 |
shines | +0.025 |
Neg logit contributions | |
ts | -0.078 |
opes | -0.078 |
tered | -0.078 |
ants | -0.077 |
ivating | -0.076 |
Token | He |
Token ID | 679 |
Feature activation | -6.56e-03 |
Pos logit contributions | |
opes | +0.001 |
tered | +0.001 |
ivating | +0.001 |
ination | +0.001 |
ts | +0.001 |
Neg logit contributions | |
kiss | -0.001 |
bless | -0.001 |
payoff | -0.001 |
ma | -0.001 |
promise | -0.001 |
Token | kept |
Token ID | 4030 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
ts | +0.011 |
opes | +0.011 |
ivating | +0.011 |
ants | +0.011 |
tered | +0.010 |
Neg logit contributions | |
kiss | -0.009 |
welcome | -0.008 |
helper | -0.008 |
bless | -0.008 |
payoff | -0.008 |
Token | throwing |
Token ID | 9644 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
kiss | +0.021 |
welcome | +0.020 |
thanks | +0.019 |
helper | +0.019 |
wave | +0.019 |
Neg logit contributions | |
ants | -0.023 |
opes | -0.023 |
ivating | -0.023 |
tered | -0.022 |
od | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
opes | +0.087 |
ts | +0.086 |
ants | +0.086 |
ivating | +0.085 |
od | +0.084 |
Neg logit contributions | |
kiss | -0.069 |
welcome | -0.063 |
luck | -0.059 |
helper | -0.059 |
payoff | -0.059 |
Token | tant |
Token ID | 24246 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
tant | +0.031 |
ts | +0.031 |
ants | +0.030 |
opes | +0.030 |
like | +0.030 |
Neg logit contributions | |
kiss | -0.029 |
welcome | -0.028 |
payoff | -0.027 |
thanks | -0.027 |
bye | -0.027 |
Token | rum |
Token ID | 6582 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
ivating | +0.202 |
opes | +0.199 |
ts | +0.195 |
targets | +0.191 |
nam | +0.189 |
Neg logit contributions | |
kiss | -0.239 |
welcome | -0.224 |
ma | -0.223 |
bye | -0.216 |
bless | -0.215 |
Token | . |
Token ID | 13 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
ts | +0.046 |
opes | +0.046 |
tered | +0.046 |
ants | +0.045 |
ivating | +0.045 |
Neg logit contributions | |
kiss | -0.020 |
welcome | -0.017 |
bless | -0.017 |
payoff | -0.016 |
helper | -0.016 |
Token | His |
Token ID | 2399 |
Feature activation | -1.58e-03 |
Pos logit contributions | |
kiss | +0.004 |
welcome | +0.004 |
helper | +0.003 |
thanks | +0.003 |
payoff | +0.003 |
Neg logit contributions | |
ts | -0.007 |
opes | -0.007 |
ants | -0.007 |
ivating | -0.006 |
od | -0.006 |
Token | mom |
Token ID | 1995 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
ts | +0.003 |
tant | +0.003 |
opes | +0.003 |
nam | +0.003 |
ggies | +0.003 |
Neg logit contributions | |
welcome | -0.002 |
kiss | -0.002 |
bless | -0.002 |
thanks | -0.002 |
payoff | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -8.62e-03 |
Pos logit contributions | |
kiss | +0.100 |
welcome | +0.095 |
luck | +0.089 |
helper | +0.087 |
payoff | +0.087 |
Neg logit contributions | |
ts | -0.149 |
opes | -0.144 |
tered | -0.142 |
ants | -0.141 |
ivating | -0.141 |
Token | should |
Token ID | 815 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
ts | +0.007 |
opes | +0.007 |
ants | +0.007 |
ivating | +0.007 |
od | +0.006 |
Neg logit contributions | |
kiss | -0.006 |
welcome | -0.005 |
helper | -0.005 |
payoff | -0.005 |
bless | -0.005 |
Token | not |
Token ID | 407 |
Feature activation | -4.41e-03 |
Pos logit contributions | |
ts | +0.016 |
opes | +0.016 |
issors | +0.016 |
tered | +0.016 |
ggies | +0.016 |
Neg logit contributions | |
seat | -0.025 |
shines | -0.025 |
girl | -0.025 |
cottage | -0.024 |
distance | -0.024 |
Token | tease |
Token ID | 34691 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
opes | +0.007 |
ts | +0.007 |
ants | +0.007 |
ivating | +0.007 |
od | +0.007 |
Neg logit contributions | |
kiss | -0.006 |
welcome | -0.005 |
luck | -0.005 |
helper | -0.005 |
payoff | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.71e-03 |
Pos logit contributions | |
opes | +0.050 |
ts | +0.050 |
ants | +0.049 |
ivating | +0.049 |
tered | +0.048 |
Neg logit contributions | |
kiss | -0.041 |
welcome | -0.038 |
bless | -0.035 |
thanks | -0.035 |
luck | -0.035 |
Token | ost |
Token ID | 23619 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
kiss | +0.002 |
welcome | +0.002 |
girl | +0.002 |
helper | +0.002 |
payoff | +0.002 |
Neg logit contributions | |
opes | -0.003 |
ivating | -0.003 |
ants | -0.003 |
ts | -0.003 |
tered | -0.003 |
Token | ric |
Token ID | 1173 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
tered | +0.065 |
ivating | +0.062 |
ts | +0.061 |
nam | +0.060 |
tant | +0.058 |
Neg logit contributions | |
kiss | -0.094 |
ma | -0.091 |
bless | -0.089 |
welcome | -0.089 |
? | -0.088 |
Token | hes |
Token ID | 956 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
viol | +0.224 |
nam | +0.217 |
ivating | +0.200 |
opes | +0.199 |
ptions | +0.198 |
Neg logit contributions | |
? | -0.241 |
welcome | -0.232 |
ma | -0.218 |
kiss | -0.214 |
. | -0.214 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e-03 |
Pos logit contributions | |
ts | +0.102 |
opes | +0.102 |
ants | +0.101 |
ivating | +0.100 |
tered | +0.099 |
Neg logit contributions | |
kiss | -0.041 |
welcome | -0.035 |
helper | -0.034 |
payoff | -0.033 |
luck | -0.033 |
Token | They |
Token ID | 1119 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
kiss | +0.002 |
luck | +0.002 |
payoff | +0.002 |
wave | +0.002 |
helper | +0.002 |
Neg logit contributions | |
ants | -0.002 |
opes | -0.002 |
ivating | -0.002 |
ination | -0.002 |
od | -0.002 |
Token | are |
Token ID | 389 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
kiss | +0.004 |
welcome | +0.003 |
helper | +0.003 |
bless | +0.003 |
payoff | +0.003 |
Neg logit contributions | |
opes | -0.005 |
ts | -0.005 |
ants | -0.005 |
ivating | -0.005 |
od | -0.005 |
Token | not |
Token ID | 407 |
Feature activation | +7.05e-03 |
Pos logit contributions | |
kiss | +0.043 |
welcome | +0.041 |
helper | +0.039 |
luck | +0.039 |
thanks | +0.039 |
Neg logit contributions | |
opes | -0.036 |
ts | -0.035 |
ants | -0.035 |
ivating | -0.035 |
od | -0.034 |
Token | ball |
Token ID | 2613 |
Feature activation | +3.10e-04 |
Pos logit contributions | |
kiss | +0.019 |
welcome | +0.017 |
helper | +0.016 |
luck | +0.016 |
girl | +0.016 |
Neg logit contributions | |
opes | -0.032 |
ts | -0.032 |
ants | -0.031 |
ivating | -0.031 |
od | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
kiss | +0.000 |
welcome | +0.000 |
luck | +0.000 |
thanks | +0.000 |
helper | +0.000 |
Neg logit contributions | |
opes | -0.001 |
ts | -0.001 |
ants | -0.001 |
ivating | -0.001 |
od | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ts | +0.021 |
opes | +0.019 |
targets | +0.019 |
tered | +0.018 |
viol | +0.018 |
Neg logit contributions | |
kiss | -0.019 |
welcome | -0.019 |
helper | -0.019 |
ma | -0.019 |
luck | -0.018 |
Token | dog |
Token ID | 3290 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
kiss | +0.027 |
welcome | +0.025 |
helper | +0.025 |
bless | +0.025 |
payoff | +0.025 |
Neg logit contributions | |
ts | -0.031 |
opes | -0.031 |
ivating | -0.029 |
ants | -0.029 |
like | -0.029 |
Token | fet |
Token ID | 11351 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ts | +0.058 |
opes | +0.058 |
ants | +0.057 |
ivating | +0.056 |
od | +0.056 |
Neg logit contributions | |
kiss | -0.034 |
welcome | -0.031 |
helper | -0.029 |
payoff | -0.029 |
bless | -0.028 |
Token | ches |
Token ID | 2052 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
nam | +0.161 |
ptions | +0.141 |
opes | +0.139 |
ivating | +0.138 |
years | +0.131 |
Neg logit contributions | |
kiss | -0.204 |
, | -0.181 |
hug | -0.181 |
welcome | -0.175 |
thanks | -0.173 |
Token | it |
Token ID | 340 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
nam | +0.367 |
opes | +0.364 |
ptions | +0.356 |
ts | +0.336 |
years | +0.334 |
Neg logit contributions | |
, | -0.144 |
. | -0.123 |
kiss | -0.104 |
hug | -0.092 |
! | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e-05 |
Pos logit contributions | |
ts | +0.119 |
opes | +0.118 |
ants | +0.116 |
ptions | +0.115 |
ivating | +0.115 |
Neg logit contributions | |
kiss | -0.017 |
, | -0.013 |
welcome | -0.011 |
thanks | -0.009 |
luck | -0.008 |
Token | They |
Token ID | 1119 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
kiss | +0.000 |
welcome | +0.000 |
thanks | +0.000 |
bless | +0.000 |
payoff | +0.000 |
Neg logit contributions | |
ts | -0.000 |
opes | -0.000 |
ants | -0.000 |
ivating | -0.000 |
od | -0.000 |
Token | push |
Token ID | 4574 |
Feature activation | +2.91e-03 |
Pos logit contributions | |
opes | +0.005 |
ants | +0.005 |
ts | +0.005 |
ivating | +0.005 |
od | +0.005 |
Neg logit contributions | |
kiss | -0.004 |
welcome | -0.003 |
wave | -0.003 |
thanks | -0.003 |
bless | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
, | +0.003 |
kiss | +0.003 |
girl | +0.003 |
welcome | +0.003 |
return | +0.003 |
Neg logit contributions | |
opes | -0.006 |
ivating | -0.006 |
ination | -0.006 |
ants | -0.006 |
anned | -0.006 |
Token | wanted |
Token ID | 2227 |
Feature activation | +5.02e-03 |
Pos logit contributions | |
ants | +0.001 |
opes | +0.001 |
ivating | +0.001 |
od | +0.001 |
ts | +0.001 |
Neg logit contributions | |
kiss | -0.001 |
welcome | -0.001 |
wave | -0.001 |
eye | -0.001 |
promise | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -5.48e-03 |
Pos logit contributions | |
kiss | +0.007 |
welcome | +0.006 |
bless | +0.006 |
bye | +0.006 |
helper | +0.006 |
Neg logit contributions | |
ts | -0.008 |
opes | -0.008 |
ants | -0.008 |
like | -0.008 |
od | -0.008 |
Token | touch |
Token ID | 3638 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
ts | +0.009 |
opes | +0.009 |
ivating | +0.009 |
ants | +0.009 |
od | +0.009 |
Neg logit contributions | |
kiss | -0.007 |
luck | -0.006 |
payoff | -0.006 |
welcome | -0.006 |
helper | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
kiss | +0.060 |
welcome | +0.056 |
helper | +0.054 |
payoff | +0.053 |
bless | +0.053 |
Neg logit contributions | |
ts | -0.055 |
opes | -0.055 |
ants | -0.054 |
ivating | -0.054 |
od | -0.052 |
Token | ost |
Token ID | 23619 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
kiss | +0.013 |
welcome | +0.012 |
girl | +0.011 |
wave | +0.011 |
eye | +0.011 |
Neg logit contributions | |
ivating | -0.019 |
ts | -0.019 |
ants | -0.019 |
opes | -0.019 |
tered | -0.019 |
Token | ric |
Token ID | 1173 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
tered | +0.064 |
ts | +0.063 |
ivating | +0.062 |
tant | +0.060 |
nam | +0.059 |
Neg logit contributions | |
kiss | -0.097 |
ma | -0.093 |
welcome | -0.092 |
bless | -0.091 |
eye | -0.091 |
Token | hes |
Token ID | 956 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
viol | +0.249 |
nam | +0.238 |
ptions | +0.223 |
opes | +0.212 |
targets | +0.211 |
Neg logit contributions | |
? | -0.228 |
welcome | -0.215 |
ma | -0.213 |
. | -0.207 |
, | -0.204 |
Token | . |
Token ID | 13 |
Feature activation | +6.44e-04 |
Pos logit contributions | |
ts | +0.107 |
opes | +0.107 |
ants | +0.105 |
ivating | +0.105 |
od | +0.103 |
Neg logit contributions | |
kiss | -0.037 |
welcome | -0.031 |
helper | -0.028 |
payoff | -0.028 |
bless | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | -4.93e-03 |
Pos logit contributions | |
kiss | +0.001 |
welcome | +0.001 |
helper | +0.001 |
bless | +0.001 |
luck | +0.001 |
Neg logit contributions | |
opes | -0.001 |
ts | -0.001 |
ants | -0.001 |
ivating | -0.001 |
tered | -0.001 |
Token | reached |
Token ID | 4251 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
ants | +0.010 |
opes | +0.010 |
ivating | +0.010 |
od | +0.010 |
ination | +0.010 |
Neg logit contributions | |
kiss | -0.006 |
left | -0.005 |
wave | -0.005 |
promise | -0.005 |
eye | -0.005 |
Token | out |
Token ID | 503 |
Feature activation | +6.85e-03 |
Pos logit contributions | |
kiss | +0.034 |
welcome | +0.032 |
eye | +0.030 |
helper | +0.030 |
wave | +0.030 |
Neg logit contributions | |
opes | -0.035 |
ts | -0.034 |
ivating | -0.034 |
ants | -0.034 |
tered | -0.033 |
Token | singing |
Token ID | 13777 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
, | +0.050 |
welcome | +0.048 |
kiss | +0.046 |
? | +0.044 |
wave | +0.043 |
Neg logit contributions | |
ts | -0.075 |
ants | -0.070 |
tered | -0.069 |
opes | -0.069 |
issors | -0.067 |
Token | about |
Token ID | 546 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
ts | +0.050 |
opes | +0.050 |
ants | +0.050 |
ivating | +0.049 |
od | +0.048 |
Neg logit contributions | |
kiss | -0.024 |
welcome | -0.021 |
helper | -0.019 |
bless | -0.019 |
luck | -0.019 |
Token | jail |
Token ID | 7356 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ts | +0.080 |
opes | +0.079 |
ants | +0.079 |
ivating | +0.078 |
od | +0.077 |
Neg logit contributions | |
kiss | -0.060 |
welcome | -0.055 |
helper | -0.052 |
bless | -0.052 |
luck | -0.051 |
Token | ?" |
Token ID | 1701 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
ts | +0.032 |
opes | +0.031 |
ants | +0.031 |
ivating | +0.031 |
od | +0.030 |
Neg logit contributions | |
kiss | -0.011 |
welcome | -0.009 |
helper | -0.009 |
payoff | -0.009 |
bless | -0.008 |
Token | Sy |
Token ID | 1632 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
opes | +0.059 |
ts | +0.059 |
ants | +0.058 |
ivating | +0.057 |
od | +0.056 |
Neg logit contributions | |
kiss | -0.051 |
welcome | -0.047 |
girl | -0.044 |
helper | -0.044 |
wave | -0.044 |
Token | lves |
Token ID | 31018 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
opes | +0.102 |
tered | +0.096 |
ants | +0.094 |
ivating | +0.093 |
ggies | +0.091 |
Neg logit contributions | |
girl | -0.141 |
ma | -0.139 |
eye | -0.139 |
, | -0.138 |
kiss | -0.138 |
Token | ter |
Token ID | 353 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
opes | +0.299 |
ivating | +0.288 |
ggies | +0.288 |
ants | +0.286 |
ination | +0.285 |
Neg logit contributions | |
girl | -0.129 |
welcome | -0.126 |
kiss | -0.122 |
fairy | -0.118 |
bye | -0.118 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
opes | +0.126 |
ts | +0.125 |
ants | +0.123 |
ivating | +0.123 |
like | +0.120 |
Neg logit contributions | |
kiss | -0.067 |
welcome | -0.058 |
wave | -0.055 |
girl | -0.055 |
helper | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +3.69e-04 |
Pos logit contributions | |
kiss | +0.014 |
welcome | +0.011 |
luck | +0.009 |
helper | +0.009 |
thanks | +0.009 |
Neg logit contributions | |
opes | -0.068 |
ts | -0.068 |
ants | -0.067 |
ivating | -0.067 |
od | -0.066 |
Token | |
Token ID | 220 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
kiss | +0.000 |
welcome | +0.000 |
, | +0.000 |
girl | +0.000 |
lady | +0.000 |
Neg logit contributions | |
ts | -0.001 |
opes | -0.001 |
ants | -0.001 |
od | -0.001 |
izards | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.53e-04 |
Pos logit contributions | |
ts | +0.112 |
opes | +0.109 |
ptions | +0.106 |
ivating | +0.104 |
ination | +0.104 |
Neg logit contributions | |
welcome | -0.033 |
kiss | -0.033 |
, | -0.030 |
? | -0.030 |
ma | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
kiss | +0.011 |
welcome | +0.010 |
helper | +0.010 |
payoff | +0.010 |
bless | +0.010 |
Neg logit contributions | |
ts | -0.013 |
opes | -0.013 |
ants | -0.012 |
ivating | -0.012 |
od | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
kiss | +0.017 |
welcome | +0.016 |
? | +0.014 |
ma | +0.014 |
, | +0.013 |
Neg logit contributions | |
ts | -0.038 |
opes | -0.038 |
ivating | -0.037 |
nam | -0.036 |
ants | -0.036 |
Token | B |
Token ID | 33 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
kiss | +0.028 |
welcome | +0.026 |
ma | +0.023 |
girl | +0.023 |
? | +0.023 |
Neg logit contributions | |
ts | -0.041 |
opes | -0.040 |
ants | -0.038 |
ivating | -0.038 |
od | -0.038 |
Token | enny |
Token ID | 11870 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
opes | +0.048 |
ants | +0.048 |
ivating | +0.047 |
ts | +0.047 |
od | +0.046 |
Neg logit contributions | |
kiss | -0.062 |
welcome | -0.058 |
payoff | -0.056 |
bless | -0.056 |
helper | -0.056 |
Token | 's |
Token ID | 338 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
opes | +0.084 |
ts | +0.083 |
ants | +0.081 |
od | +0.081 |
tered | +0.080 |
Neg logit contributions | |
kiss | -0.056 |
welcome | -0.053 |
helper | -0.049 |
luck | -0.049 |
payoff | -0.049 |
Token | mom |
Token ID | 1995 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
kiss | +0.017 |
welcome | +0.016 |
shines | +0.015 |
bless | +0.015 |
payoff | +0.015 |
Neg logit contributions | |
opes | -0.037 |
ts | -0.036 |
targets | -0.035 |
amus | -0.035 |
ants | -0.035 |
Token | my |
Token ID | 1820 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
bye | +0.101 |
luck | +0.098 |
kiss | +0.098 |
welcome | +0.097 |
reward | +0.093 |
Neg logit contributions | |
ts | -0.158 |
od | -0.156 |
opes | -0.154 |
ants | -0.149 |
ptions | -0.148 |
Token | smiled |
Token ID | 13541 |
Feature activation | +9.17e-03 |
Pos logit contributions | |
bye | +0.025 |
kiss | +0.024 |
welcome | +0.024 |
luck | +0.024 |
eye | +0.023 |
Neg logit contributions | |
ts | -0.037 |
od | -0.037 |
opes | -0.036 |
ants | -0.035 |
assed | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
use | +0.013 |
payoff | +0.013 |
service | +0.013 |
ma | +0.012 |
kiss | +0.012 |
Neg logit contributions | |
int | -0.014 |
tered | -0.014 |
od | -0.013 |
ivating | -0.013 |
uted | -0.013 |
Token | said |
Token ID | 531 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
welcome | +0.013 |
eye | +0.013 |
bye | +0.012 |
distance | +0.012 |
service | +0.012 |
Neg logit contributions | |
od | -0.016 |
ts | -0.016 |
tered | -0.015 |
viol | -0.015 |
like | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +8.22e-03 |
Pos logit contributions | |
kiss | +0.015 |
welcome | +0.011 |
eye | +0.011 |
helper | +0.010 |
payoff | +0.010 |
Neg logit contributions | |
ts | -0.077 |
od | -0.076 |
ants | -0.076 |
ivating | -0.075 |
tered | -0.075 |
Token | She |
Token ID | 1375 |
Feature activation | +9.58e-03 |
Pos logit contributions | |
opes | +0.007 |
ants | +0.007 |
ivating | +0.007 |
ts | +0.007 |
od | +0.007 |
Neg logit contributions | |
kiss | -0.007 |
welcome | -0.007 |
luck | -0.007 |
helper | -0.007 |
payoff | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
welcome | +0.013 |
kiss | +0.011 |
payoff | +0.011 |
luck | +0.011 |
helper | +0.011 |
Neg logit contributions | |
ts | -0.015 |
tered | -0.015 |
od | -0.015 |
opes | -0.015 |
viol | -0.014 |
Token | please |
Token ID | 3387 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
kiss | +0.024 |
welcome | +0.022 |
helper | +0.021 |
payoff | +0.020 |
eye | +0.020 |
Neg logit contributions | |
ts | -0.043 |
opes | -0.043 |
ants | -0.043 |
ivating | -0.042 |
tered | -0.042 |
Token | make |
Token ID | 787 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
payoff | +0.063 |
kiss | +0.063 |
helper | +0.063 |
shines | +0.062 |
girl | +0.061 |
Neg logit contributions | |
tered | -0.097 |
ts | -0.094 |
opes | -0.092 |
ination | -0.091 |
od | -0.091 |
Token | the |
Token ID | 262 |
Feature activation | -9.47e-03 |
Pos logit contributions | |
kiss | +0.005 |
welcome | +0.005 |
luck | +0.005 |
thanks | +0.005 |
helper | +0.005 |
Neg logit contributions | |
opes | -0.004 |
ts | -0.004 |
ants | -0.004 |
ivating | -0.004 |
tered | -0.004 |
Token | sun |
Token ID | 4252 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
opes | +0.015 |
nam | +0.015 |
ts | +0.015 |
targets | +0.015 |
tant | +0.015 |
Neg logit contributions | |
kiss | -0.011 |
bless | -0.010 |
shines | -0.010 |
guard | -0.010 |
payoff | -0.010 |
Token | go |
Token ID | 467 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
payoff | +0.128 |
use | +0.120 |
helper | +0.120 |
ara | +0.119 |
welcome | +0.118 |
Neg logit contributions | |
od | -0.163 |
tered | -0.157 |
like | -0.154 |
ants | -0.152 |
opes | -0.150 |
Token | away |
Token ID | 1497 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
kiss | +0.097 |
helper | +0.093 |
payoff | +0.091 |
eye | +0.091 |
bless | +0.090 |
Neg logit contributions | |
tered | -0.069 |
ivating | -0.069 |
like | -0.066 |
ts | -0.063 |
assed | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -5.83e-03 |
Pos logit contributions | |
tered | +0.033 |
od | +0.033 |
ivating | +0.032 |
like | +0.032 |
ants | +0.031 |
Neg logit contributions | |
kiss | -0.023 |
bless | -0.020 |
payoff | -0.020 |
helper | -0.020 |
welcome | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +5.89e-03 |
Pos logit contributions | |
opes | +0.008 |
ants | +0.008 |
ivating | +0.008 |
ts | +0.008 |
od | +0.008 |
Neg logit contributions | |
kiss | -0.009 |
welcome | -0.008 |
luck | -0.008 |
helper | -0.008 |
payoff | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
kiss | +0.003 |
welcome | +0.002 |
ma | +0.002 |
, | +0.002 |
? | +0.002 |
Neg logit contributions | |
ts | -0.016 |
opes | -0.016 |
nam | -0.016 |
ptions | -0.015 |
targets | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
kiss | +0.033 |
welcome | +0.029 |
helper | +0.028 |
payoff | +0.028 |
bless | +0.027 |
Neg logit contributions | |
ts | -0.051 |
opes | -0.051 |
ants | -0.050 |
ivating | -0.050 |
od | -0.049 |
Token | temple |
Token ID | 12505 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
kiss | +0.035 |
bless | +0.032 |
welcome | +0.031 |
helper | +0.031 |
bye | +0.030 |
Neg logit contributions | |
ts | -0.053 |
opes | -0.052 |
targets | -0.051 |
od | -0.051 |
amus | -0.050 |
Token | is |
Token ID | 318 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
kiss | +0.050 |
repay | +0.049 |
distance | +0.049 |
helper | +0.049 |
payoff | +0.048 |
Neg logit contributions | |
ts | -0.061 |
od | -0.060 |
opes | -0.056 |
anned | -0.054 |
ving | -0.054 |
Token | in |
Token ID | 287 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
kiss | +0.045 |
bye | +0.041 |
helper | +0.041 |
bless | +0.040 |
payoff | +0.040 |
Neg logit contributions | |
ts | -0.041 |
opes | -0.040 |
ivating | -0.039 |
ination | -0.039 |
tered | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | +3.40e-03 |
Pos logit contributions | |
ts | +0.044 |
ivating | +0.042 |
ination | +0.041 |
opes | +0.041 |
targets | +0.041 |
Neg logit contributions | |
kiss | -0.059 |
bye | -0.055 |
helper | -0.053 |
bless | -0.052 |
eye | -0.052 |
Token | sun |
Token ID | 4252 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
kiss | +0.004 |
guard | +0.004 |
repay | +0.004 |
helper | +0.004 |
bless | +0.004 |
Neg logit contributions | |
targets | -0.005 |
ination | -0.005 |
ts | -0.005 |
amus | -0.005 |
webs | -0.005 |
Token | now |
Token ID | 783 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
kiss | +0.115 |
payoff | +0.113 |
cal | +0.108 |
luck | +0.108 |
welcome | +0.106 |
Neg logit contributions | |
od | -0.190 |
opes | -0.184 |
ants | -0.184 |
ivating | -0.176 |
tered | -0.175 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
kiss | +0.050 |
helper | +0.044 |
payoff | +0.044 |
bless | +0.043 |
welcome | +0.043 |
Neg logit contributions | |
opes | -0.094 |
tered | -0.094 |
ivating | -0.092 |
ants | -0.090 |
ts | -0.090 |
Token | Maybe |
Token ID | 6674 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
luck | +0.029 |
ma | +0.029 |
payoff | +0.029 |
kiss | +0.028 |
promise | +0.028 |
Neg logit contributions | |
Whoever | -0.019 |
ivating | -0.019 |
ination | -0.019 |
tered | -0.018 |
like | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | -2.86e-03 |
Pos logit contributions | |
kiss | +0.147 |
distance | +0.139 |
repay | +0.138 |
eye | +0.137 |
flower | +0.136 |
Neg logit contributions | |
ts | -0.085 |
nam | -0.077 |
targets | -0.072 |
od | -0.070 |
Whoever | -0.069 |
Token | is |
Token ID | 318 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
ts | +0.006 |
opes | +0.006 |
ivating | +0.006 |
ants | +0.006 |
od | +0.006 |
Neg logit contributions | |
kiss | -0.003 |
welcome | -0.002 |
helper | -0.002 |
payoff | -0.002 |
luck | -0.002 |
Token | cried |
Token ID | 16896 |
Feature activation | -3.54e-03 |
Pos logit contributions | |
ants | +0.000 |
ivating | +0.000 |
od | +0.000 |
ination | +0.000 |
ptions | +0.000 |
Neg logit contributions | |
kiss | -0.000 |
left | -0.000 |
girl | -0.000 |
eye | -0.000 |
, | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
ts | +0.007 |
ants | +0.007 |
opes | +0.007 |
ivating | +0.007 |
od | +0.007 |
Neg logit contributions | |
kiss | -0.004 |
welcome | -0.003 |
luck | -0.003 |
, | -0.003 |
eye | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
kiss | +0.003 |
welcome | +0.003 |
, | +0.003 |
girl | +0.003 |
? | +0.002 |
Neg logit contributions | |
ts | -0.006 |
opes | -0.005 |
ants | -0.005 |
ivating | -0.005 |
targets | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
kiss | +0.009 |
welcome | +0.008 |
, | +0.008 |
? | +0.008 |
ma | +0.007 |
Neg logit contributions | |
opes | -0.034 |
ts | -0.034 |
ivating | -0.032 |
ants | -0.032 |
amus | -0.032 |
Token | Her |
Token ID | 9360 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
kiss | +0.033 |
welcome | +0.029 |
girl | +0.029 |
? | +0.028 |
, | +0.028 |
Neg logit contributions | |
ts | -0.042 |
opes | -0.040 |
targets | -0.040 |
ants | -0.040 |
od | -0.039 |
Token | mom |
Token ID | 1995 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
shines | +0.052 |
welcome | +0.051 |
thanks | +0.049 |
use | +0.049 |
payoff | +0.049 |
Neg logit contributions | |
viol | -0.064 |
opes | -0.062 |
tant | -0.061 |
ggies | -0.061 |
nam | -0.059 |
Token | my |
Token ID | 1820 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
kiss | +0.102 |
luck | +0.098 |
welcome | +0.097 |
payoff | +0.091 |
reward | +0.091 |
Neg logit contributions | |
ts | -0.176 |
opes | -0.171 |
tered | -0.167 |
assed | -0.166 |
ptions | -0.166 |
Token | came |
Token ID | 1625 |
Feature activation | -6.00e-03 |
Pos logit contributions | |
kiss | +0.027 |
welcome | +0.027 |
luck | +0.027 |
bye | +0.025 |
payoff | +0.025 |
Neg logit contributions | |
ts | -0.040 |
opes | -0.039 |
tered | -0.038 |
assed | -0.038 |
od | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | +3.72e-03 |
Pos logit contributions | |
ants | +0.012 |
opes | +0.012 |
ivating | +0.011 |
ts | +0.011 |
tered | +0.011 |
Neg logit contributions | |
kiss | -0.007 |
welcome | -0.007 |
girl | -0.006 |
helper | -0.006 |
, | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
luck | +0.005 |
kiss | +0.005 |
shines | +0.005 |
eye | +0.004 |
bye | +0.004 |
Neg logit contributions | |
ts | -0.006 |
ivating | -0.006 |
nam | -0.006 |
tered | -0.006 |
assed | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +7.05e-03 |
Pos logit contributions | |
kiss | +0.025 |
welcome | +0.024 |
luck | +0.023 |
payoff | +0.022 |
bye | +0.022 |
Neg logit contributions | |
ts | -0.048 |
opes | -0.048 |
ants | -0.047 |
ivating | -0.046 |
od | -0.046 |
Token | th |
Token ID | 294 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
kiss | +0.006 |
welcome | +0.005 |
payoff | +0.005 |
wave | +0.005 |
bless | +0.005 |
Neg logit contributions | |
ts | -0.005 |
opes | -0.005 |
ants | -0.005 |
ivating | -0.005 |
od | -0.004 |
Token | ud |
Token ID | 463 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
opes | +0.025 |
ts | +0.025 |
ants | +0.024 |
ivating | +0.024 |
od | +0.024 |
Neg logit contributions | |
kiss | -0.046 |
welcome | -0.043 |
bless | -0.042 |
luck | -0.042 |
helper | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -5.72e-03 |
Pos logit contributions | |
opes | +0.066 |
ts | +0.066 |
ivating | +0.066 |
ants | +0.064 |
ination | +0.064 |
Neg logit contributions | |
kiss | -0.017 |
welcome | -0.014 |
helper | -0.012 |
wave | -0.012 |
bless | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +8.43e-03 |
Pos logit contributions | |
ts | +0.010 |
opes | +0.010 |
ants | +0.010 |
ivating | +0.010 |
od | +0.010 |
Neg logit contributions | |
kiss | -0.007 |
welcome | -0.007 |
thanks | -0.006 |
? | -0.006 |
, | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
kiss | +0.007 |
welcome | +0.007 |
? | +0.006 |
ma | +0.006 |
, | +0.006 |
Neg logit contributions | |
opes | -0.018 |
ts | -0.018 |
ivating | -0.018 |
ants | -0.018 |
tered | -0.018 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
kiss | +0.019 |
welcome | +0.017 |
helper | +0.016 |
luck | +0.016 |
payoff | +0.016 |
Neg logit contributions | |
ts | -0.032 |
opes | -0.032 |
ants | -0.032 |
ivating | -0.031 |
od | -0.031 |
Token | hears |
Token ID | 23180 |
Feature activation | -9.42e-03 |
Pos logit contributions | |
bye | +0.139 |
kiss | +0.136 |
welcome | +0.130 |
helper | +0.129 |
luck | +0.129 |
Neg logit contributions | |
ts | -0.217 |
opes | -0.216 |
od | -0.204 |
assed | -0.201 |
ants | -0.201 |
Token | the |
Token ID | 262 |
Feature activation | +8.39e-03 |
Pos logit contributions | |
opes | +0.016 |
ts | +0.016 |
ivating | +0.016 |
nam | +0.016 |
ving | +0.016 |
Neg logit contributions | |
kiss | -0.012 |
, | -0.011 |
welcome | -0.011 |
thanks | -0.011 |
surprise | -0.011 |
Token | noise |
Token ID | 7838 |
Feature activation | +9.73e-03 |
Pos logit contributions | |
kiss | +0.012 |
welcome | +0.010 |
wave | +0.010 |
girl | +0.010 |
helper | +0.010 |
Neg logit contributions | |
ants | -0.015 |
ts | -0.014 |
opes | -0.014 |
ivating | -0.014 |
tered | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +7.26e-03 |
Pos logit contributions | |
kiss | +0.011 |
helper | +0.011 |
bye | +0.011 |
welcome | +0.011 |
payoff | +0.011 |
Neg logit contributions | |
ts | -0.017 |
ivating | -0.017 |
od | -0.017 |
tered | -0.017 |
opes | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
kiss | +0.010 |
luck | +0.009 |
bless | +0.009 |
helper | +0.009 |
payoff | +0.009 |
Neg logit contributions | |
opes | -0.011 |
ivating | -0.011 |
ants | -0.011 |
like | -0.011 |
od | -0.011 |
Token | She |
Token ID | 1375 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
kiss | +0.003 |
welcome | +0.003 |
thanks | +0.002 |
girl | +0.002 |
, | +0.002 |
Neg logit contributions | |
ts | -0.004 |
ants | -0.004 |
opes | -0.004 |
ivating | -0.004 |
ptions | -0.004 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
kiss | +0.013 |
welcome | +0.011 |
helper | +0.011 |
thanks | +0.011 |
payoff | +0.011 |
Neg logit contributions | |
opes | -0.019 |
ts | -0.019 |
ants | -0.019 |
ivating | -0.018 |
od | -0.018 |
Token | that |
Token ID | 326 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
ts | +0.034 |
opes | +0.033 |
ants | +0.033 |
ptions | +0.032 |
ivating | +0.032 |
Neg logit contributions | |
kiss | -0.015 |
welcome | -0.013 |
thanks | -0.013 |
luck | -0.013 |
, | -0.013 |
Token | sometimes |
Token ID | 3360 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
ts | +0.005 |
opes | +0.005 |
ivating | +0.005 |
ants | +0.005 |
od | +0.005 |
Neg logit contributions | |
kiss | -0.006 |
welcome | -0.005 |
helper | -0.005 |
bless | -0.005 |
eye | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
kiss | +0.089 |
eye | +0.080 |
bisc | +0.078 |
bye | +0.078 |
welcome | +0.077 |
Neg logit contributions | |
ts | -0.096 |
opes | -0.089 |
viol | -0.086 |
ivating | -0.086 |
webs | -0.086 |
Token | even |
Token ID | 772 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
ts | +0.018 |
opes | +0.018 |
ants | +0.018 |
ivating | +0.018 |
od | +0.018 |
Neg logit contributions | |
kiss | -0.016 |
welcome | -0.014 |
helper | -0.014 |
payoff | -0.013 |
bless | -0.013 |
Token | our |
Token ID | 674 |
Feature activation | -4.07e-03 |
Pos logit contributions | |
kiss | +0.047 |
welcome | +0.043 |
bye | +0.041 |
ma | +0.041 |
payoff | +0.041 |
Neg logit contributions | |
ts | -0.052 |
opes | -0.051 |
ivating | -0.050 |
ants | -0.050 |
like | -0.050 |
Token | dreams |
Token ID | 10625 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
opes | +0.007 |
ts | +0.007 |
targets | +0.007 |
viol | +0.007 |
webs | +0.007 |
Neg logit contributions | |
kiss | -0.005 |
welcome | -0.005 |
ma | -0.004 |
payoff | -0.004 |
bless | -0.004 |
Token | can |
Token ID | 460 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
kiss | +0.080 |
helper | +0.077 |
welcome | +0.073 |
girl | +0.073 |
payoff | +0.073 |
Neg logit contributions | |
ts | -0.109 |
opes | -0.100 |
tered | -0.100 |
like | -0.097 |
ivating | -0.095 |
Token | have |
Token ID | 423 |
Feature activation | -9.55e-03 |
Pos logit contributions | |
kiss | +0.017 |
welcome | +0.016 |
helper | +0.015 |
eye | +0.014 |
girl | +0.014 |
Neg logit contributions | |
ts | -0.027 |
opes | -0.027 |
ivating | -0.026 |
ants | -0.026 |
od | -0.026 |
Token | sad |
Token ID | 6507 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
ts | +0.015 |
opes | +0.015 |
tered | +0.014 |
like | +0.014 |
od | +0.014 |
Neg logit contributions | |
kiss | -0.014 |
helper | -0.012 |
welcome | -0.012 |
eye | -0.012 |
ma | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -6.82e-03 |
Pos logit contributions | |
ts | +0.041 |
opes | +0.040 |
ants | +0.040 |
ivating | +0.040 |
od | +0.039 |
Neg logit contributions | |
kiss | -0.021 |
payoff | -0.018 |
welcome | -0.018 |
helper | -0.018 |
bye | -0.017 |
Token | Sam |
Token ID | 3409 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
opes | +0.011 |
ts | +0.011 |
ants | +0.011 |
ivating | +0.011 |
od | +0.011 |
Neg logit contributions | |
kiss | -0.009 |
welcome | -0.008 |
helper | -0.008 |
bless | -0.008 |
luck | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -7.91e-03 |
Pos logit contributions | |
ts | +0.042 |
opes | +0.042 |
tered | +0.041 |
od | +0.040 |
ants | +0.040 |
Neg logit contributions | |
kiss | -0.033 |
welcome | -0.032 |
luck | -0.030 |
bless | -0.029 |
payoff | -0.029 |
Token | growing |
Token ID | 3957 |
Feature activation | +9.46e-03 |
Pos logit contributions | |
opes | +0.012 |
ts | +0.012 |
ants | +0.012 |
ivating | +0.012 |
od | +0.012 |
Neg logit contributions | |
kiss | -0.012 |
welcome | -0.011 |
helper | -0.010 |
payoff | -0.010 |
luck | -0.010 |
Token | up |
Token ID | 510 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
kiss | +0.015 |
payoff | +0.014 |
bless | +0.014 |
bye | +0.013 |
welcome | +0.013 |
Neg logit contributions | |
ts | -0.013 |
ivating | -0.013 |
ants | -0.013 |
opes | -0.013 |
like | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +5.37e-03 |
Pos logit contributions | |
ts | +0.057 |
opes | +0.056 |
ivating | +0.056 |
ants | +0.055 |
tered | +0.055 |
Neg logit contributions | |
kiss | -0.044 |
welcome | -0.040 |
helper | -0.038 |
bless | -0.038 |
payoff | -0.038 |
Token | would |
Token ID | 561 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
kiss | +0.007 |
welcome | +0.007 |
eye | +0.007 |
helper | +0.006 |
bye | +0.006 |
Neg logit contributions | |
ts | -0.009 |
opes | -0.008 |
od | -0.008 |
ivating | -0.008 |
like | -0.008 |
Token | be |
Token ID | 307 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
kiss | +0.005 |
helper | +0.005 |
welcome | +0.005 |
girl | +0.005 |
luck | +0.005 |
Neg logit contributions | |
ts | -0.005 |
opes | -0.005 |
ivating | -0.005 |
tered | -0.005 |
ination | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -4.82e-03 |
Pos logit contributions | |
kiss | +0.037 |
bye | +0.034 |
prayer | +0.033 |
eye | +0.032 |
shines | +0.032 |
Neg logit contributions | |
ts | -0.040 |
od | -0.037 |
nam | -0.037 |
like | -0.037 |
ivating | -0.037 |
Token | kind |
Token ID | 1611 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
tant | +0.006 |
ination | +0.006 |
scoring | +0.006 |
viol | +0.006 |
amus | +0.006 |
Neg logit contributions | |
shines | -0.007 |
kiss | -0.007 |
ma | -0.007 |
ment | -0.006 |
bye | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -5.02e-03 |
Pos logit contributions | |
shines | +0.058 |
use | +0.055 |
kiss | +0.052 |
ma | +0.050 |
payoff | +0.050 |
Neg logit contributions | |
od | -0.079 |
tered | -0.076 |
tant | -0.074 |
amus | -0.073 |
targets | -0.073 |
Token | to |
Token ID | 284 |
Feature activation | -2.21e-03 |
Pos logit contributions | |
ts | +0.063 |
opes | +0.063 |
ants | +0.062 |
ivating | +0.062 |
od | +0.060 |
Neg logit contributions | |
kiss | -0.044 |
welcome | -0.040 |
helper | -0.038 |
payoff | -0.038 |
bless | -0.038 |
Token | eat |
Token ID | 4483 |
Feature activation | +4.01e-04 |
Pos logit contributions | |
ts | +0.003 |
like | +0.003 |
targets | +0.003 |
opes | +0.003 |
assed | +0.003 |
Neg logit contributions | |
prayer | -0.003 |
shines | -0.003 |
ma | -0.003 |
luck | -0.003 |
girl | -0.003 |
Token | blue |
Token ID | 4171 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
kiss | +0.001 |
welcome | +0.001 |
bless | +0.001 |
helper | +0.001 |
payoff | +0.001 |
Neg logit contributions | |
ts | -0.001 |
opes | -0.001 |
ants | -0.001 |
ivating | -0.001 |
tered | -0.001 |
Token | berries |
Token ID | 20853 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
opes | +0.019 |
ts | +0.019 |
ivating | +0.018 |
ants | +0.018 |
like | +0.018 |
Neg logit contributions | |
welcome | -0.013 |
kiss | -0.013 |
payoff | -0.012 |
prayer | -0.012 |
bless | -0.012 |
Token | together |
Token ID | 1978 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
ts | +0.050 |
ivating | +0.050 |
tered | +0.050 |
ants | +0.049 |
like | +0.049 |
Neg logit contributions | |
kiss | -0.036 |
welcome | -0.033 |
bless | -0.032 |
payoff | -0.031 |
prayer | -0.031 |
Token | again |
Token ID | 757 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
ts | +0.059 |
tered | +0.059 |
opes | +0.058 |
od | +0.058 |
ivating | +0.058 |
Neg logit contributions | |
kiss | -0.025 |
welcome | -0.022 |
bless | -0.021 |
helper | -0.020 |
shines | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.98e-03 |
Pos logit contributions | |
kiss | +0.014 |
welcome | +0.012 |
shines | +0.012 |
bless | +0.012 |
payoff | +0.011 |
Neg logit contributions | |
ts | -0.029 |
opes | -0.028 |
od | -0.028 |
ants | -0.028 |
tered | -0.027 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.30e-03 |
Pos logit contributions | |
ts | +0.004 |
opes | +0.004 |
ants | +0.004 |
ivating | +0.004 |
od | +0.004 |
Neg logit contributions | |
kiss | -0.002 |
welcome | -0.002 |
thanks | -0.002 |
payoff | -0.002 |
girl | -0.002 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.42e-03 |
Pos logit contributions | |
kiss | +0.007 |
welcome | +0.007 |
thanks | +0.006 |
? | +0.006 |
payoff | +0.006 |
Neg logit contributions | |
opes | -0.015 |
ants | -0.015 |
ts | -0.015 |
ivating | -0.014 |
od | -0.014 |
Token | upon |
Token ID | 2402 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
opes | +0.004 |
ts | +0.004 |
ivating | +0.004 |
ants | +0.004 |
tered | +0.004 |
Neg logit contributions | |
kiss | -0.004 |
welcome | -0.003 |
helper | -0.003 |
bless | -0.003 |
luck | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
ants | +0.096 |
opes | +0.094 |
issors | +0.091 |
ivating | +0.090 |
amus | +0.089 |
Neg logit contributions | |
kiss | -0.048 |
welcome | -0.043 |
? | -0.041 |
, | -0.039 |
girl | -0.039 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
ivating | +0.011 |
ants | +0.011 |
opes | +0.011 |
ts | +0.011 |
amus | +0.011 |
Neg logit contributions | |
kiss | -0.007 |
, | -0.007 |
welcome | -0.007 |
girl | -0.007 |
ma | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
ants | +0.056 |
ivating | +0.056 |
opes | +0.056 |
tered | +0.055 |
od | +0.053 |
Neg logit contributions | |
kiss | -0.035 |
welcome | -0.033 |
thanks | -0.031 |
wave | -0.031 |
helper | -0.031 |
Token | slide |
Token ID | 10649 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
ts | +0.023 |
opes | +0.022 |
like | +0.021 |
ivating | +0.021 |
ants | +0.021 |
Neg logit contributions | |
kiss | -0.016 |
payoff | -0.015 |
bless | -0.015 |
helper | -0.015 |
luck | -0.015 |
Token | down |
Token ID | 866 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
kiss | +0.019 |
welcome | +0.017 |
bless | +0.017 |
payoff | +0.017 |
helper | +0.016 |
Neg logit contributions | |
ts | -0.025 |
opes | -0.024 |
ants | -0.024 |
ivating | -0.024 |
like | -0.024 |
Token | it |
Token ID | 340 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
ts | +0.056 |
ivating | +0.055 |
opes | +0.055 |
ants | +0.054 |
like | +0.054 |
Neg logit contributions | |
kiss | -0.048 |
welcome | -0.043 |
bless | -0.042 |
helper | -0.042 |
luck | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +6.85e-03 |
Pos logit contributions | |
opes | +0.064 |
ts | +0.064 |
ants | +0.063 |
ivating | +0.063 |
od | +0.062 |
Neg logit contributions | |
kiss | -0.024 |
welcome | -0.020 |
helper | -0.018 |
payoff | -0.018 |
luck | -0.018 |
Token | She |
Token ID | 1375 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
kiss | +0.008 |
welcome | +0.007 |
helper | +0.007 |
girl | +0.007 |
thanks | +0.007 |
Neg logit contributions | |
ts | -0.013 |
opes | -0.013 |
ants | -0.012 |
ivating | -0.012 |
od | -0.012 |
Token | climbed |
Token ID | 19952 |
Feature activation | -7.38e-03 |
Pos logit contributions | |
kiss | +0.018 |
wave | +0.016 |
girl | +0.015 |
welcome | +0.015 |
thanks | +0.015 |
Neg logit contributions | |
ivating | -0.029 |
ants | -0.029 |
opes | -0.029 |
ts | -0.028 |
od | -0.028 |
Token | up |
Token ID | 510 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
opes | +0.011 |
ts | +0.011 |
ants | +0.011 |
ivating | +0.011 |
od | +0.011 |
Neg logit contributions | |
kiss | -0.011 |
welcome | -0.010 |
luck | -0.010 |
thanks | -0.010 |
helper | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
ts | +0.056 |
opes | +0.056 |
ants | +0.055 |
ivating | +0.055 |
od | +0.054 |
Neg logit contributions | |
kiss | -0.043 |
welcome | -0.040 |
helper | -0.038 |
bless | -0.037 |
payoff | -0.037 |
Token | stairs |
Token ID | 16046 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
kiss | +0.047 |
welcome | +0.042 |
bless | +0.041 |
helper | +0.041 |
payoff | +0.040 |
Neg logit contributions | |
ts | -0.069 |
opes | -0.068 |
ivating | -0.067 |
ants | -0.067 |
like | -0.066 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.36e-03 |
Pos logit contributions | |
ts | +0.009 |
opes | +0.009 |
ants | +0.009 |
ivating | +0.009 |
od | +0.009 |
Neg logit contributions | |
kiss | -0.006 |
welcome | -0.005 |
thanks | -0.005 |
helper | -0.005 |
bless | -0.005 |
Token | Once |
Token ID | 7454 |
Feature activation | -4.05e-03 |
Pos logit contributions | |
kiss | +0.008 |
welcome | +0.007 |
thanks | +0.006 |
payoff | +0.006 |
? | +0.006 |
Neg logit contributions | |
opes | -0.015 |
ts | -0.015 |
ants | -0.015 |
ivating | -0.014 |
od | -0.014 |
Token | upon |
Token ID | 2402 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
opes | +0.006 |
ts | +0.006 |
ivating | +0.006 |
ants | +0.006 |
tered | +0.006 |
Neg logit contributions | |
kiss | -0.006 |
welcome | -0.006 |
ma | -0.006 |
helper | -0.005 |
girl | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
ants | +0.101 |
opes | +0.100 |
issors | +0.098 |
amus | +0.095 |
ivating | +0.095 |
Neg logit contributions | |
kiss | -0.050 |
welcome | -0.045 |
? | -0.042 |
girl | -0.040 |
, | -0.040 |
Token | time |
Token ID | 640 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
kiss | +0.028 |
welcome | +0.026 |
helper | +0.024 |
payoff | +0.024 |
bless | +0.024 |
Neg logit contributions | |
ts | -0.034 |
opes | -0.034 |
ants | -0.033 |
ivating | -0.033 |
od | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
kiss | +0.020 |
welcome | +0.012 |
helper | +0.010 |
payoff | +0.010 |
bless | +0.010 |
Neg logit contributions | |
ts | -0.145 |
opes | -0.145 |
ants | -0.144 |
ivating | -0.143 |
od | -0.142 |
Token | there |
Token ID | 612 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
welcome | +0.012 |
, | +0.012 |
girl | +0.011 |
kiss | +0.011 |
? | +0.010 |
Neg logit contributions | |
opes | -0.033 |
ants | -0.032 |
targets | -0.032 |
ts | -0.031 |
amus | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
opes | +0.040 |
ts | +0.040 |
ants | +0.040 |
ivating | +0.039 |
od | +0.038 |
Neg logit contributions | |
kiss | -0.020 |
welcome | -0.018 |
helper | -0.016 |
thanks | -0.016 |
payoff | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +7.42e-03 |
Pos logit contributions | |
welcome | +0.015 |
kiss | +0.015 |
, | +0.013 |
girl | +0.013 |
surprise | +0.013 |
Neg logit contributions | |
ants | -0.034 |
ts | -0.034 |
opes | -0.034 |
aned | -0.033 |
assed | -0.033 |
Token | little |
Token ID | 1310 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
kiss | +0.010 |
welcome | +0.009 |
payoff | +0.009 |
luck | +0.009 |
thanks | +0.008 |
Neg logit contributions | |
ts | -0.012 |
opes | -0.012 |
ivating | -0.012 |
ants | -0.012 |
od | -0.012 |
Token | girl |
Token ID | 2576 |
Feature activation | -6.83e-03 |
Pos logit contributions | |
payoff | +0.022 |
kiss | +0.020 |
repay | +0.019 |
luck | +0.019 |
thanks | +0.019 |
Neg logit contributions | |
ts | -0.043 |
tant | -0.042 |
nam | -0.042 |
ivating | -0.042 |
viol | -0.041 |
Token | could |
Token ID | 714 |
Feature activation | +7.21e-04 |
Pos logit contributions | |
kiss | +0.001 |
welcome | +0.001 |
payoff | +0.001 |
service | +0.001 |
helper | +0.001 |
Neg logit contributions | |
ts | -0.001 |
opes | -0.001 |
tered | -0.001 |
od | -0.001 |
like | -0.001 |
Token | go |
Token ID | 467 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
kiss | +0.001 |
payoff | +0.001 |
welcome | +0.001 |
girl | +0.001 |
bye | +0.001 |
Neg logit contributions | |
ts | -0.001 |
opes | -0.001 |
od | -0.001 |
ivating | -0.001 |
ants | -0.001 |
Token | anywhere |
Token ID | 6609 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
kiss | +0.079 |
prayer | +0.078 |
payoff | +0.074 |
bless | +0.073 |
bye | +0.071 |
Neg logit contributions | |
ts | -0.067 |
targets | -0.064 |
assed | -0.064 |
ag | -0.062 |
like | -0.062 |
Token | she |
Token ID | 673 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
ts | +0.164 |
od | +0.154 |
ggies | +0.153 |
ivating | +0.153 |
tered | +0.151 |
Neg logit contributions | |
kiss | -0.105 |
prayer | -0.094 |
eye | -0.092 |
welcome | -0.091 |
bye | -0.088 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ts | +0.043 |
od | +0.040 |
tered | +0.039 |
opes | +0.039 |
targets | +0.039 |
Neg logit contributions | |
kiss | -0.044 |
welcome | -0.041 |
prayer | -0.039 |
bless | -0.039 |
payoff | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -4.36e-03 |
Pos logit contributions | |
od | +0.024 |
tered | +0.024 |
like | +0.024 |
ts | +0.024 |
opes | +0.023 |
Neg logit contributions | |
kiss | -0.015 |
bless | -0.013 |
payoff | -0.013 |
helper | -0.013 |
wave | -0.013 |
Token | stay |
Token ID | 2652 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
ts | +0.007 |
opes | +0.006 |
like | +0.006 |
od | +0.006 |
targets | +0.006 |
Neg logit contributions | |
kiss | -0.006 |
ara | -0.005 |
bye | -0.005 |
helper | -0.005 |
welcome | -0.005 |
Token | safe |
Token ID | 3338 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
kiss | +0.034 |
bye | +0.033 |
payoff | +0.033 |
prayer | +0.033 |
bless | +0.031 |
Neg logit contributions | |
ts | -0.029 |
tered | -0.025 |
nam | -0.025 |
opes | -0.025 |
ination | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +8.04e-04 |
Pos logit contributions | |
kiss | +0.014 |
bless | +0.012 |
welcome | +0.012 |
payoff | +0.011 |
prayer | +0.011 |
Neg logit contributions | |
ts | -0.019 |
tered | -0.019 |
opes | -0.018 |
od | -0.018 |
ivating | -0.018 |
Token | She |
Token ID | 1375 |
Feature activation | +8.94e-03 |
Pos logit contributions | |
kiss | +0.001 |
welcome | +0.001 |
wave | +0.001 |
luck | +0.001 |
payoff | +0.001 |
Neg logit contributions | |
opes | -0.001 |
ants | -0.001 |
tered | -0.001 |
od | -0.001 |
ivating | -0.001 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
kiss | +0.012 |
welcome | +0.012 |
bless | +0.011 |
payoff | +0.011 |
helper | +0.011 |
Neg logit contributions | |
ts | -0.015 |
opes | -0.014 |
tered | -0.014 |
od | -0.014 |
ants | -0.013 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
kiss | +0.004 |
welcome | +0.004 |
wave | +0.004 |
thanks | +0.004 |
girl | +0.004 |
Neg logit contributions | |
opes | -0.007 |
ivating | -0.007 |
ants | -0.007 |
ts | -0.007 |
issors | -0.007 |
Token | John |
Token ID | 1757 |
Feature activation | -9.52e-03 |
Pos logit contributions | |
kiss | +0.044 |
welcome | +0.041 |
luck | +0.038 |
thanks | +0.038 |
helper | +0.037 |
Neg logit contributions | |
opes | -0.058 |
ts | -0.057 |
ivating | -0.057 |
ants | -0.056 |
like | -0.054 |
Token | what |
Token ID | 644 |
Feature activation | -8.94e-03 |
Pos logit contributions | |
ants | +0.016 |
od | +0.016 |
ts | +0.016 |
opes | +0.015 |
like | +0.015 |
Neg logit contributions | |
kiss | -0.012 |
payoff | -0.011 |
welcome | -0.011 |
bye | -0.011 |
helper | -0.011 |
Token | happened |
Token ID | 3022 |
Feature activation | -8.68e-03 |
Pos logit contributions | |
ts | +0.014 |
od | +0.014 |
opes | +0.014 |
like | +0.014 |
ants | +0.014 |
Neg logit contributions | |
kiss | -0.013 |
welcome | -0.011 |
helper | -0.011 |
eye | -0.011 |
bless | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
od | +0.018 |
opes | +0.018 |
ants | +0.017 |
ts | +0.017 |
like | +0.017 |
Neg logit contributions | |
kiss | -0.009 |
bless | -0.007 |
payoff | -0.007 |
helper | -0.007 |
welcome | -0.007 |
Token | |
Token ID | 220 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
ts | +0.020 |
opes | +0.020 |
ants | +0.020 |
ivating | +0.019 |
od | +0.019 |
Neg logit contributions | |
kiss | -0.016 |
welcome | -0.015 |
helper | -0.014 |
payoff | -0.014 |
bless | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +5.92e-03 |
Pos logit contributions | |
ts | +0.097 |
opes | +0.093 |
ivating | +0.092 |
tered | +0.090 |
viol | +0.090 |
Neg logit contributions | |
kiss | -0.037 |
welcome | -0.036 |
? | -0.032 |
ma | -0.031 |
, | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
kiss | +0.007 |
welcome | +0.006 |
ma | +0.006 |
? | +0.006 |
, | +0.006 |
Neg logit contributions | |
ts | -0.012 |
opes | -0.011 |
ivating | -0.011 |
ants | -0.011 |
targets | -0.011 |
Token | John |
Token ID | 7554 |
Feature activation | -6.80e-03 |
Pos logit contributions | |
kiss | +0.025 |
welcome | +0.023 |
ma | +0.022 |
payoff | +0.022 |
bless | +0.022 |
Neg logit contributions | |
ts | -0.026 |
opes | -0.025 |
ivating | -0.025 |
ants | -0.025 |
od | -0.024 |
Token | pointed |
Token ID | 6235 |
Feature activation | +7.87e-03 |
Pos logit contributions | |
opes | +0.012 |
ts | +0.012 |
ants | +0.012 |
od | +0.012 |
tered | +0.012 |
Neg logit contributions | |
kiss | -0.008 |
welcome | -0.007 |
luck | -0.007 |
helper | -0.007 |
payoff | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
kiss | +0.012 |
payoff | +0.011 |
helper | +0.011 |
bless | +0.011 |
welcome | +0.011 |
Neg logit contributions | |
like | -0.011 |
ants | -0.011 |
opes | -0.011 |
ivating | -0.011 |
od | -0.011 |
Token | actus |
Token ID | 34144 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
kiss | +0.024 |
eye | +0.021 |
bless | +0.020 |
welcome | +0.020 |
girl | +0.020 |
Neg logit contributions | |
ts | -0.039 |
ivating | -0.039 |
opes | -0.038 |
ants | -0.038 |
nam | -0.038 |
Token | had |
Token ID | 550 |
Feature activation | -5.26e-03 |
Pos logit contributions | |
opes | +0.064 |
ts | +0.064 |
ants | +0.063 |
ivating | +0.063 |
od | +0.062 |
Neg logit contributions | |
kiss | -0.037 |
welcome | -0.032 |
thanks | -0.030 |
helper | -0.030 |
bless | -0.030 |
Token | poked |
Token ID | 47320 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
opes | +0.008 |
ts | +0.008 |
ants | +0.008 |
ivating | +0.008 |
od | +0.008 |
Neg logit contributions | |
kiss | -0.008 |
welcome | -0.007 |
helper | -0.007 |
payoff | -0.007 |
luck | -0.007 |
Token | him |
Token ID | 683 |
Feature activation | -7.80e-03 |
Pos logit contributions | |
ivating | +0.049 |
ts | +0.049 |
opes | +0.049 |
ants | +0.048 |
ptions | +0.047 |
Neg logit contributions | |
kiss | -0.031 |
welcome | -0.030 |
, | -0.029 |
thanks | -0.028 |
girl | -0.028 |
Token | with |
Token ID | 351 |
Feature activation | -8.56e-03 |
Pos logit contributions | |
opes | +0.015 |
ts | +0.015 |
ivating | +0.015 |
ants | +0.015 |
ptions | +0.015 |
Neg logit contributions | |
kiss | -0.008 |
, | -0.008 |
welcome | -0.007 |
promise | -0.007 |
eye | -0.007 |
Token | its |
Token ID | 663 |
Feature activation | -6.98e-03 |
Pos logit contributions | |
ts | +0.012 |
opes | +0.012 |
ivating | +0.012 |
ants | +0.012 |
tered | +0.012 |
Neg logit contributions | |
kiss | -0.013 |
welcome | -0.012 |
helper | -0.012 |
payoff | -0.012 |
bless | -0.012 |
Token | needles |
Token ID | 25209 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
opes | +0.010 |
ts | +0.010 |
ants | +0.010 |
like | +0.009 |
tered | +0.009 |
Neg logit contributions | |
kiss | -0.011 |
welcome | -0.010 |
payoff | -0.010 |
helper | -0.010 |
bless | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -5.05e-03 |
Pos logit contributions | |
kiss | +0.013 |
welcome | +0.011 |
helper | +0.011 |
payoff | +0.011 |
bless | +0.011 |
Neg logit contributions | |
ts | -0.028 |
opes | -0.028 |
ants | -0.027 |
ivating | -0.027 |
like | -0.027 |
Token | It |
Token ID | 632 |
Feature activation | -5.77e-03 |
Pos logit contributions | |
ts | +0.009 |
opes | +0.009 |
ants | +0.009 |
ivating | +0.009 |
like | +0.009 |
Neg logit contributions | |
kiss | -0.006 |
welcome | -0.006 |
thanks | -0.005 |
? | -0.005 |
helper | -0.005 |
Token | hurt |
Token ID | 5938 |
Feature activation | -4.17e-03 |
Pos logit contributions | |
opes | +0.011 |
ants | +0.011 |
ts | +0.011 |
ivating | +0.011 |
od | +0.010 |
Neg logit contributions | |
kiss | -0.007 |
welcome | -0.006 |
thanks | -0.006 |
helper | -0.006 |
payoff | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
ts | +0.006 |
opes | +0.006 |
ants | +0.006 |
ivating | +0.006 |
od | +0.006 |
Neg logit contributions | |
kiss | -0.006 |
welcome | -0.006 |
helper | -0.006 |
payoff | -0.006 |
bless | -0.006 |
Token | play |
Token ID | 711 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
kiss | +0.004 |
payoff | +0.004 |
shines | +0.004 |
luck | +0.004 |
thanks | +0.004 |
Neg logit contributions | |
ts | -0.006 |
tered | -0.006 |
ivating | -0.006 |
opes | -0.006 |
od | -0.006 |
Token | with |
Token ID | 351 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
ants | +0.023 |
opes | +0.022 |
like | +0.021 |
issors | +0.021 |
ptions | +0.021 |
Neg logit contributions | |
, | -0.011 |
? | -0.011 |
welcome | -0.010 |
kiss | -0.010 |
surprise | -0.009 |
Token | other |
Token ID | 584 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
ivating | +0.033 |
ants | +0.033 |
opes | +0.033 |
od | +0.032 |
tered | +0.032 |
Neg logit contributions | |
kiss | -0.030 |
welcome | -0.028 |
luck | -0.026 |
thanks | -0.026 |
helper | -0.026 |
Token | kids |
Token ID | 3988 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
kiss | +0.024 |
payoff | +0.022 |
welcome | +0.022 |
bless | +0.022 |
bye | +0.021 |
Neg logit contributions | |
ts | -0.027 |
opes | -0.026 |
od | -0.025 |
ants | -0.025 |
viol | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
opes | +0.036 |
ts | +0.036 |
ants | +0.036 |
ivating | +0.036 |
od | +0.035 |
Neg logit contributions | |
kiss | -0.013 |
welcome | -0.011 |
helper | -0.010 |
luck | -0.010 |
bless | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
ts | +0.005 |
opes | +0.005 |
ants | +0.005 |
ivating | +0.005 |
od | +0.005 |
Neg logit contributions | |
kiss | -0.004 |
welcome | -0.003 |
helper | -0.003 |
payoff | -0.003 |
bless | -0.003 |
Token | always |
Token ID | 1464 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
ants | +0.004 |
opes | +0.004 |
ts | +0.004 |
ivating | +0.004 |
issors | +0.004 |
Neg logit contributions | |
kiss | -0.004 |
welcome | -0.004 |
helper | -0.003 |
thanks | -0.003 |
, | -0.003 |
Token | angry |
Token ID | 7954 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
kiss | +0.073 |
welcome | +0.066 |
bless | +0.065 |
payoff | +0.064 |
helper | +0.064 |
Neg logit contributions | |
ts | -0.057 |
opes | -0.055 |
ivating | -0.054 |
ants | -0.053 |
od | -0.053 |
Token | when |
Token ID | 618 |
Feature activation | +9.06e-03 |
Pos logit contributions | |
opes | +0.056 |
ts | +0.055 |
od | +0.054 |
ants | +0.054 |
ivating | +0.053 |
Neg logit contributions | |
kiss | -0.035 |
welcome | -0.031 |
payoff | -0.030 |
bless | -0.030 |
promise | -0.029 |
Token | his |
Token ID | 465 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
kiss | +0.011 |
welcome | +0.010 |
helper | +0.009 |
bless | +0.009 |
payoff | +0.009 |
Neg logit contributions | |
ts | -0.017 |
opes | -0.017 |
ants | -0.016 |
ivating | -0.016 |
od | -0.016 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
kiss | +0.022 |
payoff | +0.020 |
bless | +0.020 |
welcome | +0.019 |
thanks | +0.019 |
Neg logit contributions | |
opes | -0.035 |
ts | -0.034 |
ggies | -0.033 |
ants | -0.033 |
od | -0.033 |
Token | hoop |
Token ID | 44792 |
Feature activation | -8.06e-03 |
Pos logit contributions | |
kiss | +0.039 |
welcome | +0.036 |
payoff | +0.035 |
bye | +0.034 |
bless | +0.034 |
Neg logit contributions | |
opes | -0.063 |
ts | -0.062 |
ants | -0.060 |
like | -0.059 |
ivating | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
opes | +0.016 |
ts | +0.015 |
tered | +0.015 |
targets | +0.015 |
ants | +0.015 |
Neg logit contributions | |
kiss | -0.008 |
welcome | -0.008 |
bless | -0.008 |
payoff | -0.007 |
prayer | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
kiss | +0.003 |
welcome | +0.002 |
girl | +0.002 |
thanks | +0.002 |
helper | +0.002 |
Neg logit contributions | |
ts | -0.004 |
opes | -0.004 |
ants | -0.004 |
ivating | -0.004 |
od | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +7.19e-04 |
Pos logit contributions | |
kiss | +0.029 |
welcome | +0.026 |
helper | +0.025 |
thanks | +0.025 |
bless | +0.024 |
Neg logit contributions | |
opes | -0.042 |
ts | -0.042 |
ants | -0.041 |
ivating | -0.041 |
od | -0.040 |
Token | very |
Token ID | 845 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
welcome | +0.001 |
kiss | +0.001 |
thanks | +0.001 |
helper | +0.001 |
left | +0.001 |
Neg logit contributions | |
ants | -0.001 |
opes | -0.001 |
targets | -0.001 |
ts | -0.001 |
tant | -0.001 |
Token | competitive |
Token ID | 7606 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
ts | +0.049 |
opes | +0.048 |
ivating | +0.048 |
ants | +0.048 |
like | +0.046 |
Neg logit contributions | |
kiss | -0.050 |
welcome | -0.045 |
payoff | -0.045 |
bless | -0.044 |
helper | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
ts | +0.078 |
opes | +0.077 |
od | +0.076 |
ivating | +0.076 |
targets | +0.075 |
Neg logit contributions | |
kiss | -0.052 |
bless | -0.046 |
welcome | -0.043 |
payoff | -0.042 |
prayer | -0.042 |
Token | she |
Token ID | 673 |
Feature activation | +6.56e-03 |
Pos logit contributions | |
opes | +0.035 |
ants | +0.034 |
ts | +0.033 |
ivating | +0.033 |
od | +0.033 |
Neg logit contributions | |
kiss | -0.025 |
welcome | -0.023 |
thanks | -0.022 |
girl | -0.021 |
helper | -0.021 |
Token | always |
Token ID | 1464 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
kiss | +0.008 |
welcome | +0.007 |
wave | +0.007 |
helper | +0.007 |
girl | +0.007 |
Neg logit contributions | |
ants | -0.012 |
opes | -0.012 |
ivating | -0.012 |
ts | -0.012 |
amus | -0.011 |
Token | wanted |
Token ID | 2227 |
Feature activation | -7.53e-03 |
Pos logit contributions | |
kiss | +0.037 |
eye | +0.033 |
bless | +0.033 |
helper | +0.032 |
welcome | +0.032 |
Neg logit contributions | |
ts | -0.036 |
opes | -0.034 |
tered | -0.033 |
assed | -0.032 |
od | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
ts | +0.014 |
opes | +0.013 |
ants | +0.013 |
ivating | +0.013 |
od | +0.013 |
Neg logit contributions | |
kiss | -0.009 |
welcome | -0.008 |
helper | -0.008 |
payoff | -0.008 |
bless | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.76e-03 |
Pos logit contributions | |
opes | +0.087 |
ants | +0.086 |
ivating | +0.086 |
ination | +0.084 |
ts | +0.084 |
Neg logit contributions | |
, | -0.015 |
kiss | -0.014 |
welcome | -0.011 |
wave | -0.010 |
luck | -0.010 |
Token | But |
Token ID | 887 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
ts | +0.006 |
ants | +0.005 |
opes | +0.005 |
fters | +0.005 |
od | +0.005 |
Neg logit contributions | |
kiss | -0.003 |
girl | -0.003 |
thanks | -0.003 |
welcome | -0.003 |
helper | -0.003 |
Token | then |
Token ID | 788 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
kiss | +0.035 |
welcome | +0.031 |
helper | +0.030 |
payoff | +0.030 |
girl | +0.030 |
Neg logit contributions | |
opes | -0.060 |
ts | -0.059 |
ants | -0.058 |
ivating | -0.058 |
od | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e-03 |
Pos logit contributions | |
kiss | +0.059 |
welcome | +0.054 |
bless | +0.050 |
eye | +0.049 |
payoff | +0.048 |
Neg logit contributions | |
ts | -0.106 |
opes | -0.103 |
od | -0.102 |
ants | -0.102 |
tered | -0.101 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.90e-03 |
Pos logit contributions | |
opes | +0.002 |
ants | +0.002 |
ivating | +0.002 |
ts | +0.002 |
ination | +0.002 |
Neg logit contributions | |
kiss | -0.001 |
girl | -0.001 |
helper | -0.001 |
welcome | -0.001 |
, | -0.001 |
Token | accidentally |
Token ID | 14716 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
opes | +0.003 |
ts | +0.003 |
ants | +0.003 |
ivating | +0.003 |
od | +0.003 |
Neg logit contributions | |
kiss | -0.002 |
welcome | -0.002 |
bless | -0.002 |
payoff | -0.002 |
helper | -0.002 |
Token | stepped |
Token ID | 10764 |
Feature activation | -3.22e-03 |
Pos logit contributions | |
ts | +0.119 |
opes | +0.118 |
ants | +0.116 |
ivating | +0.114 |
od | +0.112 |
Neg logit contributions | |
kiss | -0.140 |
welcome | -0.131 |
helper | -0.125 |
payoff | -0.124 |
bless | -0.124 |
Token | on |
Token ID | 319 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
ts | +0.005 |
ants | +0.005 |
opes | +0.005 |
od | +0.005 |
ination | +0.005 |
Neg logit contributions | |
kiss | -0.004 |
luck | -0.004 |
welcome | -0.004 |
? | -0.004 |
, | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e-03 |
Pos logit contributions | |
ants | +0.105 |
opes | +0.102 |
anned | +0.102 |
ving | +0.102 |
oving | +0.100 |
Neg logit contributions | |
kiss | -0.050 |
, | -0.048 |
surprise | -0.044 |
ma | -0.041 |
lady | -0.040 |
Token | wrong |
Token ID | 2642 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
opes | +0.003 |
ants | +0.003 |
ts | +0.003 |
ivating | +0.003 |
od | +0.003 |
Neg logit contributions | |
kiss | -0.002 |
welcome | -0.002 |
girl | -0.002 |
helper | -0.002 |
wave | -0.002 |
Token | square |
Token ID | 6616 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
ts | +0.057 |
opes | +0.057 |
ants | +0.055 |
od | +0.055 |
ivating | +0.054 |
Neg logit contributions | |
kiss | -0.041 |
welcome | -0.038 |
bless | -0.037 |
thanks | -0.036 |
helper | -0.036 |
Token | they |
Token ID | 484 |
Feature activation | -4.79e-03 |
Pos logit contributions | |
opes | +0.007 |
ts | +0.007 |
ants | +0.007 |
ivating | +0.007 |
od | +0.007 |
Neg logit contributions | |
kiss | -0.004 |
welcome | -0.004 |
helper | -0.003 |
payoff | -0.003 |
thanks | -0.003 |
Token | all |
Token ID | 477 |
Feature activation | +7.88e-03 |
Pos logit contributions | |
ivating | +0.006 |
ants | +0.006 |
opes | +0.006 |
like | +0.006 |
ts | +0.006 |
Neg logit contributions | |
kiss | -0.009 |
wave | -0.008 |
welcome | -0.008 |
thanks | -0.008 |
, | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
kiss | +0.011 |
welcome | +0.010 |
helper | +0.010 |
payoff | +0.010 |
bless | +0.010 |
Neg logit contributions | |
ts | -0.013 |
opes | -0.013 |
ants | -0.012 |
ivating | -0.012 |
od | -0.012 |
Token | fun |
Token ID | 1257 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
opes | +0.047 |
ts | +0.047 |
ants | +0.047 |
ivating | +0.046 |
od | +0.045 |
Neg logit contributions | |
kiss | -0.035 |
welcome | -0.032 |
helper | -0.030 |
luck | -0.030 |
payoff | -0.030 |
Token | drum |
Token ID | 13026 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
kiss | +0.023 |
welcome | +0.020 |
luck | +0.019 |
helper | +0.019 |
thanks | +0.019 |
Neg logit contributions | |
opes | -0.040 |
ants | -0.039 |
ivating | -0.039 |
ts | -0.039 |
tered | -0.038 |
Token | ming |
Token ID | 2229 |
Feature activation | -9.94e-02 |
Pos logit contributions | |
ts | +0.099 |
opes | +0.098 |
od | +0.095 |
ants | +0.095 |
ivating | +0.094 |
Neg logit contributions | |
kiss | -0.101 |
welcome | -0.095 |
payoff | -0.090 |
bless | -0.089 |
helper | -0.089 |
Token | together |
Token ID | 1978 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
ivating | +0.217 |
ants | +0.217 |
opes | +0.213 |
ptions | +0.209 |
ts | +0.208 |
Neg logit contributions | |
kiss | -0.088 |
welcome | -0.072 |
, | -0.070 |
luck | -0.069 |
thanks | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-04 |
Pos logit contributions | |
opes | +0.101 |
ts | +0.101 |
ants | +0.100 |
ivating | +0.100 |
like | +0.097 |
Neg logit contributions | |
kiss | -0.021 |
welcome | -0.017 |
luck | -0.014 |
thanks | -0.014 |
helper | -0.014 |
Token | She |
Token ID | 1375 |
Feature activation | +8.44e-03 |
Pos logit contributions | |
kiss | +0.000 |
welcome | +0.000 |
thanks | +0.000 |
girl | +0.000 |
helper | +0.000 |
Neg logit contributions | |
ts | -0.000 |
opes | -0.000 |
ivating | -0.000 |
ants | -0.000 |
assed | -0.000 |
Token | would |
Token ID | 561 |
Feature activation | +3.30e-03 |
Pos logit contributions | |
kiss | +0.011 |
welcome | +0.010 |
helper | +0.009 |
payoff | +0.009 |
bless | +0.009 |
Neg logit contributions | |
ts | -0.015 |
opes | -0.015 |
ants | -0.014 |
ivating | -0.014 |
od | -0.014 |
Token | drum |
Token ID | 13026 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
kiss | +0.004 |
welcome | +0.004 |
wave | +0.004 |
thanks | +0.003 |
bless | +0.003 |
Neg logit contributions | |
ants | -0.006 |
opes | -0.006 |
ts | -0.006 |
ivating | -0.006 |
od | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
kiss | +0.034 |
welcome | +0.031 |
helper | +0.030 |
payoff | +0.029 |
bless | +0.029 |
Neg logit contributions | |
ts | -0.045 |
opes | -0.045 |
ants | -0.044 |
ivating | -0.044 |
od | -0.043 |
Token | his |
Token ID | 465 |
Feature activation | -4.27e-03 |
Pos logit contributions | |
ants | +0.028 |
opes | +0.028 |
ivating | +0.027 |
tered | +0.027 |
od | +0.027 |
Neg logit contributions | |
kiss | -0.016 |
welcome | -0.015 |
surprise | -0.014 |
wave | -0.013 |
return | -0.013 |
Token | room |
Token ID | 2119 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
targets | +0.007 |
opes | +0.007 |
ts | +0.007 |
viol | +0.007 |
amus | +0.007 |
Neg logit contributions | |
kiss | -0.005 |
bless | -0.005 |
welcome | -0.005 |
bye | -0.005 |
shines | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -3.32e-03 |
Pos logit contributions | |
kiss | +0.036 |
welcome | +0.033 |
bless | +0.030 |
luck | +0.030 |
payoff | +0.030 |
Neg logit contributions | |
ts | -0.069 |
opes | -0.069 |
ants | -0.067 |
ivating | -0.067 |
tered | -0.066 |
Token | sul |
Token ID | 33154 |
Feature activation | -6.00e-03 |
Pos logit contributions | |
ts | +0.006 |
opes | +0.006 |
ivating | +0.006 |
ants | +0.006 |
tered | +0.006 |
Neg logit contributions | |
kiss | -0.004 |
welcome | -0.004 |
luck | -0.004 |
bless | -0.004 |
payoff | -0.004 |
Token | ked |
Token ID | 9091 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
ts | +0.004 |
opes | +0.004 |
ivating | +0.004 |
ants | +0.004 |
od | +0.004 |
Neg logit contributions | |
kiss | -0.014 |
welcome | -0.013 |
eye | -0.013 |
luck | -0.013 |
helper | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +5.66e-03 |
Pos logit contributions | |
ivating | +0.190 |
ptions | +0.190 |
ants | +0.188 |
od | +0.187 |
opes | +0.184 |
Neg logit contributions | |
kiss | -0.071 |
, | -0.068 |
luck | -0.065 |
welcome | -0.060 |
thanks | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
kiss | +0.006 |
welcome | +0.006 |
thanks | +0.005 |
helper | +0.005 |
, | +0.005 |
Neg logit contributions | |
ts | -0.012 |
opes | -0.011 |
ivating | -0.011 |
ants | -0.011 |
od | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
, | +0.005 |
kiss | +0.004 |
welcome | +0.004 |
ma | +0.004 |
? | +0.004 |
Neg logit contributions | |
opes | -0.031 |
nam | -0.030 |
ts | -0.030 |
ivating | -0.030 |
ants | -0.029 |
Token | Then |
Token ID | 6423 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
Mom | +0.018 |
next | +0.015 |
distance | +0.015 |
kiss | +0.015 |
return | +0.015 |
Neg logit contributions | |
izards | -0.049 |
ts | -0.049 |
nam | -0.048 |
opes | -0.048 |
od | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
kiss | +0.056 |
bless | +0.048 |
promise | +0.048 |
payoff | +0.047 |
guard | +0.047 |
Neg logit contributions | |
ts | -0.124 |
tered | -0.124 |
opes | -0.119 |
nam | -0.117 |
ggies | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | +8.48e-04 |
Pos logit contributions | |
tered | +0.062 |
ts | +0.061 |
ivating | +0.060 |
like | +0.059 |
od | +0.057 |
Neg logit contributions | |
kiss | -0.089 |
bless | -0.083 |
payoff | -0.080 |
welcome | -0.080 |
service | -0.080 |
Token | But |
Token ID | 887 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
kiss | +0.001 |
welcome | +0.001 |
girl | +0.001 |
, | +0.001 |
thanks | +0.001 |
Neg logit contributions | |
ts | -0.002 |
ants | -0.002 |
opes | -0.002 |
ivating | -0.002 |
od | -0.002 |
Token | then |
Token ID | 788 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
kiss | +0.039 |
welcome | +0.035 |
helper | +0.033 |
bless | +0.032 |
payoff | +0.032 |
Neg logit contributions | |
ts | -0.062 |
opes | -0.062 |
ants | -0.061 |
ivating | -0.061 |
tered | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -6.36e-05 |
Pos logit contributions | |
kiss | +0.044 |
welcome | +0.039 |
bless | +0.037 |
payoff | +0.037 |
distance | +0.037 |
Neg logit contributions | |
ts | -0.126 |
od | -0.122 |
tered | -0.122 |
nam | -0.120 |
opes | -0.120 |
Token | she |
Token ID | 673 |
Feature activation | +4.64e-03 |
Pos logit contributions | |
opes | +0.000 |
ts | +0.000 |
ants | +0.000 |
ivating | +0.000 |
od | +0.000 |
Neg logit contributions | |
kiss | -0.000 |
welcome | -0.000 |
helper | -0.000 |
girl | -0.000 |
luck | -0.000 |
Token | accidentally |
Token ID | 14716 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
kiss | +0.006 |
welcome | +0.006 |
payoff | +0.005 |
bless | +0.005 |
helper | +0.005 |
Neg logit contributions | |
ts | -0.008 |
opes | -0.008 |
ants | -0.008 |
od | -0.007 |
ivating | -0.007 |
Token | dropped |
Token ID | 5710 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
ts | +0.135 |
opes | +0.134 |
ants | +0.131 |
ivating | +0.129 |
od | +0.128 |
Neg logit contributions | |
kiss | -0.125 |
welcome | -0.120 |
helper | -0.112 |
payoff | -0.111 |
bless | -0.110 |
Token | the |
Token ID | 262 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
opes | +0.037 |
ts | +0.037 |
ants | +0.037 |
ivating | +0.036 |
od | +0.035 |
Neg logit contributions | |
kiss | -0.034 |
welcome | -0.031 |
luck | -0.029 |
helper | -0.029 |
payoff | -0.029 |
Token | spoon |
Token ID | 24556 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
kiss | +0.036 |
welcome | +0.034 |
bye | +0.034 |
thanks | +0.032 |
bless | +0.032 |
Neg logit contributions | |
ts | -0.051 |
like | -0.049 |
opes | -0.049 |
ants | -0.049 |
ivating | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
ivating | +0.049 |
ants | +0.049 |
like | +0.049 |
od | +0.049 |
ts | +0.048 |
Neg logit contributions | |
kiss | -0.056 |
welcome | -0.053 |
bless | -0.052 |
payoff | -0.051 |
helper | -0.050 |
Token | it |
Token ID | 340 |
Feature activation | -8.15e-03 |
Pos logit contributions | |
opes | +0.009 |
ts | +0.009 |
ants | +0.008 |
ivating | +0.008 |
od | +0.008 |
Neg logit contributions | |
kiss | -0.008 |
welcome | -0.008 |
helper | -0.007 |
payoff | -0.007 |
bless | -0.007 |
Token | both |
Token ID | 1111 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
ts | +0.020 |
opes | +0.019 |
ants | +0.019 |
ivating | +0.019 |
od | +0.019 |
Neg logit contributions | |
kiss | -0.015 |
welcome | -0.014 |
payoff | -0.013 |
helper | -0.013 |
bless | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
kiss | +0.002 |
helper | +0.002 |
payoff | +0.002 |
bless | +0.002 |
repay | +0.002 |
Neg logit contributions | |
ts | -0.003 |
opes | -0.003 |
like | -0.003 |
od | -0.003 |
tered | -0.003 |
Token | brother |
Token ID | 3956 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
opes | +0.019 |
ts | +0.019 |
ivating | +0.019 |
ants | +0.019 |
tered | +0.019 |
Neg logit contributions | |
kiss | -0.017 |
welcome | -0.015 |
payoff | -0.015 |
helper | -0.015 |
bless | -0.015 |
Token | ! |
Token ID | 0 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
od | +0.055 |
ts | +0.054 |
ants | +0.053 |
tered | +0.053 |
opes | +0.052 |
Neg logit contributions | |
kiss | -0.032 |
eye | -0.030 |
payoff | -0.029 |
shines | -0.029 |
luck | -0.029 |
Token | â |
Token ID | 22940 |
Feature activation | +7.86e-03 |
Pos logit contributions | |
ivating | +0.022 |
ants | +0.022 |
opes | +0.022 |
Whoever | +0.022 |
like | +0.022 |
Neg logit contributions | |
kiss | -0.022 |
luck | -0.021 |
payoff | -0.020 |
helper | -0.020 |
eye | -0.020 |
Token | € |
Token ID | 26391 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
kiss | +0.015 |
helper | +0.014 |
luck | +0.014 |
bless | +0.013 |
surprise | +0.013 |
Neg logit contributions | |
ts | -0.009 |
tered | -0.009 |
ivating | -0.008 |
ination | -0.008 |
opes | -0.008 |
Token | |
Token ID | 220 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
opes | +0.146 |
ts | +0.146 |
ants | +0.143 |
od | +0.142 |
ggies | +0.140 |
Neg logit contributions | |
kiss | -0.113 |
welcome | -0.100 |
luck | -0.099 |
helper | -0.099 |
payoff | -0.098 |
Token |
|
Token ID | 198 |
Feature activation | +4.83e-04 |
Pos logit contributions | |
ts | +0.095 |
opes | +0.093 |
ivating | +0.091 |
ants | +0.090 |
tered | +0.089 |
Neg logit contributions | |
kiss | -0.050 |
welcome | -0.047 |
? | -0.042 |
thanks | -0.041 |
bless | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
kiss | +0.000 |
welcome | +0.000 |
? | +0.000 |
ma | +0.000 |
bless | +0.000 |
Neg logit contributions | |
opes | -0.001 |
ts | -0.001 |
ants | -0.001 |
nam | -0.001 |
ivating | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
kiss | +0.015 |
welcome | +0.014 |
ma | +0.013 |
payoff | +0.013 |
bless | +0.013 |
Neg logit contributions | |
opes | -0.022 |
ts | -0.022 |
ants | -0.020 |
ivating | -0.020 |
targets | -0.020 |
Token | end |
Token ID | 886 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
kiss | +0.027 |
bless | +0.024 |
shines | +0.024 |
welcome | +0.024 |
thanks | +0.023 |
Neg logit contributions | |
ts | -0.047 |
opes | -0.047 |
targets | -0.046 |
viol | -0.046 |
od | -0.046 |