Token | , |
Token ID | 11 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
crib | +0.051 |
Mom | +0.049 |
ara | +0.049 |
beef | +0.040 |
End | +0.040 |
Neg logit contributions | |
vell | -0.124 |
wheel | -0.116 |
inations | -0.113 |
disl | -0.112 |
od | -0.112 |
Token | Anna |
Token ID | 11735 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
crib | +0.040 |
Mom | +0.038 |
ara | +0.037 |
kitten | +0.034 |
beef | +0.033 |
Neg logit contributions | |
vell | -0.094 |
wheel | -0.086 |
inations | -0.084 |
disl | -0.083 |
od | -0.082 |
Token | and |
Token ID | 290 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
crib | +0.083 |
ara | +0.078 |
Mom | +0.076 |
Sunny | +0.068 |
mom | +0.068 |
Neg logit contributions | |
vell | -0.167 |
wheel | -0.157 |
disl | -0.149 |
inations | -0.147 |
od | -0.147 |
Token | Ben |
Token ID | 3932 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
crib | +0.027 |
Mom | +0.025 |
kitten | +0.024 |
ara | +0.024 |
Me | +0.023 |
Neg logit contributions | |
vell | -0.029 |
wheel | -0.028 |
asing | -0.025 |
cher | -0.025 |
od | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
crib | +0.044 |
ara | +0.043 |
Mom | +0.042 |
mom | +0.038 |
Sunny | +0.037 |
Neg logit contributions | |
vell | -0.083 |
wheel | -0.077 |
disl | -0.074 |
inations | -0.073 |
od | -0.072 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
crib | +0.032 |
ara | +0.031 |
Mom | +0.031 |
mom | +0.029 |
beef | +0.028 |
Neg logit contributions | |
vell | -0.047 |
wheel | -0.043 |
disl | -0.043 |
od | -0.040 |
inations | -0.040 |
Token | well |
Token ID | 880 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
Mom | +0.278 |
beef | +0.250 |
ham | +0.248 |
crib | +0.248 |
Sunny | +0.243 |
Neg logit contributions | |
vell | -0.425 |
inations | -0.382 |
disl | -0.379 |
wheel | -0.377 |
cast | -0.358 |
Token | . |
Token ID | 13 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
crib | +0.090 |
ara | +0.088 |
Mom | +0.087 |
mom | +0.080 |
Sunny | +0.076 |
Neg logit contributions | |
vell | -0.157 |
wheel | -0.145 |
disl | -0.137 |
inations | -0.137 |
od | -0.135 |
Token | We |
Token ID | 775 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
crib | +0.030 |
ara | +0.028 |
Mom | +0.028 |
mom | +0.026 |
beef | +0.025 |
Neg logit contributions | |
vell | -0.050 |
wheel | -0.047 |
disl | -0.046 |
od | -0.044 |
inations | -0.043 |
Token | love |
Token ID | 1842 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
crib | +0.024 |
ara | +0.023 |
Mom | +0.023 |
mom | +0.022 |
bunny | +0.021 |
Neg logit contributions | |
vell | -0.043 |
wheel | -0.039 |
inations | -0.037 |
disl | -0.037 |
od | -0.037 |
Token | you |
Token ID | 345 |
Feature activation | -4.96e-03 |
Pos logit contributions | |
ara | +0.092 |
crib | +0.090 |
um | +0.090 |
Mom | +0.089 |
vet | +0.086 |
Neg logit contributions | |
vell | -0.059 |
inations | -0.058 |
achieve | -0.056 |
od | -0.056 |
disl | -0.055 |
Token | Sara |
Token ID | 24799 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
crib | +0.034 |
Mom | +0.032 |
End | +0.030 |
ara | +0.029 |
um | +0.029 |
Neg logit contributions | |
vell | -0.081 |
wheel | -0.075 |
od | -0.072 |
disl | -0.071 |
inations | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
crib | +0.033 |
ara | +0.032 |
Mom | +0.031 |
mom | +0.028 |
End | +0.028 |
Neg logit contributions | |
vell | -0.057 |
wheel | -0.053 |
disl | -0.050 |
od | -0.050 |
inations | -0.050 |
Token | Good |
Token ID | 4599 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
crib | +0.018 |
ara | +0.018 |
Mom | +0.018 |
um | +0.017 |
chicken | +0.017 |
Neg logit contributions | |
vell | -0.020 |
wheel | -0.019 |
disl | -0.019 |
asing | -0.017 |
od | -0.017 |
Token | night |
Token ID | 1755 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
Mom | +0.104 |
ara | +0.094 |
vet | +0.094 |
Sunny | +0.092 |
crib | +0.091 |
Neg logit contributions | |
vell | -0.179 |
disl | -0.163 |
ont | -0.162 |
cast | -0.161 |
wheel | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
ara | +0.049 |
crib | +0.049 |
Mom | +0.048 |
End | +0.040 |
beef | +0.040 |
Neg logit contributions | |
vell | -0.119 |
wheel | -0.113 |
inations | -0.107 |
disl | -0.106 |
od | -0.106 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
crib | +0.017 |
ara | +0.017 |
Mom | +0.016 |
beef | +0.016 |
um | +0.016 |
Neg logit contributions | |
vell | -0.023 |
wheel | -0.022 |
disl | -0.022 |
asing | -0.020 |
od | -0.020 |
Token | tight |
Token ID | 5381 |
Feature activation | +9.94e-02 |
Pos logit contributions | |
Mom | +0.268 |
beef | +0.253 |
ham | +0.249 |
vet | +0.244 |
crib | +0.241 |
Neg logit contributions | |
vell | -0.415 |
disl | -0.371 |
wheel | -0.368 |
inations | -0.367 |
cast | -0.353 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
crib | +0.119 |
Mom | +0.119 |
ara | +0.119 |
mom | +0.105 |
End | +0.102 |
Neg logit contributions | |
vell | -0.239 |
wheel | -0.225 |
disl | -0.212 |
inations | -0.208 |
od | -0.207 |
Token | Don |
Token ID | 2094 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
crib | +0.016 |
ara | +0.015 |
Mom | +0.015 |
mom | +0.014 |
beef | +0.014 |
Neg logit contributions | |
vell | -0.024 |
wheel | -0.023 |
disl | -0.022 |
inations | -0.021 |
od | -0.021 |
Token | 't |
Token ID | 470 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
vell | +0.070 |
wheel | +0.068 |
inations | +0.060 |
od | +0.058 |
achieve | +0.058 |
Neg logit contributions | |
crib | -0.058 |
ara | -0.056 |
Mom | -0.054 |
ham | -0.052 |
mom | -0.051 |
Token | let |
Token ID | 1309 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
vell | +0.065 |
wheel | +0.061 |
disl | +0.058 |
inations | +0.056 |
od | +0.056 |
Neg logit contributions | |
crib | -0.052 |
ara | -0.052 |
Mom | -0.050 |
beef | -0.046 |
um | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
crib | +0.042 |
ara | +0.041 |
Mom | +0.040 |
mom | +0.034 |
Sunny | +0.033 |
Neg logit contributions | |
vell | -0.130 |
wheel | -0.122 |
disl | -0.117 |
inations | -0.117 |
od | -0.116 |
Token | my |
Token ID | 616 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
ara | +0.037 |
crib | +0.036 |
Mom | +0.035 |
mom | +0.034 |
Mom | +0.031 |
Neg logit contributions | |
vell | -0.088 |
wheel | -0.082 |
od | -0.078 |
inations | -0.077 |
disl | -0.077 |
Token | sweet |
Token ID | 6029 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
Mom | +0.017 |
crib | +0.017 |
Sunny | +0.016 |
ara | +0.015 |
vet | +0.014 |
Neg logit contributions | |
vell | -0.032 |
disl | -0.029 |
wheel | -0.029 |
inations | -0.028 |
od | -0.028 |
Token | ies |
Token ID | 444 |
Feature activation | -9.59e-02 |
Pos logit contributions | |
crib | +0.088 |
Mom | +0.085 |
Sunny | +0.081 |
ara | +0.078 |
beef | +0.076 |
Neg logit contributions | |
vell | -0.114 |
wheel | -0.106 |
disl | -0.103 |
od | -0.101 |
inations | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
vell | +0.240 |
wheel | +0.221 |
disl | +0.212 |
od | +0.210 |
inations | +0.208 |
Neg logit contributions | |
crib | -0.116 |
ara | -0.112 |
Mom | -0.105 |
mom | -0.102 |
Sunny | -0.099 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
crib | +0.021 |
ara | +0.020 |
Mom | +0.020 |
mom | +0.018 |
Sunny | +0.018 |
Neg logit contributions | |
vell | -0.038 |
wheel | -0.035 |
disl | -0.033 |
inations | -0.033 |
od | -0.033 |
Token | tight |
Token ID | 5381 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
Mom | +0.263 |
crib | +0.240 |
ham | +0.235 |
beef | +0.233 |
ara | +0.229 |
Neg logit contributions | |
vell | -0.432 |
disl | -0.389 |
wheel | -0.387 |
inations | -0.385 |
cast | -0.367 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
crib | +0.122 |
ara | +0.120 |
Mom | +0.118 |
mom | +0.107 |
Sunny | +0.102 |
Neg logit contributions | |
vell | -0.240 |
wheel | -0.223 |
disl | -0.212 |
inations | -0.210 |
od | -0.208 |
Token | And |
Token ID | 843 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
crib | +0.021 |
ara | +0.020 |
Mom | +0.020 |
mom | +0.018 |
beef | +0.017 |
Neg logit contributions | |
vell | -0.037 |
wheel | -0.034 |
disl | -0.033 |
inations | -0.032 |
od | -0.032 |
Token | don |
Token ID | 836 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
vell | +0.077 |
wheel | +0.070 |
disl | +0.067 |
inations | +0.066 |
od | +0.065 |
Neg logit contributions | |
crib | -0.055 |
ara | -0.054 |
Mom | -0.052 |
mom | -0.049 |
Sunny | -0.047 |
Token | 't |
Token ID | 470 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
vell | +0.108 |
wheel | +0.099 |
disl | +0.094 |
inations | +0.093 |
od | +0.092 |
Neg logit contributions | |
crib | -0.067 |
ara | -0.065 |
Mom | -0.064 |
mom | -0.060 |
Sunny | -0.057 |
Token | You |
Token ID | 921 |
Feature activation | -8.28e-04 |
Pos logit contributions | |
vell | +0.000 |
wheel | +0.000 |
disl | +0.000 |
od | +0.000 |
inations | +0.000 |
Neg logit contributions | |
crib | -0.000 |
ara | -0.000 |
Mom | -0.000 |
mom | -0.000 |
beef | -0.000 |
Token | need |
Token ID | 761 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
vell | +0.002 |
disl | +0.002 |
wheel | +0.002 |
od | +0.002 |
inations | +0.002 |
Neg logit contributions | |
crib | -0.001 |
mom | -0.001 |
bunny | -0.001 |
Mom | -0.001 |
Sunny | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +7.47e-03 |
Pos logit contributions | |
ara | +0.027 |
crib | +0.024 |
Mom | +0.024 |
um | +0.023 |
End | +0.023 |
Neg logit contributions | |
vell | -0.037 |
wheel | -0.035 |
inations | -0.034 |
disl | -0.033 |
smart | -0.032 |
Token | sleep |
Token ID | 3993 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
crib | +0.010 |
ara | +0.010 |
Mom | +0.010 |
mom | +0.009 |
Sunny | +0.009 |
Neg logit contributions | |
vell | -0.017 |
wheel | -0.016 |
disl | -0.015 |
inations | -0.015 |
od | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +6.75e-04 |
Pos logit contributions | |
crib | +0.113 |
ara | +0.111 |
Mom | +0.107 |
mom | +0.099 |
Sunny | +0.095 |
Neg logit contributions | |
vell | -0.225 |
wheel | -0.208 |
disl | -0.198 |
inations | -0.197 |
od | -0.195 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
ara | +0.001 |
crib | +0.001 |
Mom | +0.001 |
beef | +0.001 |
um | +0.001 |
Neg logit contributions | |
vell | -0.001 |
wheel | -0.001 |
disl | -0.001 |
asing | -0.001 |
inations | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
Mom | +0.259 |
crib | +0.253 |
ara | +0.248 |
beef | +0.229 |
mom | +0.229 |
Neg logit contributions | |
vell | -0.444 |
wheel | -0.406 |
disl | -0.394 |
inations | -0.391 |
od | -0.375 |
Token | good |
Token ID | 922 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
ara | +0.026 |
crib | +0.024 |
Mom | +0.024 |
um | +0.022 |
ham | +0.021 |
Neg logit contributions | |
vell | -0.035 |
wheel | -0.032 |
inations | -0.031 |
disl | -0.030 |
cher | -0.029 |
Token | for |
Token ID | 329 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
vell | +0.099 |
wheel | +0.091 |
disl | +0.087 |
inations | +0.086 |
od | +0.086 |
Neg logit contributions | |
crib | -0.042 |
ara | -0.040 |
Mom | -0.038 |
mom | -0.037 |
bunny | -0.035 |
Token | you |
Token ID | 345 |
Feature activation | -7.78e-03 |
Pos logit contributions | |
ara | +0.054 |
crib | +0.050 |
Mom | +0.049 |
um | +0.046 |
ham | +0.043 |
Neg logit contributions | |
vell | -0.080 |
inations | -0.075 |
wheel | -0.073 |
disl | -0.071 |
od | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
vell | +0.018 |
wheel | +0.016 |
inations | +0.016 |
disl | +0.016 |
od | +0.015 |
Neg logit contributions | |
ara | -0.011 |
crib | -0.010 |
Mom | -0.010 |
mom | -0.009 |
Sunny | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
crib | +0.023 |
ara | +0.022 |
Mom | +0.020 |
mom | +0.017 |
beef | +0.017 |
Neg logit contributions | |
vell | -0.060 |
wheel | -0.057 |
od | -0.054 |
disl | -0.054 |
inations | -0.052 |
Token | It |
Token ID | 1026 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
ara | +0.042 |
crib | +0.041 |
Mom | +0.040 |
mom | +0.036 |
Sunny | +0.035 |
Neg logit contributions | |
vell | -0.099 |
wheel | -0.092 |
inations | -0.088 |
disl | -0.088 |
od | -0.086 |
Token | 's |
Token ID | 338 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
crib | +0.063 |
ara | +0.059 |
bunny | +0.057 |
mom | +0.057 |
Sunny | +0.056 |
Neg logit contributions | |
vell | -0.168 |
wheel | -0.157 |
inations | -0.150 |
disl | -0.149 |
od | -0.145 |
Token | easy |
Token ID | 2562 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
crib | +0.076 |
ara | +0.076 |
Mom | +0.073 |
mom | +0.067 |
bunny | +0.065 |
Neg logit contributions | |
vell | -0.132 |
wheel | -0.121 |
disl | -0.115 |
inations | -0.114 |
od | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | +8.47e-05 |
Pos logit contributions | |
vell | +0.076 |
wheel | +0.070 |
disl | +0.067 |
inations | +0.066 |
od | +0.066 |
Neg logit contributions | |
crib | -0.032 |
ara | -0.030 |
Mom | -0.028 |
mom | -0.028 |
Sunny | -0.026 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
crib | +0.000 |
ara | +0.000 |
Mom | +0.000 |
mom | +0.000 |
beef | +0.000 |
Neg logit contributions | |
vell | -0.000 |
wheel | -0.000 |
disl | -0.000 |
od | -0.000 |
inations | -0.000 |
Token | is |
Token ID | 318 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
Mom | +0.253 |
crib | +0.244 |
ara | +0.242 |
mom | +0.221 |
beef | +0.219 |
Neg logit contributions | |
vell | -0.459 |
wheel | -0.417 |
disl | -0.409 |
inations | -0.404 |
od | -0.393 |
Token | when |
Token ID | 618 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
crib | +0.019 |
ara | +0.019 |
Mom | +0.018 |
mom | +0.017 |
Sunny | +0.016 |
Neg logit contributions | |
vell | -0.033 |
wheel | -0.030 |
disl | -0.029 |
inations | -0.029 |
od | -0.028 |
Token | you |
Token ID | 345 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
ara | +0.024 |
Mom | +0.023 |
crib | +0.023 |
um | +0.021 |
End | +0.020 |
Neg logit contributions | |
vell | -0.031 |
wheel | -0.028 |
inations | -0.027 |
disl | -0.027 |
od | -0.027 |
Token | close |
Token ID | 1969 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
vell | +0.023 |
wheel | +0.021 |
disl | +0.021 |
od | +0.020 |
inations | +0.020 |
Neg logit contributions | |
crib | -0.016 |
ara | -0.016 |
Mom | -0.015 |
mom | -0.015 |
bunny | -0.014 |
Token | your |
Token ID | 534 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
crib | +0.105 |
ara | +0.103 |
Mom | +0.099 |
mom | +0.092 |
Sunny | +0.088 |
Neg logit contributions | |
vell | -0.221 |
wheel | -0.205 |
disl | -0.195 |
inations | -0.194 |
od | -0.192 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
vell | +0.015 |
wheel | +0.014 |
inations | +0.013 |
cher | +0.013 |
cast | +0.012 |
Neg logit contributions | |
crib | -0.012 |
ara | -0.011 |
Mom | -0.011 |
beef | -0.011 |
um | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
vell | +0.047 |
wheel | +0.045 |
disl | +0.042 |
od | +0.040 |
inations | +0.039 |
Neg logit contributions | |
ara | -0.041 |
Mom | -0.037 |
um | -0.036 |
crib | -0.035 |
� | -0.034 |
Token | big |
Token ID | 1263 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ara | +0.027 |
um | +0.027 |
Mom | +0.026 |
End | +0.026 |
brow | +0.025 |
Neg logit contributions | |
vell | -0.043 |
wheel | -0.039 |
achieve | -0.036 |
cher | -0.034 |
inations | -0.034 |
Token | ball |
Token ID | 2613 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
wheel | +0.018 |
vell | +0.018 |
achieve | +0.016 |
disl | +0.016 |
ologist | +0.016 |
Neg logit contributions | |
Mom | -0.016 |
End | -0.014 |
ara | -0.014 |
Me | -0.014 |
um | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -3.63e-03 |
Pos logit contributions | |
wheel | +0.009 |
vell | +0.009 |
od | +0.008 |
cher | +0.008 |
smart | +0.007 |
Neg logit contributions | |
ara | -0.007 |
Mom | -0.007 |
crib | -0.007 |
mom | -0.007 |
End | -0.006 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
wheel | +0.006 |
vell | +0.005 |
smart | +0.005 |
achieve | +0.005 |
cher | +0.004 |
Neg logit contributions | |
ara | -0.007 |
Mom | -0.006 |
End | -0.006 |
um | -0.006 |
end | -0.006 |
Token | y |
Token ID | 88 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
crib | +0.280 |
Mom | +0.275 |
beef | +0.275 |
vet | +0.266 |
ham | +0.262 |
Neg logit contributions | |
vell | -0.420 |
cast | -0.360 |
wheel | -0.357 |
disl | -0.355 |
od | -0.350 |
Token | loved |
Token ID | 6151 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
crib | +0.066 |
Mom | +0.066 |
ara | +0.064 |
beef | +0.059 |
End | +0.058 |
Neg logit contributions | |
vell | -0.085 |
wheel | -0.084 |
od | -0.077 |
inations | -0.075 |
cast | -0.075 |
Token | balls |
Token ID | 11333 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
ara | +0.065 |
Mom | +0.063 |
um | +0.060 |
crib | +0.058 |
End | +0.055 |
Neg logit contributions | |
vell | -0.081 |
wheel | -0.078 |
disl | -0.073 |
smart | -0.072 |
inations | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | -3.05e-03 |
Pos logit contributions | |
vell | +0.231 |
disl | +0.213 |
wheel | +0.209 |
inations | +0.205 |
od | +0.202 |
Neg logit contributions | |
crib | -0.085 |
ara | -0.074 |
Mom | -0.073 |
mom | -0.073 |
bunny | -0.070 |
Token | He |
Token ID | 679 |
Feature activation | -1.97e-03 |
Pos logit contributions | |
vell | +0.005 |
wheel | +0.004 |
achieve | +0.004 |
cast | +0.004 |
smart | +0.004 |
Neg logit contributions | |
Mom | -0.005 |
ara | -0.005 |
End | -0.005 |
um | -0.005 |
mother | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
wheel | +0.007 |
vell | +0.007 |
achieve | +0.007 |
cast | +0.007 |
inations | +0.007 |
Neg logit contributions | |
ara | -0.008 |
Mom | -0.008 |
End | -0.007 |
um | -0.007 |
lady | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
vell | +0.034 |
wheel | +0.033 |
od | +0.033 |
inations | +0.033 |
achieve | +0.031 |
Neg logit contributions | |
crib | -0.022 |
ara | -0.021 |
ham | -0.020 |
Mom | -0.020 |
kitten | -0.020 |
Token | One |
Token ID | 3198 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
achieve | +0.026 |
vell | +0.025 |
inations | +0.024 |
wheel | +0.024 |
accomplish | +0.022 |
Neg logit contributions | |
eyes | -0.028 |
mom | -0.028 |
mother | -0.027 |
Mom | -0.027 |
kitten | -0.026 |
Token | day |
Token ID | 1110 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
cash | +0.174 |
ara | +0.162 |
checkout | +0.161 |
Mom | +0.155 |
brow | +0.154 |
Neg logit contributions | |
wheel | -0.223 |
vell | -0.223 |
ont | -0.215 |
adows | -0.209 |
inations | -0.209 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
Mom | +0.047 |
ara | +0.046 |
crib | +0.046 |
vet | +0.045 |
nurse | +0.044 |
Neg logit contributions | |
vell | -0.044 |
wheel | -0.038 |
smart | -0.037 |
cher | -0.036 |
od | -0.036 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ara | +0.036 |
um | +0.034 |
crib | +0.032 |
End | +0.032 |
Mom | +0.032 |
Neg logit contributions | |
vell | -0.036 |
wheel | -0.031 |
cher | -0.029 |
cast | -0.029 |
achieve | -0.029 |
Token | y |
Token ID | 88 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
beef | +0.280 |
cash | +0.268 |
ham | +0.266 |
crib | +0.266 |
Mom | +0.255 |
Neg logit contributions | |
vell | -0.386 |
disl | -0.342 |
cast | -0.337 |
od | -0.331 |
ont | -0.324 |
Token | went |
Token ID | 1816 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
crib | +0.063 |
Mom | +0.063 |
ara | +0.058 |
beef | +0.058 |
um | +0.055 |
Neg logit contributions | |
vell | -0.078 |
wheel | -0.076 |
od | -0.070 |
inations | -0.070 |
cast | -0.067 |
Token | for |
Token ID | 329 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
vell | +0.053 |
wheel | +0.051 |
inations | +0.045 |
cher | +0.045 |
smart | +0.045 |
Neg logit contributions | |
ara | -0.044 |
Mom | -0.042 |
End | -0.039 |
crib | -0.039 |
mom | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
ara | +0.059 |
um | +0.056 |
Mom | +0.054 |
crib | +0.048 |
� | +0.047 |
Neg logit contributions | |
inations | -0.058 |
vell | -0.057 |
wheel | -0.057 |
achieve | -0.054 |
disl | -0.053 |
Token | walk |
Token ID | 2513 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
ara | +0.023 |
Mom | +0.023 |
um | +0.023 |
End | +0.022 |
crib | +0.022 |
Neg logit contributions | |
vell | -0.041 |
wheel | -0.038 |
inations | -0.038 |
achieve | -0.035 |
disl | -0.035 |
Token | Good |
Token ID | 10248 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
crib | +0.051 |
mom | +0.045 |
beef | +0.043 |
eyes | +0.043 |
Sunny | +0.043 |
Neg logit contributions | |
wheel | -0.069 |
vell | -0.068 |
disl | -0.061 |
asing | -0.059 |
inations | -0.059 |
Token | night |
Token ID | 3847 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
vell | +0.007 |
wheel | +0.007 |
ont | +0.007 |
disl | +0.006 |
od | +0.006 |
Neg logit contributions | |
Mom | -0.004 |
Sunny | -0.004 |
crib | -0.004 |
ara | -0.004 |
stall | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
Mom | +0.174 |
ara | +0.169 |
crib | +0.168 |
End | +0.153 |
beef | +0.141 |
Neg logit contributions | |
vell | -0.419 |
wheel | -0.397 |
disl | -0.372 |
od | -0.371 |
cher | -0.368 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
crib | +0.021 |
ara | +0.020 |
Mom | +0.020 |
beef | +0.017 |
End | +0.017 |
Neg logit contributions | |
vell | -0.049 |
wheel | -0.046 |
disl | -0.044 |
inations | -0.043 |
od | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
vell | +0.042 |
wheel | +0.038 |
disl | +0.036 |
inations | +0.036 |
od | +0.035 |
Neg logit contributions | |
crib | -0.032 |
ara | -0.032 |
Mom | -0.031 |
mom | -0.029 |
Sunny | -0.028 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
vell | +0.021 |
wheel | +0.020 |
disl | +0.019 |
inations | +0.018 |
asing | +0.018 |
Neg logit contributions | |
crib | -0.015 |
ara | -0.015 |
beef | -0.014 |
Mom | -0.014 |
chicken | -0.014 |
Token | well |
Token ID | 880 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
Mom | +0.262 |
ham | +0.252 |
beef | +0.248 |
vet | +0.236 |
crib | +0.231 |
Neg logit contributions | |
vell | -0.402 |
wheel | -0.366 |
disl | -0.363 |
inations | -0.355 |
cast | -0.343 |
Token | ." |
Token ID | 526 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
crib | +0.070 |
ara | +0.068 |
Mom | +0.066 |
mom | +0.062 |
Sunny | +0.059 |
Neg logit contributions | |
vell | -0.135 |
wheel | -0.125 |
disl | -0.119 |
inations | -0.118 |
od | -0.117 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
wheel | +0.052 |
vell | +0.051 |
disl | +0.050 |
od | +0.047 |
inations | +0.047 |
Neg logit contributions | |
crib | -0.028 |
Mom | -0.027 |
ara | -0.027 |
End | -0.025 |
beef | -0.025 |
Token | replied |
Token ID | 8712 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
vell | +0.034 |
wheel | +0.033 |
inations | +0.031 |
od | +0.029 |
ont | +0.029 |
Neg logit contributions | |
crib | -0.032 |
beef | -0.030 |
ara | -0.030 |
Mom | -0.030 |
kitten | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
ara | +0.144 |
vet | +0.124 |
kitten | +0.121 |
ham | +0.119 |
Mom | +0.119 |
Neg logit contributions | |
vell | -0.167 |
wheel | -0.158 |
od | -0.145 |
achieve | -0.140 |
smart | -0.138 |
Token | day |
Token ID | 1110 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
vell | +0.093 |
wheel | +0.085 |
inations | +0.082 |
disl | +0.082 |
cher | +0.081 |
Neg logit contributions | |
crib | -0.018 |
ara | -0.015 |
Mom | -0.014 |
mom | -0.012 |
Sunny | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -7.18e-03 |
Pos logit contributions | |
ara | +0.034 |
Mom | +0.033 |
crib | +0.032 |
End | +0.029 |
mom | +0.028 |
Neg logit contributions | |
vell | -0.062 |
wheel | -0.058 |
inations | -0.056 |
od | -0.055 |
disl | -0.052 |
Token | all |
Token ID | 477 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
vell | +0.015 |
wheel | +0.014 |
disl | +0.014 |
inations | +0.014 |
achieve | +0.013 |
Neg logit contributions | |
ara | -0.011 |
Mom | -0.010 |
crib | -0.010 |
um | -0.010 |
kitten | -0.009 |
Token | night |
Token ID | 1755 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
vell | +0.086 |
wheel | +0.079 |
disl | +0.076 |
inations | +0.076 |
od | +0.075 |
Neg logit contributions | |
crib | -0.022 |
ara | -0.020 |
Mom | -0.019 |
mom | -0.018 |
Sunny | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -6.85e-03 |
Pos logit contributions | |
ara | +0.053 |
crib | +0.051 |
Mom | +0.051 |
mom | +0.047 |
End | +0.045 |
Neg logit contributions | |
vell | -0.088 |
wheel | -0.082 |
inations | -0.078 |
od | -0.077 |
disl | -0.077 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
wheel | +0.010 |
vell | +0.010 |
achieve | +0.010 |
cast | +0.009 |
inations | +0.009 |
Neg logit contributions | |
ara | -0.011 |
Mom | -0.011 |
um | -0.010 |
End | -0.010 |
kitten | -0.010 |
Token | y |
Token ID | 88 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
beef | +0.258 |
crib | +0.254 |
Mom | +0.249 |
vet | +0.247 |
ham | +0.247 |
Neg logit contributions | |
vell | -0.401 |
disl | -0.358 |
wheel | -0.347 |
cast | -0.347 |
od | -0.343 |
Token | had |
Token ID | 550 |
Feature activation | +5.33e-03 |
Pos logit contributions | |
Mom | +0.051 |
crib | +0.050 |
ara | +0.050 |
beef | +0.045 |
mom | +0.045 |
Neg logit contributions | |
vell | -0.085 |
wheel | -0.081 |
inations | -0.077 |
od | -0.076 |
disl | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ara | +0.008 |
Mom | +0.007 |
crib | +0.007 |
End | +0.007 |
um | +0.006 |
Neg logit contributions | |
vell | -0.012 |
wheel | -0.011 |
inations | -0.010 |
od | -0.010 |
disl | -0.010 |
Token | big |
Token ID | 1263 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
ara | +0.025 |
um | +0.023 |
End | +0.023 |
Mom | +0.022 |
Sunny | +0.021 |
Neg logit contributions | |
vell | -0.025 |
inations | -0.022 |
achieve | -0.021 |
wheel | -0.021 |
disl | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
inations | +0.024 |
wheel | +0.024 |
disl | +0.024 |
vell | +0.023 |
ont | +0.023 |
Neg logit contributions | |
Mom | -0.021 |
ara | -0.020 |
Ivy | -0.018 |
Please | -0.018 |
cash | -0.018 |
Token | night |
Token ID | 1755 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
vell | +0.014 |
wheel | +0.014 |
disl | +0.013 |
od | +0.013 |
ologist | +0.012 |
Neg logit contributions | |
crib | -0.007 |
ara | -0.007 |
Mom | -0.007 |
Sunny | -0.006 |
mom | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
crib | +0.037 |
ara | +0.036 |
Mom | +0.035 |
mom | +0.030 |
Sunny | +0.029 |
Neg logit contributions | |
vell | -0.098 |
wheel | -0.092 |
inations | -0.088 |
disl | -0.088 |
od | -0.087 |
Token | sweet |
Token ID | 6029 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
crib | +0.022 |
ara | +0.021 |
Mom | +0.020 |
mom | +0.017 |
Sunny | +0.017 |
Neg logit contributions | |
vell | -0.059 |
wheel | -0.055 |
disl | -0.053 |
inations | -0.052 |
od | -0.052 |
Token | ie |
Token ID | 494 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
crib | +0.074 |
Mom | +0.072 |
ara | +0.067 |
Sunny | +0.066 |
End | +0.064 |
Neg logit contributions | |
vell | -0.085 |
wheel | -0.077 |
disl | -0.076 |
od | -0.075 |
inations | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
vell | +0.046 |
wheel | +0.042 |
disl | +0.039 |
inations | +0.039 |
od | +0.039 |
Neg logit contributions | |
crib | -0.031 |
ara | -0.030 |
Mom | -0.029 |
mom | -0.027 |
Sunny | -0.027 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
crib | +0.002 |
ara | +0.002 |
Mom | +0.002 |
mom | +0.001 |
beef | +0.001 |
Neg logit contributions | |
vell | -0.003 |
wheel | -0.003 |
disl | -0.003 |
inations | -0.003 |
od | -0.003 |
Token | tight |
Token ID | 5381 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
Mom | +0.255 |
ham | +0.240 |
ara | +0.235 |
crib | +0.235 |
beef | +0.234 |
Neg logit contributions | |
vell | -0.412 |
wheel | -0.366 |
inations | -0.366 |
disl | -0.362 |
cast | -0.342 |
Token | ." |
Token ID | 526 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
crib | +0.120 |
ara | +0.119 |
Mom | +0.118 |
mom | +0.107 |
End | +0.103 |
Neg logit contributions | |
vell | -0.200 |
wheel | -0.186 |
disl | -0.176 |
inations | -0.174 |
od | -0.171 |
Token | He |
Token ID | 679 |
Feature activation | +1.81e-04 |
Pos logit contributions | |
vell | +0.053 |
wheel | +0.051 |
disl | +0.051 |
inations | +0.048 |
od | +0.048 |
Neg logit contributions | |
crib | -0.028 |
ara | -0.027 |
Mom | -0.027 |
End | -0.025 |
kitten | -0.024 |
Token | tucked |
Token ID | 29779 |
Feature activation | +9.04e-02 |
Pos logit contributions | |
crib | +0.000 |
ara | +0.000 |
Mom | +0.000 |
beef | +0.000 |
End | +0.000 |
Neg logit contributions | |
vell | -0.000 |
wheel | -0.000 |
inations | -0.000 |
od | -0.000 |
cher | -0.000 |
Token | her |
Token ID | 607 |
Feature activation | +6.49e-03 |
Pos logit contributions | |
crib | +0.128 |
ara | +0.124 |
Mom | +0.113 |
beef | +0.109 |
End | +0.108 |
Neg logit contributions | |
vell | -0.187 |
wheel | -0.168 |
cher | -0.163 |
cast | -0.156 |
smart | -0.155 |
Token | you |
Token ID | 345 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
crib | +0.056 |
ara | +0.055 |
Mom | +0.052 |
End | +0.048 |
um | +0.048 |
Neg logit contributions | |
vell | -0.064 |
wheel | -0.061 |
disl | -0.060 |
od | -0.058 |
inations | -0.057 |
Token | too |
Token ID | 1165 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
vell | +0.033 |
inations | +0.031 |
wheel | +0.030 |
ologist | +0.030 |
asing | +0.028 |
Neg logit contributions | |
ara | -0.027 |
crib | -0.025 |
Goose | -0.023 |
nurse | -0.023 |
therapist | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
ara | +0.053 |
crib | +0.052 |
Mom | +0.050 |
bunny | +0.044 |
nurse | +0.044 |
Neg logit contributions | |
vell | -0.115 |
wheel | -0.105 |
disl | -0.103 |
inations | -0.103 |
od | -0.102 |
Token | kids |
Token ID | 3988 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
crib | +0.029 |
ara | +0.025 |
Mom | +0.024 |
beef | +0.022 |
Sunny | +0.021 |
Neg logit contributions | |
vell | -0.069 |
wheel | -0.065 |
disl | -0.063 |
inations | -0.062 |
od | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
vell | +0.215 |
wheel | +0.200 |
disl | +0.188 |
inations | +0.188 |
od | +0.186 |
Neg logit contributions | |
crib | -0.132 |
ara | -0.130 |
Mom | -0.128 |
mom | -0.116 |
End | -0.115 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
crib | +0.021 |
ara | +0.020 |
Mom | +0.019 |
mom | +0.018 |
bunny | +0.018 |
Neg logit contributions | |
vell | -0.027 |
wheel | -0.025 |
disl | -0.025 |
asing | -0.023 |
od | -0.023 |
Token | well |
Token ID | 880 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
Mom | +0.258 |
beef | +0.240 |
crib | +0.239 |
ham | +0.233 |
hen | +0.230 |
Neg logit contributions | |
vell | -0.397 |
disl | -0.364 |
wheel | -0.353 |
inations | -0.351 |
cast | -0.339 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
crib | +0.072 |
ara | +0.071 |
Mom | +0.070 |
mom | +0.064 |
Sunny | +0.061 |
Neg logit contributions | |
vell | -0.132 |
wheel | -0.122 |
disl | -0.116 |
inations | -0.115 |
od | -0.114 |
Token | Have |
Token ID | 8192 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
crib | +0.020 |
ara | +0.019 |
Mom | +0.018 |
mom | +0.018 |
beef | +0.017 |
Neg logit contributions | |
vell | -0.027 |
wheel | -0.026 |
disl | -0.025 |
od | -0.023 |
inations | -0.023 |
Token | sweet |
Token ID | 6029 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
crib | +0.074 |
ara | +0.071 |
Mom | +0.067 |
nurse | +0.064 |
kitten | +0.064 |
Neg logit contributions | |
vell | -0.075 |
wheel | -0.072 |
disl | -0.070 |
inations | -0.069 |
od | -0.064 |
Token | dreams |
Token ID | 10625 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
Mom | +0.068 |
crib | +0.067 |
ara | +0.063 |
End | +0.059 |
Sunny | +0.058 |
Neg logit contributions | |
vell | -0.092 |
disl | -0.090 |
wheel | -0.089 |
inations | -0.089 |
asing | -0.084 |
Token | Good |
Token ID | 10248 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
crib | +0.045 |
ara | +0.041 |
mom | +0.041 |
um | +0.038 |
Mom | +0.037 |
Neg logit contributions | |
vell | -0.066 |
wheel | -0.066 |
disl | -0.059 |
inations | -0.058 |
cher | -0.058 |
Token | night |
Token ID | 3847 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
vell | +0.016 |
wheel | +0.016 |
ont | +0.015 |
cast | +0.015 |
disl | +0.015 |
Neg logit contributions | |
Mom | -0.007 |
crib | -0.007 |
ara | -0.006 |
End | -0.006 |
Sunny | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
Mom | +0.167 |
crib | +0.164 |
ara | +0.164 |
End | +0.143 |
beef | +0.132 |
Neg logit contributions | |
vell | -0.425 |
wheel | -0.400 |
disl | -0.378 |
od | -0.376 |
inations | -0.375 |
Token | Max |
Token ID | 5436 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
crib | +0.019 |
ara | +0.019 |
Mom | +0.018 |
mom | +0.016 |
Sunny | +0.016 |
Neg logit contributions | |
vell | -0.043 |
wheel | -0.040 |
disl | -0.038 |
inations | -0.038 |
od | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
crib | +0.034 |
ara | +0.033 |
Mom | +0.033 |
mom | +0.031 |
Sunny | +0.029 |
Neg logit contributions | |
vell | -0.042 |
wheel | -0.038 |
disl | -0.036 |
inations | -0.035 |
od | -0.035 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
vell | +0.029 |
wheel | +0.028 |
disl | +0.026 |
inations | +0.025 |
od | +0.025 |
Neg logit contributions | |
crib | -0.018 |
ara | -0.017 |
Mom | -0.016 |
beef | -0.015 |
mom | -0.015 |
Token | tight |
Token ID | 5381 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
Mom | +0.261 |
ham | +0.236 |
crib | +0.235 |
beef | +0.234 |
vet | +0.229 |
Neg logit contributions | |
vell | -0.412 |
wheel | -0.372 |
inations | -0.363 |
disl | -0.362 |
cast | -0.355 |
Token | ." |
Token ID | 526 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
Mom | +0.138 |
ara | +0.136 |
crib | +0.133 |
mom | +0.122 |
End | +0.122 |
Neg logit contributions | |
vell | -0.192 |
wheel | -0.178 |
disl | -0.168 |
inations | -0.164 |
od | -0.161 |
Token | Max |
Token ID | 5436 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
vell | +0.059 |
wheel | +0.057 |
disl | +0.054 |
inations | +0.053 |
od | +0.053 |
Neg logit contributions | |
crib | -0.031 |
ara | -0.030 |
Mom | -0.029 |
mom | -0.026 |
End | -0.026 |
Token | fell |
Token ID | 3214 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
crib | +0.034 |
Mom | +0.032 |
ara | +0.031 |
beef | +0.030 |
kitten | +0.030 |
Neg logit contributions | |
vell | -0.039 |
wheel | -0.038 |
inations | -0.035 |
od | -0.034 |
cast | -0.034 |
Token | asleep |
Token ID | 16039 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
vell | +0.006 |
wheel | +0.006 |
cast | +0.006 |
cher | +0.005 |
smart | +0.005 |
Neg logit contributions | |
ara | -0.006 |
Mom | -0.005 |
End | -0.005 |
crib | -0.005 |
ham | -0.005 |
Token | Good |
Token ID | 10248 |
Feature activation | -5.18e-03 |
Pos logit contributions | |
crib | +0.059 |
mom | +0.051 |
um | +0.050 |
eyes | +0.050 |
beef | +0.050 |
Neg logit contributions | |
vell | -0.080 |
wheel | -0.078 |
disl | -0.071 |
cher | -0.067 |
inations | -0.066 |
Token | night |
Token ID | 1755 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
vell | +0.011 |
wheel | +0.011 |
disl | +0.010 |
od | +0.010 |
ont | +0.010 |
Neg logit contributions | |
crib | -0.006 |
Mom | -0.006 |
Sunny | -0.006 |
beef | -0.006 |
ara | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
crib | +0.038 |
ara | +0.037 |
Mom | +0.037 |
End | +0.031 |
beef | +0.031 |
Neg logit contributions | |
vell | -0.095 |
wheel | -0.090 |
inations | -0.086 |
od | -0.085 |
disl | -0.084 |
Token | doll |
Token ID | 3654 |
Feature activation | -2.31e-03 |
Pos logit contributions | |
Mom | +0.029 |
ara | +0.028 |
crib | +0.028 |
um | +0.026 |
brow | +0.026 |
Neg logit contributions | |
vell | -0.054 |
wheel | -0.052 |
disl | -0.050 |
inations | -0.046 |
od | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +5.83e-04 |
Pos logit contributions | |
vell | +0.005 |
wheel | +0.005 |
disl | +0.004 |
inations | +0.004 |
od | +0.004 |
Neg logit contributions | |
crib | -0.003 |
ara | -0.003 |
Mom | -0.003 |
mom | -0.003 |
Sunny | -0.003 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
crib | +0.001 |
ara | +0.001 |
beef | +0.001 |
Mom | +0.001 |
chicken | +0.001 |
Neg logit contributions | |
vell | -0.001 |
wheel | -0.001 |
disl | -0.001 |
od | -0.001 |
cher | -0.001 |
Token | well |
Token ID | 880 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
Mom | +0.255 |
beef | +0.247 |
ham | +0.238 |
crib | +0.235 |
cash | +0.229 |
Neg logit contributions | |
vell | -0.403 |
wheel | -0.359 |
disl | -0.353 |
inations | -0.352 |
cast | -0.338 |
Token | ." |
Token ID | 526 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
crib | +0.076 |
ara | +0.075 |
Mom | +0.074 |
mom | +0.069 |
Sunny | +0.066 |
Neg logit contributions | |
vell | -0.117 |
wheel | -0.108 |
disl | -0.102 |
inations | -0.101 |
od | -0.100 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
disl | +0.040 |
wheel | +0.039 |
vell | +0.039 |
od | +0.037 |
inations | +0.036 |
Neg logit contributions | |
crib | -0.029 |
End | -0.027 |
Mom | -0.027 |
beef | -0.027 |
ara | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
vell | +0.030 |
wheel | +0.029 |
inations | +0.026 |
disl | +0.026 |
od | +0.026 |
Neg logit contributions | |
crib | -0.025 |
Mom | -0.023 |
ara | -0.023 |
beef | -0.023 |
kitten | -0.022 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
ara | +0.020 |
crib | +0.019 |
Mom | +0.018 |
ham | +0.017 |
beef | +0.017 |
Neg logit contributions | |
vell | -0.028 |
wheel | -0.026 |
disl | -0.024 |
inations | -0.024 |
od | -0.024 |
Token | dog |
Token ID | 3290 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
End | +0.038 |
Mom | +0.036 |
um | +0.034 |
ara | +0.033 |
brow | +0.033 |
Neg logit contributions | |
vell | -0.082 |
wheel | -0.072 |
od | -0.070 |
ologist | -0.069 |
disl | -0.067 |
Token | named |
Token ID | 3706 |
Feature activation | +9.41e-03 |
Pos logit contributions | |
ara | +0.057 |
crib | +0.056 |
Mom | +0.054 |
End | +0.054 |
um | +0.053 |
Neg logit contributions | |
vell | -0.061 |
wheel | -0.061 |
od | -0.057 |
smart | -0.056 |
disl | -0.055 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
End | +0.014 |
ara | +0.013 |
crib | +0.013 |
um | +0.012 |
Mom | +0.012 |
Neg logit contributions | |
vell | -0.019 |
wheel | -0.018 |
disl | -0.017 |
od | -0.016 |
inations | -0.016 |
Token | y |
Token ID | 88 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
beef | +0.259 |
ham | +0.245 |
crib | +0.243 |
cash | +0.241 |
Mom | +0.238 |
Neg logit contributions | |
vell | -0.397 |
disl | -0.342 |
od | -0.333 |
ont | -0.327 |
wheel | -0.323 |
Token | . |
Token ID | 13 |
Feature activation | -8.39e-03 |
Pos logit contributions | |
ara | +0.065 |
crib | +0.061 |
End | +0.061 |
Mom | +0.060 |
beef | +0.060 |
Neg logit contributions | |
vell | -0.056 |
od | -0.051 |
wheel | -0.051 |
disl | -0.045 |
ophone | -0.045 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
wheel | +0.014 |
vell | +0.013 |
achieve | +0.013 |
smart | +0.013 |
od | +0.012 |
Neg logit contributions | |
End | -0.012 |
um | -0.011 |
ara | -0.011 |
end | -0.010 |
Mom | -0.010 |
Token | y |
Token ID | 88 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
beef | +0.262 |
crib | +0.249 |
cash | +0.247 |
vet | +0.246 |
Mom | +0.246 |
Neg logit contributions | |
vell | -0.390 |
disl | -0.351 |
cast | -0.333 |
wheel | -0.331 |
ont | -0.331 |
Token | was |
Token ID | 373 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
crib | +0.054 |
beef | +0.053 |
Mom | +0.052 |
ara | +0.052 |
um | +0.048 |
Neg logit contributions | |
vell | -0.069 |
wheel | -0.067 |
od | -0.065 |
disl | -0.063 |
inations | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
ara | +0.020 |
� | +0.017 |
vet | +0.016 |
cash | +0.016 |
Mom | +0.016 |
Neg logit contributions | |
vell | -0.017 |
supposed | -0.017 |
wheel | -0.016 |
inations | -0.015 |
od | -0.015 |
Token | very |
Token ID | 845 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ara | +0.018 |
um | +0.018 |
End | +0.017 |
brow | +0.017 |
eyes | +0.016 |
Neg logit contributions | |
vell | -0.023 |
wheel | -0.020 |
disl | -0.018 |
cest | -0.018 |
inations | -0.018 |
Token | sleepy |
Token ID | 42023 |
Feature activation | -4.51e-03 |
Pos logit contributions | |
vell | +0.029 |
disl | +0.026 |
inations | +0.025 |
wheel | +0.025 |
cast | +0.022 |
Neg logit contributions | |
ara | -0.021 |
Mom | -0.021 |
crib | -0.020 |
End | -0.019 |
cash | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | +9.13e-03 |
Pos logit contributions | |
vell | +0.049 |
od | +0.047 |
wheel | +0.047 |
disl | +0.045 |
achieve | +0.043 |
Neg logit contributions | |
crib | -0.029 |
Mom | -0.027 |
ara | -0.026 |
beef | -0.026 |
ham | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ara | +0.014 |
crib | +0.013 |
therapist | +0.012 |
Mom | +0.012 |
nurse | +0.012 |
Neg logit contributions | |
vell | -0.017 |
wheel | -0.016 |
od | -0.016 |
supposed | -0.015 |
disl | -0.015 |
Token | little |
Token ID | 1310 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
crib | +0.012 |
ara | +0.012 |
um | +0.012 |
brow | +0.011 |
Mom | +0.011 |
Neg logit contributions | |
vell | -0.024 |
wheel | -0.021 |
od | -0.021 |
disl | -0.020 |
inations | -0.020 |
Token | dog |
Token ID | 3290 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
End | +0.038 |
Mom | +0.036 |
um | +0.034 |
ara | +0.033 |
brow | +0.033 |
Neg logit contributions | |
vell | -0.082 |
wheel | -0.072 |
od | -0.070 |
ologist | -0.069 |
disl | -0.067 |
Token | named |
Token ID | 3706 |
Feature activation | +9.41e-03 |
Pos logit contributions | |
ara | +0.057 |
crib | +0.056 |
Mom | +0.054 |
End | +0.054 |
um | +0.053 |
Neg logit contributions | |
vell | -0.061 |
wheel | -0.061 |
od | -0.057 |
smart | -0.056 |
disl | -0.055 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
End | +0.014 |
ara | +0.013 |
crib | +0.013 |
um | +0.012 |
Mom | +0.012 |
Neg logit contributions | |
vell | -0.019 |
wheel | -0.018 |
disl | -0.017 |
od | -0.016 |
inations | -0.016 |
Token | y |
Token ID | 88 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
beef | +0.259 |
ham | +0.245 |
crib | +0.243 |
cash | +0.241 |
Mom | +0.238 |
Neg logit contributions | |
vell | -0.397 |
disl | -0.342 |
od | -0.333 |
ont | -0.327 |
wheel | -0.323 |
Token | . |
Token ID | 13 |
Feature activation | -8.39e-03 |
Pos logit contributions | |
ara | +0.065 |
crib | +0.061 |
End | +0.061 |
Mom | +0.060 |
beef | +0.060 |
Neg logit contributions | |
vell | -0.056 |
od | -0.051 |
wheel | -0.051 |
disl | -0.045 |
ophone | -0.045 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
wheel | +0.014 |
vell | +0.013 |
achieve | +0.013 |
smart | +0.013 |
od | +0.012 |
Neg logit contributions | |
End | -0.012 |
um | -0.011 |
ara | -0.011 |
end | -0.010 |
Mom | -0.010 |
Token | y |
Token ID | 88 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
beef | +0.262 |
crib | +0.249 |
cash | +0.247 |
vet | +0.246 |
Mom | +0.246 |
Neg logit contributions | |
vell | -0.390 |
disl | -0.351 |
cast | -0.333 |
wheel | -0.331 |
ont | -0.331 |
Token | was |
Token ID | 373 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
crib | +0.054 |
beef | +0.053 |
Mom | +0.052 |
ara | +0.052 |
um | +0.048 |
Neg logit contributions | |
vell | -0.069 |
wheel | -0.067 |
od | -0.065 |
disl | -0.063 |
inations | -0.062 |
Token | Good |
Token ID | 10248 |
Feature activation | -9.91e-03 |
Pos logit contributions | |
crib | +0.046 |
ara | +0.042 |
mom | +0.040 |
Mom | +0.038 |
Sunny | +0.037 |
Neg logit contributions | |
vell | -0.087 |
wheel | -0.083 |
disl | -0.078 |
inations | -0.076 |
od | -0.076 |
Token | night |
Token ID | 1755 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
vell | +0.023 |
wheel | +0.022 |
disl | +0.021 |
od | +0.020 |
inations | +0.020 |
Neg logit contributions | |
crib | -0.013 |
Mom | -0.012 |
ara | -0.012 |
Sunny | -0.011 |
mom | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
crib | +0.039 |
ara | +0.038 |
Mom | +0.037 |
mom | +0.034 |
Sunny | +0.032 |
Neg logit contributions | |
vell | -0.091 |
wheel | -0.085 |
disl | -0.081 |
inations | -0.080 |
od | -0.080 |
Token | drum |
Token ID | 13026 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
crib | +0.021 |
ara | +0.021 |
Mom | +0.020 |
mom | +0.019 |
bunny | +0.018 |
Neg logit contributions | |
vell | -0.048 |
wheel | -0.045 |
disl | -0.043 |
inations | -0.043 |
od | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -2.41e-03 |
Pos logit contributions | |
vell | +0.256 |
wheel | +0.229 |
disl | +0.223 |
inations | +0.222 |
od | +0.219 |
Neg logit contributions | |
crib | -0.167 |
ara | -0.163 |
Mom | -0.154 |
mom | -0.153 |
bunny | -0.148 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
vell | +0.006 |
wheel | +0.006 |
inations | +0.005 |
disl | +0.005 |
od | +0.005 |
Neg logit contributions | |
crib | -0.003 |
ara | -0.003 |
Mom | -0.003 |
mom | -0.003 |
Sunny | -0.002 |
Token | well |
Token ID | 880 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
Mom | +0.245 |
crib | +0.242 |
ara | +0.234 |
beef | +0.222 |
ham | +0.222 |
Neg logit contributions | |
vell | -0.426 |
wheel | -0.386 |
inations | -0.377 |
disl | -0.376 |
od | -0.359 |
Token | ." |
Token ID | 526 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
crib | +0.069 |
ara | +0.067 |
Mom | +0.064 |
mom | +0.061 |
Sunny | +0.059 |
Neg logit contributions | |
vell | -0.120 |
wheel | -0.110 |
disl | -0.105 |
od | -0.104 |
inations | -0.104 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
vell | +0.056 |
wheel | +0.053 |
disl | +0.051 |
inations | +0.050 |
od | +0.050 |
Neg logit contributions | |
crib | -0.024 |
ara | -0.024 |
Mom | -0.023 |
End | -0.020 |
mom | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
vell | +0.029 |
wheel | +0.027 |
disl | +0.026 |
inations | +0.026 |
od | +0.026 |
Neg logit contributions | |
crib | -0.011 |
ara | -0.011 |
Mom | -0.010 |
bunny | -0.009 |
mom | -0.009 |
Token | The |
Token ID | 464 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
vell | +0.024 |
wheel | +0.023 |
disl | +0.022 |
inations | +0.021 |
od | +0.021 |
Neg logit contributions | |
crib | -0.015 |
ara | -0.013 |
mom | -0.013 |
Mom | -0.012 |
bunny | -0.012 |
Token | you |
Token ID | 345 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
crib | +0.011 |
ara | +0.011 |
Mom | +0.011 |
mom | +0.010 |
bunny | +0.010 |
Neg logit contributions | |
vell | -0.020 |
wheel | -0.018 |
disl | -0.018 |
inations | -0.017 |
od | -0.017 |
Token | need |
Token ID | 761 |
Feature activation | +3.93e-03 |
Pos logit contributions | |
vell | +0.051 |
wheel | +0.047 |
disl | +0.047 |
od | +0.045 |
cast | +0.045 |
Neg logit contributions | |
mom | -0.032 |
Mom | -0.030 |
crib | -0.030 |
bunny | -0.029 |
ara | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -5.76e-03 |
Pos logit contributions | |
ara | +0.006 |
crib | +0.006 |
Mom | +0.005 |
End | +0.005 |
um | +0.005 |
Neg logit contributions | |
vell | -0.008 |
wheel | -0.008 |
disl | -0.007 |
inations | -0.007 |
smart | -0.007 |
Token | sleep |
Token ID | 3993 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
vell | +0.012 |
wheel | +0.011 |
disl | +0.011 |
inations | +0.011 |
od | +0.010 |
Neg logit contributions | |
crib | -0.009 |
ara | -0.009 |
Mom | -0.008 |
mom | -0.008 |
Sunny | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
crib | +0.105 |
ara | +0.104 |
Mom | +0.101 |
mom | +0.094 |
Sunny | +0.090 |
Neg logit contributions | |
vell | -0.187 |
wheel | -0.172 |
disl | -0.163 |
inations | -0.162 |
od | -0.160 |
Token | Sleep |
Token ID | 17376 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
vell | +0.027 |
wheel | +0.026 |
disl | +0.025 |
asing | +0.024 |
smart | +0.023 |
Neg logit contributions | |
crib | -0.021 |
ara | -0.020 |
Mom | -0.019 |
End | -0.018 |
blanket | -0.018 |
Token | will |
Token ID | 481 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
crib | +0.237 |
Mom | +0.237 |
ara | +0.230 |
mom | +0.212 |
beef | +0.209 |
Neg logit contributions | |
vell | -0.435 |
wheel | -0.401 |
disl | -0.387 |
inations | -0.381 |
od | -0.371 |
Token | help |
Token ID | 1037 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
crib | +0.038 |
ara | +0.037 |
Mom | +0.037 |
mom | +0.035 |
Sunny | +0.034 |
Neg logit contributions | |
vell | -0.065 |
wheel | -0.059 |
disl | -0.057 |
od | -0.056 |
inations | -0.056 |
Token | you |
Token ID | 345 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
vell | +0.038 |
wheel | +0.036 |
inations | +0.034 |
disl | +0.034 |
od | +0.034 |
Neg logit contributions | |
crib | -0.015 |
ara | -0.014 |
Mom | -0.013 |
End | -0.012 |
mom | -0.012 |
Token | feel |
Token ID | 1254 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
vell | +0.049 |
wheel | +0.045 |
disl | +0.043 |
od | +0.043 |
inations | +0.042 |
Neg logit contributions | |
crib | -0.032 |
ara | -0.030 |
Mom | -0.030 |
mom | -0.029 |
bunny | -0.028 |
Token | better |
Token ID | 1365 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
vell | +0.113 |
wheel | +0.104 |
disl | +0.099 |
inations | +0.098 |
od | +0.093 |
Neg logit contributions | |
ara | -0.079 |
crib | -0.078 |
Mom | -0.075 |
mom | -0.069 |
Sunny | -0.067 |
Token | house |
Token ID | 2156 |
Feature activation | -6.83e-03 |
Pos logit contributions | |
ara | +0.002 |
Mom | +0.002 |
crib | +0.002 |
Sunny | +0.002 |
um | +0.002 |
Neg logit contributions | |
vell | -0.004 |
disl | -0.003 |
wheel | -0.003 |
inations | -0.003 |
od | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
vell | +0.017 |
wheel | +0.016 |
od | +0.015 |
disl | +0.015 |
inations | +0.015 |
Neg logit contributions | |
crib | -0.008 |
ara | -0.008 |
Mom | -0.008 |
mom | -0.007 |
Sunny | -0.007 |
Token | our |
Token ID | 674 |
Feature activation | +2.71e-03 |
Pos logit contributions | |
crib | +0.015 |
ara | +0.015 |
Mom | +0.015 |
mom | +0.013 |
Sunny | +0.013 |
Neg logit contributions | |
vell | -0.029 |
wheel | -0.027 |
disl | -0.026 |
inations | -0.026 |
od | -0.025 |
Token | family |
Token ID | 1641 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
ara | +0.003 |
crib | +0.003 |
Mom | +0.003 |
Sunny | +0.003 |
um | +0.002 |
Neg logit contributions | |
vell | -0.007 |
wheel | -0.006 |
disl | -0.006 |
inations | -0.006 |
od | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
vell | +0.029 |
wheel | +0.027 |
disl | +0.025 |
inations | +0.025 |
od | +0.025 |
Neg logit contributions | |
crib | -0.022 |
ara | -0.021 |
Mom | -0.021 |
mom | -0.020 |
Sunny | -0.019 |
Token | Amen |
Token ID | 34717 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
crib | +0.019 |
ara | +0.019 |
End | +0.016 |
blanket | +0.016 |
um | +0.016 |
Neg logit contributions | |
vell | -0.028 |
disl | -0.027 |
wheel | -0.026 |
od | -0.024 |
smart | -0.024 |
Token | ." |
Token ID | 526 |
Feature activation | -9.53e-03 |
Pos logit contributions | |
crib | +0.366 |
ara | +0.350 |
bunny | +0.344 |
beef | +0.340 |
Sunny | +0.339 |
Neg logit contributions | |
vell | -0.263 |
wheel | -0.244 |
disl | -0.236 |
inations | -0.234 |
od | -0.229 |
Token |
|
Token ID | 198 |
Feature activation | +2.10e-03 |
Pos logit contributions | |
disl | +0.018 |
vell | +0.018 |
od | +0.018 |
wheel | +0.017 |
achieve | +0.017 |
Neg logit contributions | |
crib | -0.013 |
End | -0.012 |
Mom | -0.012 |
ara | -0.012 |
end | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.85e-03 |
Pos logit contributions | |
crib | +0.003 |
ara | +0.003 |
bunny | +0.003 |
kitten | +0.003 |
brow | +0.003 |
Neg logit contributions | |
vell | -0.004 |
disl | -0.004 |
od | -0.004 |
wheel | -0.004 |
achieve | -0.004 |
Token | Mom |
Token ID | 29252 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
crib | +0.003 |
night | +0.003 |
eyes | +0.003 |
brow | +0.003 |
blanket | +0.003 |
Neg logit contributions | |
achieve | -0.003 |
vell | -0.003 |
disl | -0.003 |
od | -0.003 |
wheel | -0.003 |
Token | smiled |
Token ID | 13541 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
crib | +0.147 |
ara | +0.130 |
Mom | +0.127 |
beef | +0.125 |
Sunny | +0.125 |
Neg logit contributions | |
vell | -0.211 |
wheel | -0.200 |
od | -0.184 |
inations | -0.182 |
cher | -0.181 |
Token | family |
Token ID | 1641 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
Mom | +0.005 |
ara | +0.004 |
um | +0.004 |
Goose | +0.004 |
Sunny | +0.004 |
Neg logit contributions | |
vell | -0.009 |
disl | -0.009 |
inations | -0.008 |
cast | -0.008 |
ologist | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
vell | +0.026 |
wheel | +0.024 |
inations | +0.022 |
disl | +0.022 |
od | +0.022 |
Neg logit contributions | |
crib | -0.020 |
ara | -0.020 |
Mom | -0.019 |
mom | -0.018 |
Sunny | -0.017 |
Token | our |
Token ID | 674 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
ara | +0.014 |
crib | +0.013 |
Mom | +0.013 |
um | +0.012 |
End | +0.012 |
Neg logit contributions | |
vell | -0.030 |
wheel | -0.028 |
disl | -0.028 |
inations | -0.027 |
cher | -0.026 |
Token | friends |
Token ID | 2460 |
Feature activation | -7.04e-02 |
Pos logit contributions | |
ara | +0.007 |
Mom | +0.006 |
um | +0.006 |
crib | +0.005 |
Sunny | +0.005 |
Neg logit contributions | |
vell | -0.011 |
disl | -0.010 |
inations | -0.010 |
wheel | -0.009 |
cast | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
vell | +0.135 |
wheel | +0.122 |
inations | +0.114 |
disl | +0.114 |
od | +0.112 |
Neg logit contributions | |
crib | -0.122 |
ara | -0.121 |
Mom | -0.118 |
mom | -0.110 |
Sunny | -0.108 |
Token | Amen |
Token ID | 34717 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ara | +0.017 |
crib | +0.016 |
um | +0.015 |
End | +0.015 |
basket | +0.014 |
Neg logit contributions | |
vell | -0.026 |
disl | -0.025 |
wheel | -0.025 |
cher | -0.023 |
smart | -0.023 |
Token | ." |
Token ID | 526 |
Feature activation | -9.47e-03 |
Pos logit contributions | |
crib | +0.375 |
ara | +0.364 |
beef | +0.355 |
bunny | +0.355 |
kitten | +0.351 |
Neg logit contributions | |
vell | -0.242 |
wheel | -0.224 |
inations | -0.214 |
disl | -0.213 |
od | -0.209 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-03 |
Pos logit contributions | |
disl | +0.015 |
od | +0.014 |
smart | +0.014 |
achieve | +0.014 |
wheel | +0.014 |
Neg logit contributions | |
um | -0.014 |
crib | -0.014 |
ara | -0.014 |
End | -0.014 |
kitten | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
crib | +0.002 |
ara | +0.002 |
ham | +0.002 |
kitten | +0.002 |
bunny | +0.002 |
Neg logit contributions | |
vell | -0.003 |
disl | -0.003 |
wheel | -0.003 |
achieve | -0.003 |
od | -0.003 |
Token | Anna |
Token ID | 31160 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
eyes | +0.003 |
tum | +0.003 |
kitten | +0.003 |
um | +0.003 |
Goose | +0.003 |
Neg logit contributions | |
achieve | -0.004 |
vell | -0.003 |
disl | -0.003 |
smart | -0.003 |
wheel | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
crib | +0.142 |
beef | +0.132 |
Mom | +0.129 |
ara | +0.127 |
kitten | +0.124 |
Neg logit contributions | |
vell | -0.169 |
wheel | -0.157 |
od | -0.147 |
disl | -0.144 |
inations | -0.143 |
Token | , |
Token ID | 11 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
vell | +0.021 |
wheel | +0.019 |
disl | +0.019 |
od | +0.019 |
smart | +0.018 |
Neg logit contributions | |
Mom | -0.010 |
ara | -0.010 |
crib | -0.010 |
End | -0.009 |
nurse | -0.008 |
Token | I |
Token ID | 314 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ara | +0.018 |
crib | +0.018 |
Mom | +0.017 |
mom | +0.016 |
um | +0.015 |
Neg logit contributions | |
vell | -0.035 |
wheel | -0.032 |
disl | -0.031 |
inations | -0.030 |
od | -0.030 |
Token | can |
Token ID | 460 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
mom | +0.018 |
ara | +0.018 |
Mom | +0.018 |
crib | +0.017 |
bunny | +0.017 |
Neg logit contributions | |
vell | -0.039 |
wheel | -0.036 |
disl | -0.035 |
od | -0.034 |
inations | -0.034 |
Token | help |
Token ID | 1037 |
Feature activation | -8.33e-03 |
Pos logit contributions | |
vell | +0.096 |
wheel | +0.088 |
disl | +0.084 |
inations | +0.083 |
od | +0.082 |
Neg logit contributions | |
crib | -0.069 |
ara | -0.068 |
Mom | -0.067 |
mom | -0.064 |
bunny | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
vell | +0.020 |
wheel | +0.018 |
disl | +0.017 |
inations | +0.017 |
od | +0.017 |
Neg logit contributions | |
crib | -0.011 |
ara | -0.011 |
Mom | -0.011 |
mom | -0.010 |
Sunny | -0.010 |
Token | Close |
Token ID | 13872 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
vell | +0.034 |
wheel | +0.032 |
disl | +0.030 |
inations | +0.029 |
od | +0.029 |
Neg logit contributions | |
crib | -0.023 |
ara | -0.023 |
Mom | -0.021 |
beef | -0.020 |
mom | -0.020 |
Token | your |
Token ID | 534 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
crib | +0.239 |
ara | +0.235 |
Mom | +0.229 |
mom | +0.211 |
Sunny | +0.204 |
Neg logit contributions | |
vell | -0.414 |
wheel | -0.379 |
disl | -0.364 |
inations | -0.360 |
od | -0.356 |
Token | eyes |
Token ID | 2951 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
ara | +0.024 |
Mom | +0.021 |
crib | +0.019 |
Me | +0.019 |
Sunny | +0.019 |
Neg logit contributions | |
vell | -0.036 |
disl | -0.031 |
achieve | -0.031 |
inations | -0.031 |
smart | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
crib | +0.061 |
ara | +0.058 |
Mom | +0.056 |
mom | +0.052 |
Sunny | +0.049 |
Neg logit contributions | |
vell | -0.188 |
wheel | -0.177 |
disl | -0.175 |
inations | -0.169 |
od | -0.168 |
Token | make |
Token ID | 787 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
vell | +0.028 |
wheel | +0.025 |
disl | +0.024 |
inations | +0.024 |
od | +0.023 |
Neg logit contributions | |
crib | -0.019 |
ara | -0.018 |
Mom | -0.018 |
mom | -0.016 |
Sunny | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
vell | +0.036 |
wheel | +0.033 |
disl | +0.032 |
inations | +0.031 |
od | +0.031 |
Neg logit contributions | |
crib | -0.023 |
ara | -0.022 |
Mom | -0.022 |
mom | -0.021 |
Sunny | -0.021 |
Token | Fl |
Token ID | 1610 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
crib | +0.010 |
ara | +0.010 |
mom | +0.010 |
Mom | +0.010 |
Sunny | +0.010 |
Neg logit contributions | |
vell | -0.022 |
wheel | -0.020 |
disl | -0.020 |
inations | -0.020 |
asing | -0.019 |
Token | oppy |
Token ID | 26696 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
crib | +0.102 |
Mom | +0.102 |
Sunny | +0.092 |
beef | +0.092 |
nurse | +0.090 |
Neg logit contributions | |
vell | -0.148 |
od | -0.132 |
wheel | -0.127 |
asing | -0.125 |
disl | -0.125 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
vell | +0.084 |
wheel | +0.076 |
disl | +0.074 |
inations | +0.073 |
od | +0.071 |
Neg logit contributions | |
ara | -0.040 |
crib | -0.039 |
Mom | -0.038 |
mom | -0.036 |
bunny | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +7.22e-03 |
Pos logit contributions | |
vell | +0.110 |
wheel | +0.100 |
inations | +0.098 |
disl | +0.096 |
od | +0.095 |
Neg logit contributions | |
crib | -0.045 |
ara | -0.042 |
mom | -0.042 |
Mom | -0.041 |
bunny | -0.038 |
Token | mar |
Token ID | 1667 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ara | +0.009 |
crib | +0.009 |
Mom | +0.009 |
Sunny | +0.008 |
um | +0.008 |
Neg logit contributions | |
vell | -0.017 |
wheel | -0.015 |
inations | -0.014 |
od | -0.014 |
disl | -0.014 |
Token | vell |
Token ID | 29333 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
disl | +0.255 |
inations | +0.179 |
wheel | +0.176 |
smart | +0.175 |
supposed | +0.171 |
Neg logit contributions | |
ara | -0.324 |
um | -0.321 |
Mom | -0.306 |
crib | -0.303 |
bunny | -0.300 |
Token | ous |
Token ID | 516 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
disl | +0.523 |
vell | +0.450 |
inations | +0.433 |
wheel | +0.432 |
achieve | +0.420 |
Neg logit contributions | |
crib | -0.570 |
um | -0.554 |
ara | -0.543 |
bunny | -0.535 |
Mom | -0.529 |
Token | view |
Token ID | 1570 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
vell | +0.170 |
wheel | +0.155 |
disl | +0.147 |
inations | +0.147 |
od | +0.144 |
Neg logit contributions | |
crib | -0.096 |
ara | -0.092 |
Mom | -0.087 |
mom | -0.085 |
bunny | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
vell | +0.074 |
disl | +0.068 |
wheel | +0.067 |
inations | +0.066 |
od | +0.064 |
Neg logit contributions | |
crib | -0.030 |
ara | -0.029 |
Mom | -0.027 |
mom | -0.026 |
Sunny | -0.025 |
Token | He |
Token ID | 679 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
vell | +0.035 |
wheel | +0.033 |
disl | +0.031 |
od | +0.031 |
cher | +0.029 |
Neg logit contributions | |
crib | -0.022 |
ara | -0.022 |
Mom | -0.022 |
End | -0.020 |
mom | -0.020 |
Token | also |
Token ID | 635 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
vell | +0.033 |
wheel | +0.030 |
disl | +0.029 |
inations | +0.029 |
od | +0.029 |
Neg logit contributions | |
crib | -0.021 |
ara | -0.020 |
Mom | -0.019 |
mom | -0.018 |
Sunny | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
crib | +0.004 |
ara | +0.004 |
Mom | +0.004 |
mom | +0.004 |
Sunny | +0.004 |
Neg logit contributions | |
vell | -0.010 |
wheel | -0.009 |
disl | -0.009 |
inations | -0.009 |
od | -0.009 |
Token | laughed |
Token ID | 13818 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
crib | +0.020 |
ara | +0.019 |
Mom | +0.019 |
mom | +0.019 |
Sunny | +0.018 |
Neg logit contributions | |
vell | -0.028 |
wheel | -0.025 |
od | -0.024 |
disl | -0.024 |
inations | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
crib | +0.033 |
ara | +0.033 |
Mom | +0.031 |
mom | +0.028 |
End | +0.027 |
Neg logit contributions | |
vell | -0.079 |
wheel | -0.074 |
disl | -0.070 |
od | -0.069 |
inations | -0.069 |
Token | built |
Token ID | 3170 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
vell | +0.036 |
wheel | +0.032 |
inations | +0.032 |
disl | +0.031 |
od | +0.031 |
Neg logit contributions | |
crib | -0.021 |
mom | -0.021 |
Mom | -0.021 |
ara | -0.020 |
Sunny | -0.020 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
vell | +0.083 |
wheel | +0.077 |
disl | +0.074 |
od | +0.072 |
inations | +0.072 |
Neg logit contributions | |
ara | -0.038 |
crib | -0.038 |
Mom | -0.037 |
mom | -0.033 |
Sunny | -0.032 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
vell | +0.127 |
wheel | +0.119 |
disl | +0.119 |
inations | +0.115 |
asing | +0.108 |
Neg logit contributions | |
crib | -0.153 |
mom | -0.151 |
ara | -0.151 |
bunny | -0.142 |
Mom | -0.142 |
Token | les |
Token ID | 829 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
vell | +0.681 |
wheel | +0.629 |
disl | +0.612 |
inations | +0.581 |
od | +0.570 |
Neg logit contributions | |
ara | -0.439 |
crib | -0.415 |
Mom | -0.392 |
Sunny | -0.376 |
mom | -0.374 |
Token | . |
Token ID | 13 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
vell | +0.193 |
wheel | +0.177 |
disl | +0.174 |
inations | +0.171 |
od | +0.165 |
Neg logit contributions | |
crib | -0.079 |
ara | -0.075 |
Mom | -0.071 |
mom | -0.070 |
bunny | -0.066 |
Token | Soon |
Token ID | 15894 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
vell | +0.032 |
wheel | +0.030 |
disl | +0.029 |
od | +0.028 |
inations | +0.028 |
Neg logit contributions | |
crib | -0.013 |
ara | -0.013 |
Mom | -0.012 |
mom | -0.011 |
bunny | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +7.36e-03 |
Pos logit contributions | |
vell | +0.037 |
wheel | +0.034 |
disl | +0.033 |
inations | +0.032 |
od | +0.032 |
Neg logit contributions | |
crib | -0.012 |
ara | -0.012 |
Mom | -0.011 |
mom | -0.010 |
Sunny | -0.010 |
Token | they |
Token ID | 484 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
crib | +0.008 |
ara | +0.008 |
Mom | +0.007 |
mom | +0.007 |
Sunny | +0.007 |
Neg logit contributions | |
vell | -0.019 |
wheel | -0.018 |
disl | -0.017 |
inations | -0.017 |
od | -0.017 |
Token | bucket |
Token ID | 19236 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
vell | +0.052 |
wheel | +0.048 |
disl | +0.045 |
inations | +0.044 |
od | +0.043 |
Neg logit contributions | |
crib | -0.039 |
ara | -0.038 |
Mom | -0.037 |
Sunny | -0.035 |
mom | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
vell | +0.129 |
wheel | +0.119 |
disl | +0.115 |
inations | +0.114 |
od | +0.112 |
Neg logit contributions | |
crib | -0.057 |
ara | -0.055 |
Mom | -0.054 |
mom | -0.050 |
Sunny | -0.047 |
Token | She |
Token ID | 1375 |
Feature activation | -2.87e-03 |
Pos logit contributions | |
vell | +0.052 |
wheel | +0.049 |
disl | +0.047 |
od | +0.047 |
inations | +0.046 |
Neg logit contributions | |
crib | -0.019 |
ara | -0.018 |
Mom | -0.017 |
mom | -0.015 |
bunny | -0.015 |
Token | made |
Token ID | 925 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
vell | +0.007 |
wheel | +0.006 |
disl | +0.006 |
inations | +0.006 |
od | +0.006 |
Neg logit contributions | |
crib | -0.004 |
ara | -0.004 |
Mom | -0.004 |
mom | -0.003 |
bunny | -0.003 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
crib | +0.018 |
mom | +0.017 |
ara | +0.016 |
Mom | +0.016 |
Mom | +0.015 |
Neg logit contributions | |
vell | -0.056 |
wheel | -0.052 |
disl | -0.050 |
inations | -0.050 |
ologist | -0.050 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
vell | +0.115 |
wheel | +0.111 |
disl | +0.110 |
inations | +0.104 |
asing | +0.102 |
Neg logit contributions | |
mom | -0.153 |
ara | -0.148 |
Mom | -0.145 |
crib | -0.144 |
Mom | -0.142 |
Token | les |
Token ID | 829 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
vell | +0.638 |
wheel | +0.583 |
disl | +0.561 |
inations | +0.544 |
od | +0.534 |
Neg logit contributions | |
ara | -0.459 |
crib | -0.448 |
Mom | -0.430 |
mom | -0.407 |
Sunny | -0.400 |
Token | and |
Token ID | 290 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
vell | +0.211 |
wheel | +0.193 |
disl | +0.193 |
inations | +0.190 |
ologist | +0.183 |
Neg logit contributions | |
crib | -0.060 |
ara | -0.055 |
Mom | -0.052 |
mom | -0.052 |
bunny | -0.048 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
vell | +0.046 |
wheel | +0.040 |
disl | +0.039 |
inations | +0.038 |
ologist | +0.038 |
Neg logit contributions | |
crib | -0.026 |
mom | -0.026 |
ara | -0.026 |
Mom | -0.025 |
Mom | -0.025 |
Token | pies |
Token ID | 47199 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
vell | +0.166 |
wheel | +0.158 |
disl | +0.157 |
inations | +0.156 |
asing | +0.148 |
Neg logit contributions | |
mom | -0.102 |
ara | -0.101 |
crib | -0.098 |
Mom | -0.092 |
Mom | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
vell | +0.335 |
disl | +0.325 |
inations | +0.311 |
wheel | +0.307 |
asing | +0.307 |
Neg logit contributions | |
mom | -0.067 |
crib | -0.066 |
ara | -0.065 |
Mom | -0.060 |
blanket | -0.060 |
Token | beach |
Token ID | 10481 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
vell | +0.072 |
wheel | +0.066 |
disl | +0.061 |
od | +0.061 |
achieve | +0.060 |
Neg logit contributions | |
crib | -0.040 |
ara | -0.040 |
Mom | -0.037 |
Sunny | -0.035 |
um | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
vell | +0.075 |
wheel | +0.069 |
disl | +0.068 |
inations | +0.066 |
asing | +0.065 |
Neg logit contributions | |
crib | -0.023 |
mom | -0.021 |
ara | -0.021 |
Mom | -0.019 |
Mom | -0.017 |
Token | They |
Token ID | 1119 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
vell | +0.038 |
wheel | +0.036 |
disl | +0.034 |
od | +0.034 |
inations | +0.033 |
Neg logit contributions | |
ara | -0.019 |
crib | -0.019 |
Mom | -0.019 |
End | -0.017 |
mom | -0.016 |
Token | made |
Token ID | 925 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
crib | +0.024 |
ara | +0.023 |
Mom | +0.022 |
mom | +0.021 |
Sunny | +0.020 |
Neg logit contributions | |
vell | -0.040 |
wheel | -0.037 |
inations | -0.035 |
disl | -0.035 |
od | -0.034 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
crib | +0.020 |
ara | +0.019 |
mom | +0.018 |
Mom | +0.018 |
Mom | +0.016 |
Neg logit contributions | |
vell | -0.054 |
wheel | -0.050 |
disl | -0.048 |
inations | -0.047 |
ologist | -0.047 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
wheel | +0.104 |
disl | +0.103 |
vell | +0.099 |
asing | +0.094 |
cher | +0.088 |
Neg logit contributions | |
mom | -0.164 |
crib | -0.153 |
ara | -0.153 |
Mom | -0.151 |
blanket | -0.150 |
Token | les |
Token ID | 829 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
vell | +0.648 |
wheel | +0.594 |
disl | +0.578 |
inations | +0.550 |
od | +0.542 |
Neg logit contributions | |
ara | -0.450 |
crib | -0.436 |
Mom | -0.418 |
mom | -0.399 |
Sunny | -0.393 |
Token | and |
Token ID | 290 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
vell | +0.226 |
disl | +0.213 |
wheel | +0.210 |
inations | +0.202 |
asing | +0.197 |
Neg logit contributions | |
crib | -0.048 |
mom | -0.041 |
bunny | -0.037 |
ara | -0.036 |
Sunny | -0.035 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
vell | +0.040 |
wheel | +0.035 |
disl | +0.035 |
asing | +0.034 |
inations | +0.034 |
Neg logit contributions | |
mom | -0.023 |
crib | -0.023 |
Mom | -0.023 |
ara | -0.022 |
Mom | -0.022 |
Token | through |
Token ID | 832 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
vell | +0.057 |
wheel | +0.051 |
disl | +0.050 |
asing | +0.049 |
ologist | +0.049 |
Neg logit contributions | |
crib | -0.027 |
mom | -0.025 |
ara | -0.024 |
Mom | -0.024 |
Mom | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
vell | +0.079 |
wheel | +0.074 |
disl | +0.070 |
inations | +0.070 |
od | +0.068 |
Neg logit contributions | |
crib | -0.030 |
ara | -0.029 |
Mom | -0.028 |
mom | -0.027 |
Sunny | -0.025 |
Token | while |
Token ID | 981 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
crib | +0.002 |
ara | +0.002 |
Mom | +0.002 |
mom | +0.001 |
Sunny | +0.001 |
Neg logit contributions | |
vell | -0.005 |
wheel | -0.005 |
inations | -0.005 |
disl | -0.004 |
od | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
crib | +0.102 |
ara | +0.100 |
Mom | +0.095 |
mom | +0.085 |
Sunny | +0.082 |
Neg logit contributions | |
vell | -0.273 |
wheel | -0.255 |
disl | -0.242 |
inations | -0.242 |
od | -0.241 |
Token | then |
Token ID | 788 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
crib | +0.005 |
ara | +0.005 |
mom | +0.005 |
Mom | +0.005 |
bunny | +0.004 |
Neg logit contributions | |
vell | -0.010 |
wheel | -0.009 |
disl | -0.009 |
inations | -0.008 |
od | -0.008 |
Token | built |
Token ID | 3170 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
crib | +0.087 |
ara | +0.085 |
Mom | +0.083 |
mom | +0.078 |
Sunny | +0.075 |
Neg logit contributions | |
vell | -0.144 |
wheel | -0.132 |
disl | -0.126 |
inations | -0.125 |
od | -0.124 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
vell | +0.081 |
wheel | +0.075 |
disl | +0.071 |
inations | +0.070 |
od | +0.070 |
Neg logit contributions | |
crib | -0.052 |
ara | -0.051 |
Mom | -0.049 |
mom | -0.046 |
Sunny | -0.044 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
vell | +0.086 |
disl | +0.083 |
wheel | +0.080 |
inations | +0.078 |
asing | +0.072 |
Neg logit contributions | |
ara | -0.178 |
mom | -0.177 |
crib | -0.177 |
Mom | -0.169 |
bunny | -0.169 |
Token | les |
Token ID | 829 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
vell | +0.644 |
wheel | +0.591 |
disl | +0.574 |
inations | +0.551 |
od | +0.543 |
Neg logit contributions | |
ara | -0.451 |
crib | -0.440 |
Mom | -0.420 |
mom | -0.398 |
Sunny | -0.393 |
Token | with |
Token ID | 351 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
vell | +0.206 |
disl | +0.188 |
wheel | +0.188 |
inations | +0.185 |
od | +0.178 |
Neg logit contributions | |
crib | -0.069 |
ara | -0.063 |
Mom | -0.059 |
mom | -0.059 |
bunny | -0.057 |
Token | his |
Token ID | 465 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
crib | +0.033 |
ara | +0.032 |
Mom | +0.032 |
mom | +0.031 |
Sunny | +0.028 |
Neg logit contributions | |
vell | -0.064 |
wheel | -0.059 |
disl | -0.057 |
inations | -0.056 |
od | -0.055 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
vell | +0.052 |
wheel | +0.050 |
disl | +0.046 |
od | +0.046 |
inations | +0.046 |
Neg logit contributions | |
crib | -0.021 |
mom | -0.020 |
ara | -0.020 |
Mom | -0.019 |
bunny | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
crib | +0.032 |
ara | +0.031 |
Mom | +0.031 |
mom | +0.030 |
bunny | +0.027 |
Neg logit contributions | |
vell | -0.082 |
wheel | -0.075 |
disl | -0.074 |
inations | -0.073 |
od | -0.070 |
Token | 't |
Token ID | 470 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
vell | +0.107 |
wheel | +0.096 |
disl | +0.093 |
inations | +0.093 |
od | +0.091 |
Neg logit contributions | |
crib | -0.061 |
ara | -0.060 |
Mom | -0.059 |
mom | -0.055 |
Sunny | -0.053 |
Token | wait |
Token ID | 4043 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
vell | +0.107 |
wheel | +0.095 |
disl | +0.093 |
inations | +0.091 |
od | +0.090 |
Neg logit contributions | |
Mom | -0.070 |
crib | -0.069 |
mom | -0.068 |
ara | -0.067 |
bunny | -0.064 |
Token | to |
Token ID | 284 |
Feature activation | -9.77e-03 |
Pos logit contributions | |
crib | +0.035 |
mom | +0.033 |
ara | +0.032 |
Mom | +0.030 |
Mom | +0.029 |
Neg logit contributions | |
vell | -0.119 |
wheel | -0.110 |
disl | -0.106 |
cher | -0.103 |
ologist | -0.103 |
Token | make |
Token ID | 787 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
vell | +0.025 |
wheel | +0.022 |
asing | +0.022 |
cher | +0.021 |
disl | +0.021 |
Neg logit contributions | |
mom | -0.012 |
crib | -0.012 |
Mom | -0.011 |
Mom | -0.011 |
bunny | -0.011 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
vell | +0.077 |
wheel | +0.071 |
ologist | +0.068 |
inations | +0.068 |
cher | +0.068 |
Neg logit contributions | |
mom | -0.022 |
crib | -0.022 |
ara | -0.020 |
Mom | -0.020 |
chicken | -0.019 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
disl | +0.084 |
wheel | +0.084 |
vell | +0.083 |
asing | +0.081 |
inations | +0.076 |
Neg logit contributions | |
mom | -0.164 |
crib | -0.156 |
bunny | -0.154 |
ara | -0.153 |
blanket | -0.152 |
Token | les |
Token ID | 829 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
vell | +0.654 |
wheel | +0.598 |
disl | +0.578 |
inations | +0.559 |
od | +0.548 |
Neg logit contributions | |
ara | -0.442 |
crib | -0.431 |
Mom | -0.406 |
Sunny | -0.388 |
mom | -0.387 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
vell | +0.196 |
wheel | +0.178 |
disl | +0.178 |
inations | +0.175 |
ologist | +0.168 |
Neg logit contributions | |
crib | -0.076 |
ara | -0.070 |
mom | -0.067 |
Mom | -0.066 |
bunny | -0.065 |
Token | |
Token ID | 220 |
Feature activation | -1.81e-03 |
Pos logit contributions | |
vell | +0.034 |
wheel | +0.032 |
disl | +0.031 |
inations | +0.030 |
od | +0.030 |
Neg logit contributions | |
crib | -0.011 |
ara | -0.011 |
Mom | -0.010 |
mom | -0.009 |
Sunny | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
vell | +0.006 |
wheel | +0.005 |
disl | +0.005 |
inations | +0.005 |
ologist | +0.005 |
Neg logit contributions | |
ara | -0.001 |
Mom | -0.001 |
crib | -0.001 |
mom | -0.001 |
Mom | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
vell | +0.074 |
wheel | +0.068 |
disl | +0.066 |
inations | +0.066 |
od | +0.065 |
Neg logit contributions | |
ara | -0.021 |
Mom | -0.021 |
crib | -0.021 |
mom | -0.018 |
Sunny | -0.017 |
Token | play |
Token ID | 711 |
Feature activation | +9.55e-03 |
Pos logit contributions | |
vell | +0.005 |
wheel | +0.005 |
inations | +0.004 |
asing | +0.004 |
cher | +0.004 |
Neg logit contributions | |
crib | -0.002 |
Mom | -0.002 |
mom | -0.002 |
ara | -0.002 |
bunny | -0.002 |
Token | outside |
Token ID | 2354 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
ara | +0.013 |
crib | +0.012 |
Mom | +0.012 |
End | +0.011 |
mom | +0.011 |
Neg logit contributions | |
vell | -0.022 |
wheel | -0.021 |
od | -0.019 |
disl | -0.019 |
inations | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ara | +0.037 |
End | +0.031 |
Mom | +0.031 |
vet | +0.031 |
ham | +0.031 |
Neg logit contributions | |
vell | -0.035 |
wheel | -0.033 |
od | -0.033 |
cast | -0.030 |
smart | -0.030 |
Token | make |
Token ID | 787 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
vell | +0.028 |
wheel | +0.026 |
disl | +0.024 |
inations | +0.024 |
od | +0.024 |
Neg logit contributions | |
crib | -0.023 |
ara | -0.023 |
Mom | -0.022 |
mom | -0.021 |
Sunny | -0.020 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
vell | +0.055 |
wheel | +0.050 |
inations | +0.048 |
disl | +0.047 |
cher | +0.047 |
Neg logit contributions | |
crib | -0.029 |
ara | -0.027 |
Mom | -0.026 |
mom | -0.026 |
bunny | -0.024 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
vell | +0.098 |
disl | +0.098 |
wheel | +0.096 |
asing | +0.089 |
inations | +0.088 |
Neg logit contributions | |
mom | -0.157 |
crib | -0.154 |
ara | -0.152 |
Mom | -0.151 |
blanket | -0.146 |
Token | les |
Token ID | 829 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
vell | +0.591 |
wheel | +0.536 |
disl | +0.502 |
inations | +0.501 |
od | +0.498 |
Neg logit contributions | |
crib | -0.492 |
ara | -0.480 |
Mom | -0.474 |
mom | -0.449 |
Sunny | -0.432 |
Token | on |
Token ID | 319 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
vell | +0.178 |
wheel | +0.165 |
disl | +0.157 |
inations | +0.156 |
od | +0.155 |
Neg logit contributions | |
crib | -0.088 |
ara | -0.087 |
Mom | -0.084 |
mom | -0.078 |
Sunny | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
vell | +0.092 |
wheel | +0.086 |
disl | +0.083 |
od | +0.082 |
inations | +0.081 |
Neg logit contributions | |
crib | -0.039 |
ara | -0.039 |
Mom | -0.037 |
mom | -0.033 |
End | -0.032 |
Token | beach |
Token ID | 10481 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
vell | +0.060 |
wheel | +0.056 |
disl | +0.055 |
inations | +0.055 |
asing | +0.055 |
Neg logit contributions | |
crib | -0.028 |
Mom | -0.027 |
mom | -0.026 |
ara | -0.026 |
bunny | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
vell | +0.069 |
wheel | +0.064 |
inations | +0.062 |
disl | +0.062 |
cher | +0.060 |
Neg logit contributions | |
crib | -0.026 |
ara | -0.025 |
Mom | -0.024 |
mom | -0.024 |
Sunny | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
vell | +0.139 |
wheel | +0.128 |
disl | +0.127 |
inations | +0.124 |
cher | +0.121 |
Neg logit contributions | |
crib | -0.041 |
ara | -0.039 |
Mom | -0.039 |
mom | -0.037 |
Mom | -0.032 |
Token | He |
Token ID | 679 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
vell | +0.045 |
wheel | +0.042 |
disl | +0.040 |
inations | +0.040 |
od | +0.039 |
Neg logit contributions | |
crib | -0.019 |
ara | -0.018 |
Mom | -0.018 |
mom | -0.016 |
Sunny | -0.015 |
Token | would |
Token ID | 561 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
vell | +0.036 |
wheel | +0.033 |
disl | +0.032 |
inations | +0.031 |
od | +0.031 |
Neg logit contributions | |
crib | -0.019 |
ara | -0.019 |
Mom | -0.018 |
mom | -0.017 |
Sunny | -0.016 |
Token | build |
Token ID | 1382 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
crib | +0.036 |
ara | +0.035 |
Mom | +0.034 |
mom | +0.032 |
Sunny | +0.031 |
Neg logit contributions | |
vell | -0.054 |
wheel | -0.049 |
disl | -0.047 |
inations | -0.046 |
od | -0.046 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
vell | +0.250 |
wheel | +0.233 |
disl | +0.226 |
cher | +0.225 |
inations | +0.220 |
Neg logit contributions | |
mom | -0.133 |
crib | -0.131 |
ara | -0.125 |
Mom | -0.124 |
Mom | -0.123 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
disl | +0.104 |
vell | +0.102 |
wheel | +0.097 |
inations | +0.093 |
asing | +0.089 |
Neg logit contributions | |
mom | -0.159 |
ara | -0.156 |
Mom | -0.151 |
crib | -0.150 |
Mom | -0.148 |
Token | les |
Token ID | 829 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
vell | +0.645 |
wheel | +0.591 |
disl | +0.572 |
inations | +0.552 |
od | +0.540 |
Neg logit contributions | |
ara | -0.450 |
crib | -0.438 |
Mom | -0.419 |
mom | -0.397 |
Sunny | -0.392 |
Token | and |
Token ID | 290 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
vell | +0.226 |
disl | +0.215 |
inations | +0.208 |
wheel | +0.206 |
cher | +0.199 |
Neg logit contributions | |
crib | -0.042 |
mom | -0.037 |
Mom | -0.034 |
ara | -0.034 |
bunny | -0.033 |
Token | collect |
Token ID | 2824 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
vell | +0.038 |
wheel | +0.031 |
cher | +0.031 |
asing | +0.031 |
inations | +0.031 |
Neg logit contributions | |
mom | -0.021 |
crib | -0.020 |
Mom | -0.020 |
bunny | -0.020 |
one | -0.020 |
Token | seas |
Token ID | 21547 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
vell | +0.223 |
wheel | +0.223 |
cher | +0.211 |
disl | +0.210 |
inations | +0.207 |
Neg logit contributions | |
ara | -0.124 |
mom | -0.123 |
pink | -0.119 |
ham | -0.119 |
one | -0.117 |
Token | hell |
Token ID | 12758 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
vell | +0.084 |
wheel | +0.076 |
disl | +0.074 |
cher | +0.070 |
asing | +0.069 |
Neg logit contributions | |
ara | -0.124 |
um | -0.114 |
Mom | -0.113 |
mom | -0.112 |
crib | -0.111 |
Token | She |
Token ID | 1375 |
Feature activation | -6.99e-03 |
Pos logit contributions | |
wheel | +0.035 |
disl | +0.033 |
od | +0.032 |
vell | +0.032 |
ooters | +0.030 |
Neg logit contributions | |
Mom | -0.019 |
End | -0.019 |
crib | -0.018 |
ara | -0.018 |
beef | -0.018 |
Token | liked |
Token ID | 8288 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
vell | +0.016 |
wheel | +0.015 |
disl | +0.014 |
inations | +0.014 |
od | +0.014 |
Neg logit contributions | |
crib | -0.009 |
ara | -0.009 |
Mom | -0.009 |
mom | -0.008 |
Sunny | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -2.94e-03 |
Pos logit contributions | |
crib | +0.030 |
mom | +0.028 |
Mom | +0.027 |
ara | +0.027 |
chicken | +0.025 |
Neg logit contributions | |
vell | -0.099 |
wheel | -0.091 |
inations | -0.087 |
cher | -0.087 |
disl | -0.086 |
Token | build |
Token ID | 1382 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
vell | +0.008 |
asing | +0.007 |
wheel | +0.007 |
cher | +0.007 |
od | +0.007 |
Neg logit contributions | |
mom | -0.004 |
crib | -0.003 |
Mom | -0.003 |
ara | -0.003 |
Mom | -0.003 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.44e-02 |
Pos logit contributions | |
vell | +0.257 |
wheel | +0.245 |
cher | +0.236 |
disl | +0.232 |
asing | +0.229 |
Neg logit contributions | |
mom | -0.129 |
crib | -0.129 |
ara | -0.123 |
beef | -0.119 |
me | -0.118 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
disl | +0.098 |
vell | +0.097 |
wheel | +0.094 |
inations | +0.089 |
asing | +0.085 |
Neg logit contributions | |
mom | -0.169 |
ara | -0.167 |
crib | -0.162 |
Mom | -0.162 |
um | -0.158 |
Token | les |
Token ID | 829 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
vell | +0.619 |
wheel | +0.565 |
disl | +0.538 |
inations | +0.528 |
od | +0.518 |
Neg logit contributions | |
crib | -0.464 |
ara | -0.464 |
Mom | -0.445 |
mom | -0.422 |
Sunny | -0.411 |
Token | and |
Token ID | 290 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
vell | +0.208 |
disl | +0.192 |
wheel | +0.191 |
inations | +0.188 |
cher | +0.181 |
Neg logit contributions | |
crib | -0.062 |
ara | -0.057 |
Mom | -0.055 |
mom | -0.052 |
bunny | -0.049 |
Token | collect |
Token ID | 2824 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
vell | +0.037 |
wheel | +0.031 |
cher | +0.030 |
asing | +0.030 |
inations | +0.030 |
Neg logit contributions | |
crib | -0.021 |
mom | -0.021 |
Mom | -0.020 |
bunny | -0.020 |
ara | -0.020 |
Token | seas |
Token ID | 21547 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
vell | +0.217 |
wheel | +0.214 |
cher | +0.199 |
disl | +0.199 |
inations | +0.199 |
Neg logit contributions | |
ara | -0.139 |
mom | -0.135 |
crib | -0.135 |
ham | -0.131 |
chicken | -0.130 |
Token | hell |
Token ID | 12758 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
vell | +0.086 |
wheel | +0.077 |
disl | +0.075 |
cher | +0.071 |
asing | +0.070 |
Neg logit contributions | |
ara | -0.128 |
Mom | -0.119 |
um | -0.119 |
mom | -0.117 |
crib | -0.115 |
Token | the |
Token ID | 262 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
vell | +0.089 |
wheel | +0.083 |
disl | +0.080 |
od | +0.079 |
inations | +0.078 |
Neg logit contributions | |
ara | -0.041 |
crib | -0.041 |
Mom | -0.040 |
mom | -0.035 |
End | -0.035 |
Token | beach |
Token ID | 10481 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
vell | +0.056 |
wheel | +0.052 |
disl | +0.049 |
inations | +0.049 |
od | +0.048 |
Neg logit contributions | |
crib | -0.031 |
ara | -0.031 |
Mom | -0.030 |
mom | -0.028 |
Sunny | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
vell | +0.064 |
wheel | +0.060 |
disl | +0.058 |
inations | +0.057 |
od | +0.056 |
Neg logit contributions | |
crib | -0.022 |
ara | -0.021 |
Mom | -0.020 |
mom | -0.019 |
Sunny | -0.017 |
Token | build |
Token ID | 1382 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
vell | +0.028 |
wheel | +0.025 |
inations | +0.024 |
disl | +0.024 |
od | +0.024 |
Neg logit contributions | |
crib | -0.018 |
ara | -0.017 |
Mom | -0.017 |
mom | -0.017 |
bunny | -0.016 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
vell | +0.229 |
wheel | +0.214 |
disl | +0.203 |
cher | +0.201 |
inations | +0.200 |
Neg logit contributions | |
crib | -0.157 |
ara | -0.156 |
mom | -0.153 |
Mom | -0.149 |
Mom | -0.142 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
vell | +0.083 |
disl | +0.082 |
wheel | +0.078 |
inations | +0.072 |
asing | +0.069 |
Neg logit contributions | |
ara | -0.173 |
mom | -0.173 |
crib | -0.171 |
Mom | -0.169 |
Mom | -0.162 |
Token | les |
Token ID | 829 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
vell | +0.590 |
wheel | +0.535 |
disl | +0.501 |
inations | +0.500 |
od | +0.497 |
Neg logit contributions | |
crib | -0.490 |
ara | -0.478 |
Mom | -0.472 |
mom | -0.446 |
Sunny | -0.431 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
vell | +0.185 |
wheel | +0.171 |
disl | +0.167 |
inations | +0.165 |
od | +0.159 |
Neg logit contributions | |
crib | -0.078 |
ara | -0.075 |
Mom | -0.073 |
mom | -0.069 |
bunny | -0.064 |
Token | But |
Token ID | 887 |
Feature activation | -7.74e-03 |
Pos logit contributions | |
wheel | +0.027 |
od | +0.026 |
disl | +0.026 |
vell | +0.025 |
ooters | +0.025 |
Neg logit contributions | |
crib | -0.014 |
beef | -0.014 |
End | -0.013 |
therapist | -0.013 |
chicken | -0.013 |
Token | one |
Token ID | 530 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
wheel | +0.015 |
disl | +0.015 |
vell | +0.015 |
od | +0.015 |
asing | +0.014 |
Neg logit contributions | |
crib | -0.009 |
beef | -0.009 |
ara | -0.009 |
um | -0.008 |
waitress | -0.008 |
Token | day |
Token ID | 1110 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
crib | +0.094 |
ara | +0.093 |
Mom | +0.089 |
Sunny | +0.087 |
brow | +0.083 |
Neg logit contributions | |
vell | -0.172 |
wheel | -0.169 |
od | -0.163 |
ont | -0.160 |
disl | -0.159 |
Token | the |
Token ID | 262 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
vell | +0.016 |
wheel | +0.014 |
inations | +0.014 |
cher | +0.014 |
disl | +0.013 |
Neg logit contributions | |
crib | -0.005 |
ara | -0.005 |
Mom | -0.005 |
mom | -0.005 |
Mom | -0.004 |
Token | beach |
Token ID | 10481 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
vell | +0.052 |
wheel | +0.049 |
disl | +0.047 |
od | +0.046 |
inations | +0.045 |
Neg logit contributions | |
crib | -0.025 |
ara | -0.024 |
Mom | -0.023 |
mom | -0.021 |
Sunny | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
vell | +0.064 |
wheel | +0.060 |
od | +0.057 |
disl | +0.057 |
inations | +0.057 |
Neg logit contributions | |
crib | -0.026 |
ara | -0.026 |
Mom | -0.025 |
mom | -0.022 |
Sunny | -0.022 |
Token | building |
Token ID | 2615 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
vell | +0.028 |
wheel | +0.026 |
disl | +0.025 |
inations | +0.025 |
od | +0.024 |
Neg logit contributions | |
crib | -0.017 |
ara | -0.017 |
Mom | -0.017 |
mom | -0.016 |
Sunny | -0.015 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
vell | +0.203 |
wheel | +0.188 |
inations | +0.179 |
disl | +0.179 |
cher | +0.176 |
Neg logit contributions | |
crib | -0.097 |
ara | -0.095 |
Mom | -0.093 |
mom | -0.091 |
Mom | -0.083 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
vell | +0.120 |
disl | +0.117 |
wheel | +0.114 |
inations | +0.113 |
asing | +0.105 |
Neg logit contributions | |
ara | -0.137 |
mom | -0.136 |
crib | -0.136 |
Mom | -0.132 |
um | -0.127 |
Token | les |
Token ID | 829 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
vell | +0.582 |
wheel | +0.527 |
inations | +0.493 |
disl | +0.492 |
od | +0.491 |
Neg logit contributions | |
crib | -0.496 |
ara | -0.481 |
Mom | -0.478 |
mom | -0.452 |
Sunny | -0.437 |
Token | . |
Token ID | 13 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
vell | +0.178 |
wheel | +0.165 |
disl | +0.158 |
inations | +0.157 |
od | +0.154 |
Neg logit contributions | |
crib | -0.084 |
ara | -0.082 |
Mom | -0.080 |
mom | -0.074 |
Sunny | -0.070 |
Token | One |
Token ID | 1881 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
wheel | +0.029 |
disl | +0.028 |
od | +0.028 |
ooters | +0.027 |
vell | +0.027 |
Neg logit contributions | |
crib | -0.016 |
beef | -0.015 |
therapist | -0.015 |
End | -0.015 |
Mom | -0.014 |
Token | day |
Token ID | 1110 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
crib | +0.113 |
ara | +0.106 |
Sunny | +0.098 |
Mom | +0.098 |
kitten | +0.090 |
Neg logit contributions | |
vell | -0.259 |
wheel | -0.250 |
disl | -0.240 |
od | -0.236 |
inations | -0.235 |
Token | , |
Token ID | 11 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
crib | +0.034 |
vet | +0.032 |
Mom | +0.031 |
Amen | +0.031 |
ara | +0.030 |
Neg logit contributions | |
vell | -0.039 |
wheel | -0.039 |
od | -0.038 |
disl | -0.035 |
smart | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
ara | +0.025 |
crib | +0.025 |
Mom | +0.023 |
Sunny | +0.021 |
bunny | +0.021 |
Neg logit contributions | |
vell | -0.048 |
wheel | -0.045 |
disl | -0.043 |
inations | -0.042 |
od | -0.042 |
Token | waves |
Token ID | 9813 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
vell | +0.055 |
wheel | +0.050 |
disl | +0.048 |
inations | +0.047 |
od | +0.046 |
Neg logit contributions | |
crib | -0.038 |
ara | -0.037 |
Mom | -0.036 |
mom | -0.034 |
Sunny | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
vell | +0.123 |
wheel | +0.113 |
disl | +0.110 |
inations | +0.109 |
od | +0.107 |
Neg logit contributions | |
crib | -0.054 |
ara | -0.053 |
Mom | -0.051 |
mom | -0.048 |
bunny | -0.045 |
Token | built |
Token ID | 3170 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
vell | +0.039 |
wheel | +0.034 |
disl | +0.034 |
inations | +0.033 |
ologist | +0.033 |
Neg logit contributions | |
mom | -0.020 |
crib | -0.020 |
Mom | -0.020 |
ara | -0.019 |
Mom | -0.019 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
vell | +0.097 |
wheel | +0.090 |
disl | +0.086 |
inations | +0.085 |
od | +0.084 |
Neg logit contributions | |
crib | -0.038 |
ara | -0.037 |
Mom | -0.036 |
mom | -0.033 |
Sunny | -0.031 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
vell | +0.078 |
disl | +0.076 |
wheel | +0.074 |
inations | +0.068 |
asing | +0.066 |
Neg logit contributions | |
ara | -0.178 |
crib | -0.177 |
mom | -0.175 |
Mom | -0.168 |
blanket | -0.167 |
Token | les |
Token ID | 829 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
vell | +0.699 |
disl | +0.649 |
wheel | +0.647 |
ologist | +0.602 |
asing | +0.597 |
Neg logit contributions | |
ara | -0.401 |
crib | -0.368 |
Mom | -0.339 |
Sunny | -0.335 |
bunny | -0.332 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
vell | +0.193 |
wheel | +0.177 |
disl | +0.174 |
inations | +0.173 |
ologist | +0.167 |
Neg logit contributions | |
crib | -0.073 |
ara | -0.066 |
mom | -0.064 |
Mom | -0.062 |
bunny | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
vell | +0.047 |
wheel | +0.044 |
inations | +0.042 |
disl | +0.042 |
cher | +0.041 |
Neg logit contributions | |
crib | -0.016 |
Mom | -0.016 |
ara | -0.016 |
mom | -0.015 |
Mom | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
vell | +0.075 |
wheel | +0.070 |
disl | +0.067 |
inations | +0.066 |
od | +0.065 |
Neg logit contributions | |
crib | -0.022 |
Mom | -0.021 |
ara | -0.021 |
mom | -0.019 |
Sunny | -0.017 |
Token | M |
Token ID | 44 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
vell | +0.057 |
wheel | +0.053 |
disl | +0.050 |
inations | +0.049 |
od | +0.049 |
Neg logit contributions | |
crib | -0.038 |
ara | -0.037 |
Mom | -0.036 |
mom | -0.034 |
Sunny | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
vell | +0.073 |
wheel | +0.068 |
disl | +0.066 |
inations | +0.065 |
od | +0.064 |
Neg logit contributions | |
crib | -0.032 |
ara | -0.031 |
Mom | -0.030 |
mom | -0.029 |
bunny | -0.026 |
Token | They |
Token ID | 1119 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
vell | +0.036 |
wheel | +0.036 |
disl | +0.035 |
od | +0.033 |
ount | +0.033 |
Neg logit contributions | |
crib | -0.017 |
ara | -0.016 |
End | -0.015 |
Mom | -0.015 |
bunny | -0.015 |
Token | would |
Token ID | 561 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
crib | +0.026 |
ara | +0.025 |
Mom | +0.025 |
mom | +0.023 |
Sunny | +0.022 |
Neg logit contributions | |
vell | -0.051 |
wheel | -0.047 |
disl | -0.045 |
inations | -0.044 |
od | -0.044 |
Token | build |
Token ID | 1382 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
crib | +0.034 |
ara | +0.033 |
Mom | +0.032 |
mom | +0.030 |
Sunny | +0.029 |
Neg logit contributions | |
vell | -0.056 |
wheel | -0.051 |
disl | -0.049 |
inations | -0.048 |
od | -0.048 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
vell | +0.260 |
wheel | +0.249 |
disl | +0.238 |
cher | +0.234 |
inations | +0.228 |
Neg logit contributions | |
crib | -0.127 |
mom | -0.125 |
ara | -0.125 |
Mom | -0.118 |
Mom | -0.118 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
disl | +0.098 |
vell | +0.094 |
wheel | +0.094 |
asing | +0.082 |
cher | +0.081 |
Neg logit contributions | |
mom | -0.169 |
ara | -0.169 |
Mom | -0.161 |
crib | -0.160 |
Mom | -0.157 |
Token | les |
Token ID | 829 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
vell | +0.637 |
wheel | +0.585 |
disl | +0.563 |
inations | +0.544 |
od | +0.535 |
Neg logit contributions | |
ara | -0.452 |
crib | -0.443 |
Mom | -0.423 |
mom | -0.403 |
Sunny | -0.395 |
Token | and |
Token ID | 290 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
vell | +0.223 |
disl | +0.213 |
wheel | +0.208 |
inations | +0.202 |
cher | +0.197 |
Neg logit contributions | |
crib | -0.038 |
mom | -0.034 |
ara | -0.031 |
Mom | -0.030 |
chicken | -0.029 |
Token | swim |
Token ID | 9422 |
Feature activation | +8.03e-03 |
Pos logit contributions | |
vell | +0.033 |
wheel | +0.029 |
asing | +0.028 |
cher | +0.028 |
smart | +0.027 |
Neg logit contributions | |
mom | -0.018 |
crib | -0.018 |
Mom | -0.017 |
Mom | -0.017 |
ham | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
crib | +0.007 |
mom | +0.007 |
ara | +0.007 |
Mom | +0.007 |
Mom | +0.006 |
Neg logit contributions | |
vell | -0.022 |
wheel | -0.022 |
disl | -0.021 |
inations | -0.020 |
ologist | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
crib | +0.021 |
ara | +0.021 |
Mom | +0.020 |
mom | +0.019 |
Sunny | +0.017 |
Neg logit contributions | |
vell | -0.053 |
wheel | -0.049 |
disl | -0.047 |
inations | -0.046 |
od | -0.046 |
Token | She |
Token ID | 1375 |
Feature activation | -6.22e-03 |
Pos logit contributions | |
vell | +0.034 |
wheel | +0.033 |
disl | +0.033 |
od | +0.032 |
achieve | +0.029 |
Neg logit contributions | |
ara | -0.019 |
Mom | -0.018 |
crib | -0.018 |
End | -0.017 |
bunny | -0.016 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
vell | +0.017 |
wheel | +0.015 |
disl | +0.015 |
od | +0.014 |
inations | +0.014 |
Neg logit contributions | |
ara | -0.006 |
mom | -0.006 |
crib | -0.006 |
Mom | -0.006 |
Mom | -0.005 |
Token | shells |
Token ID | 19679 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
vell | +0.100 |
wheel | +0.093 |
inations | +0.089 |
disl | +0.089 |
od | +0.086 |
Neg logit contributions | |
crib | -0.040 |
ara | -0.038 |
Mom | -0.038 |
mom | -0.036 |
bunny | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
vell | +0.338 |
disl | +0.319 |
wheel | +0.317 |
inations | +0.307 |
asing | +0.297 |
Neg logit contributions | |
crib | -0.078 |
ara | -0.075 |
Mom | -0.069 |
mom | -0.068 |
bunny | -0.065 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
chicken | +0.018 |
mom | +0.018 |
ham | +0.017 |
bunny | +0.017 |
Mom | +0.017 |
Neg logit contributions | |
vell | -0.026 |
wheel | -0.024 |
disl | -0.022 |
cher | -0.022 |
inations | -0.021 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
vell | +0.214 |
wheel | +0.210 |
disl | +0.203 |
inations | +0.199 |
cher | +0.193 |
Neg logit contributions | |
ara | -0.045 |
mom | -0.042 |
crib | -0.041 |
Mom | -0.035 |
eyes | -0.033 |
Token | les |
Token ID | 829 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
vell | +0.646 |
wheel | +0.597 |
disl | +0.576 |
inations | +0.552 |
od | +0.541 |
Neg logit contributions | |
ara | -0.446 |
crib | -0.429 |
Mom | -0.410 |
mom | -0.390 |
Sunny | -0.387 |
Token | and |
Token ID | 290 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
vell | +0.214 |
wheel | +0.199 |
disl | +0.199 |
inations | +0.192 |
cher | +0.187 |
Neg logit contributions | |
crib | -0.048 |
ara | -0.044 |
mom | -0.041 |
Mom | -0.040 |
bunny | -0.038 |
Token | se |
Token ID | 384 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
vell | +0.033 |
wheel | +0.029 |
disl | +0.028 |
inations | +0.028 |
cher | +0.027 |
Neg logit contributions | |
crib | -0.018 |
mom | -0.018 |
Mom | -0.017 |
bunny | -0.017 |
ara | -0.017 |
Token | ag |
Token ID | 363 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
vell | +0.213 |
wheel | +0.183 |
achieve | +0.169 |
disl | +0.165 |
cher | +0.163 |
Neg logit contributions | |
ara | -0.244 |
Mom | -0.225 |
crib | -0.224 |
um | -0.222 |
beef | -0.211 |
Token | ull |
Token ID | 724 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
Mom | +0.086 |
crib | +0.084 |
ara | +0.083 |
mom | +0.083 |
Mom | +0.079 |
Neg logit contributions | |
vell | -0.086 |
wheel | -0.080 |
disl | -0.072 |
cher | -0.072 |
inations | -0.071 |
Token | each |
Token ID | 1123 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
vell | +0.118 |
wheel | +0.113 |
inations | +0.105 |
disl | +0.105 |
cher | +0.103 |
Neg logit contributions | |
crib | -0.062 |
ara | -0.061 |
mom | -0.059 |
Mom | -0.058 |
Mom | -0.055 |
Token | other |
Token ID | 584 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
crib | +0.032 |
ara | +0.032 |
Mom | +0.031 |
Sunny | +0.028 |
mom | +0.028 |
Neg logit contributions | |
vell | -0.053 |
wheel | -0.049 |
inations | -0.046 |
od | -0.046 |
disl | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
vell | +0.102 |
wheel | +0.096 |
disl | +0.092 |
inations | +0.090 |
cher | +0.088 |
Neg logit contributions | |
crib | -0.052 |
ara | -0.049 |
mom | -0.047 |
Mom | -0.047 |
bunny | -0.045 |
Token | making |
Token ID | 1642 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
vell | +0.036 |
wheel | +0.033 |
od | +0.031 |
inations | +0.030 |
cher | +0.030 |
Neg logit contributions | |
crib | -0.024 |
mom | -0.023 |
Mom | -0.022 |
ara | -0.022 |
Mom | -0.021 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
vell | +0.068 |
wheel | +0.063 |
cher | +0.059 |
inations | +0.059 |
disl | +0.058 |
Neg logit contributions | |
crib | -0.036 |
ara | -0.034 |
mom | -0.034 |
Mom | -0.033 |
Mom | -0.032 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
wheel | +0.105 |
disl | +0.102 |
vell | +0.102 |
asing | +0.097 |
cher | +0.094 |
Neg logit contributions | |
mom | -0.156 |
crib | -0.146 |
blanket | -0.145 |
ara | -0.144 |
Mom | -0.144 |
Token | les |
Token ID | 829 |
Feature activation | -7.10e-02 |
Pos logit contributions | |
vell | +0.691 |
wheel | +0.639 |
disl | +0.627 |
inations | +0.589 |
ologist | +0.586 |
Neg logit contributions | |
ara | -0.410 |
crib | -0.379 |
Sunny | -0.351 |
Mom | -0.348 |
bunny | -0.341 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
vell | +0.203 |
wheel | +0.189 |
disl | +0.186 |
inations | +0.184 |
ologist | +0.178 |
Neg logit contributions | |
crib | -0.056 |
mom | -0.051 |
bunny | -0.046 |
chicken | -0.046 |
blanket | -0.044 |
Token | |
Token ID | 220 |
Feature activation | -2.68e-03 |
Pos logit contributions | |
vell | +0.049 |
wheel | +0.046 |
disl | +0.044 |
inations | +0.044 |
od | +0.043 |
Neg logit contributions | |
crib | -0.017 |
ara | -0.017 |
Mom | -0.016 |
mom | -0.014 |
Sunny | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
vell | +0.009 |
wheel | +0.008 |
disl | +0.008 |
inations | +0.008 |
ologist | +0.008 |
Neg logit contributions | |
Mom | -0.001 |
ara | -0.001 |
mom | -0.001 |
crib | -0.001 |
Mom | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
vell | +0.070 |
wheel | +0.066 |
od | +0.064 |
inations | +0.064 |
disl | +0.063 |
Neg logit contributions | |
crib | -0.031 |
ara | -0.028 |
Mom | -0.026 |
mom | -0.025 |
bunny | -0.025 |
Token | She |
Token ID | 1375 |
Feature activation | -7.83e-03 |
Pos logit contributions | |
wheel | +0.035 |
disl | +0.033 |
vell | +0.033 |
od | +0.032 |
ooters | +0.030 |
Neg logit contributions | |
Mom | -0.019 |
crib | -0.019 |
End | -0.018 |
beef | -0.018 |
ara | -0.018 |
Token | liked |
Token ID | 8288 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
vell | +0.019 |
wheel | +0.018 |
disl | +0.017 |
inations | +0.017 |
od | +0.016 |
Neg logit contributions | |
crib | -0.010 |
ara | -0.010 |
Mom | -0.009 |
mom | -0.009 |
Sunny | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -4.67e-03 |
Pos logit contributions | |
crib | +0.030 |
mom | +0.027 |
ara | +0.026 |
Mom | +0.026 |
bunny | +0.024 |
Neg logit contributions | |
vell | -0.096 |
wheel | -0.088 |
inations | -0.085 |
cher | -0.084 |
disl | -0.083 |
Token | build |
Token ID | 1382 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
vell | +0.012 |
asing | +0.011 |
od | +0.011 |
cher | +0.011 |
wheel | +0.011 |
Neg logit contributions | |
mom | -0.005 |
crib | -0.005 |
Mom | -0.005 |
Mom | -0.005 |
ara | -0.005 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
vell | +0.249 |
wheel | +0.236 |
cher | +0.228 |
disl | +0.224 |
asing | +0.220 |
Neg logit contributions | |
mom | -0.135 |
crib | -0.133 |
ara | -0.131 |
me | -0.126 |
Mom | -0.125 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
disl | +0.092 |
vell | +0.090 |
wheel | +0.087 |
inations | +0.082 |
asing | +0.079 |
Neg logit contributions | |
mom | -0.168 |
ara | -0.167 |
crib | -0.161 |
Mom | -0.161 |
um | -0.157 |
Token | les |
Token ID | 829 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
vell | +0.615 |
wheel | +0.562 |
disl | +0.535 |
inations | +0.525 |
od | +0.516 |
Neg logit contributions | |
crib | -0.462 |
ara | -0.462 |
Mom | -0.443 |
mom | -0.420 |
Sunny | -0.409 |
Token | and |
Token ID | 290 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
vell | +0.204 |
disl | +0.188 |
wheel | +0.188 |
inations | +0.185 |
cher | +0.177 |
Neg logit contributions | |
crib | -0.063 |
ara | -0.058 |
Mom | -0.056 |
mom | -0.053 |
bunny | -0.050 |
Token | collect |
Token ID | 2824 |
Feature activation | -9.70e-02 |
Pos logit contributions | |
vell | +0.037 |
wheel | +0.032 |
cher | +0.031 |
asing | +0.030 |
inations | +0.030 |
Neg logit contributions | |
crib | -0.021 |
mom | -0.021 |
Mom | -0.020 |
bunny | -0.020 |
Mom | -0.020 |
Token | seas |
Token ID | 21547 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
vell | +0.210 |
wheel | +0.208 |
cher | +0.194 |
disl | +0.192 |
ologist | +0.191 |
Neg logit contributions | |
ara | -0.142 |
mom | -0.138 |
crib | -0.135 |
ham | -0.134 |
pink | -0.134 |
Token | hell |
Token ID | 12758 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
vell | +0.084 |
wheel | +0.076 |
disl | +0.073 |
cher | +0.070 |
asing | +0.068 |
Neg logit contributions | |
ara | -0.126 |
um | -0.115 |
Mom | -0.115 |
mom | -0.114 |
crib | -0.113 |
Token | building |
Token ID | 2615 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
crib | +0.022 |
mom | +0.020 |
ara | +0.020 |
Mom | +0.020 |
bunny | +0.019 |
Neg logit contributions | |
vell | -0.044 |
disl | -0.041 |
wheel | -0.041 |
cher | -0.037 |
inations | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
vell | +0.232 |
wheel | +0.211 |
disl | +0.211 |
inations | +0.204 |
asing | +0.203 |
Neg logit contributions | |
crib | -0.076 |
mom | -0.068 |
ara | -0.064 |
Mom | -0.061 |
Mom | -0.057 |
Token | most |
Token ID | 749 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
vell | +0.050 |
wheel | +0.045 |
disl | +0.043 |
inations | +0.042 |
od | +0.041 |
Neg logit contributions | |
ara | -0.031 |
crib | -0.031 |
Mom | -0.030 |
Sunny | -0.028 |
mom | -0.027 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
vell | +0.198 |
wheel | +0.182 |
disl | +0.173 |
inations | +0.171 |
od | +0.169 |
Neg logit contributions | |
crib | -0.127 |
ara | -0.125 |
Mom | -0.122 |
mom | -0.115 |
bunny | -0.110 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
vell | +0.049 |
wheel | +0.046 |
disl | +0.044 |
inations | +0.044 |
od | +0.043 |
Neg logit contributions | |
crib | -0.021 |
ara | -0.021 |
Mom | -0.020 |
mom | -0.018 |
Sunny | -0.018 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
vell | +0.189 |
disl | +0.182 |
wheel | +0.181 |
inations | +0.174 |
asing | +0.169 |
Neg logit contributions | |
crib | -0.071 |
mom | -0.066 |
ara | -0.065 |
Mom | -0.060 |
bunny | -0.060 |
Token | les |
Token ID | 829 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
vell | +0.603 |
wheel | +0.549 |
disl | +0.519 |
inations | +0.513 |
od | +0.507 |
Neg logit contributions | |
crib | -0.473 |
ara | -0.468 |
Mom | -0.454 |
mom | -0.429 |
Sunny | -0.417 |
Token | on |
Token ID | 319 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
vell | +0.187 |
wheel | +0.173 |
disl | +0.167 |
inations | +0.165 |
od | +0.162 |
Neg logit contributions | |
crib | -0.078 |
ara | -0.075 |
Mom | -0.072 |
mom | -0.067 |
Sunny | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
vell | +0.088 |
wheel | +0.081 |
od | +0.078 |
disl | +0.077 |
inations | +0.075 |
Neg logit contributions | |
ara | -0.047 |
crib | -0.046 |
Mom | -0.045 |
End | -0.041 |
ham | -0.040 |
Token | beach |
Token ID | 10481 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
vell | +0.052 |
wheel | +0.048 |
disl | +0.045 |
inations | +0.045 |
od | +0.045 |
Neg logit contributions | |
crib | -0.034 |
ara | -0.033 |
Mom | -0.032 |
mom | -0.030 |
Sunny | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
vell | +0.065 |
wheel | +0.060 |
disl | +0.058 |
inations | +0.058 |
asing | +0.056 |
Neg logit contributions | |
crib | -0.024 |
ara | -0.023 |
mom | -0.021 |
Mom | -0.021 |
bunny | -0.019 |
Token | took |
Token ID | 1718 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
crib | +0.080 |
ara | +0.079 |
Mom | +0.076 |
mom | +0.071 |
Sunny | +0.068 |
Neg logit contributions | |
vell | -0.147 |
wheel | -0.135 |
disl | -0.129 |
inations | -0.128 |
od | -0.126 |
Token | time |
Token ID | 640 |
Feature activation | +9.47e-04 |
Pos logit contributions | |
vell | +0.090 |
wheel | +0.083 |
disl | +0.082 |
inations | +0.080 |
ologist | +0.079 |
Neg logit contributions | |
mom | -0.030 |
Mom | -0.030 |
crib | -0.030 |
ara | -0.030 |
Mom | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -5.57e-03 |
Pos logit contributions | |
crib | +0.001 |
ara | +0.001 |
Mom | +0.001 |
mom | +0.001 |
Sunny | +0.001 |
Neg logit contributions | |
vell | -0.002 |
wheel | -0.002 |
disl | -0.002 |
inations | -0.002 |
od | -0.002 |
Token | make |
Token ID | 787 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
vell | +0.015 |
asing | +0.013 |
wheel | +0.013 |
cher | +0.013 |
inations | +0.013 |
Neg logit contributions | |
mom | -0.007 |
crib | -0.006 |
Mom | -0.006 |
Mom | -0.006 |
end | -0.006 |
Token | sand |
Token ID | 6450 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
vell | +0.061 |
wheel | +0.055 |
cher | +0.054 |
ologist | +0.054 |
asing | +0.053 |
Neg logit contributions | |
mom | -0.020 |
Mom | -0.017 |
one | -0.017 |
chicken | -0.017 |
crib | -0.016 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
wheel | +0.102 |
vell | +0.102 |
disl | +0.099 |
asing | +0.095 |
inations | +0.091 |
Neg logit contributions | |
mom | -0.144 |
crib | -0.134 |
eyes | -0.133 |
Mom | -0.132 |
blanket | -0.132 |
Token | les |
Token ID | 829 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
vell | +0.689 |
wheel | +0.641 |
disl | +0.632 |
inations | +0.590 |
ologist | +0.588 |
Neg logit contributions | |
ara | -0.399 |
crib | -0.372 |
Sunny | -0.345 |
bunny | -0.342 |
Mom | -0.341 |
Token | and |
Token ID | 290 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
vell | +0.207 |
disl | +0.190 |
wheel | +0.190 |
inations | +0.186 |
asing | +0.182 |
Neg logit contributions | |
crib | -0.048 |
mom | -0.044 |
bunny | -0.040 |
Sunny | -0.036 |
blanket | -0.036 |
Token | feel |
Token ID | 1254 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
vell | +0.040 |
wheel | +0.035 |
disl | +0.034 |
od | +0.034 |
inations | +0.033 |
Neg logit contributions | |
mom | -0.020 |
crib | -0.020 |
Mom | -0.019 |
Mom | -0.019 |
bunny | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
vell | +0.145 |
wheel | +0.133 |
ologist | +0.130 |
inations | +0.128 |
od | +0.128 |
Neg logit contributions | |
crib | -0.061 |
Mom | -0.056 |
mom | -0.056 |
Mom | -0.053 |
bunny | -0.053 |
Token | waves |
Token ID | 9813 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
vell | +0.054 |
wheel | +0.051 |
disl | +0.048 |
od | +0.048 |
inations | +0.048 |
Neg logit contributions | |
crib | -0.027 |
ara | -0.026 |
Mom | -0.026 |
mom | -0.025 |
bunny | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
crib | +0.019 |
ara | +0.017 |
Mom | +0.017 |
mom | +0.016 |
Sunny | +0.016 |
Neg logit contributions | |
vell | -0.050 |
wheel | -0.046 |
inations | -0.043 |
disl | -0.043 |
od | -0.043 |
Token | beach |
Token ID | 10481 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
vell | +0.035 |
wheel | +0.033 |
disl | +0.030 |
achieve | +0.030 |
inations | +0.030 |
Neg logit contributions | |
ara | -0.019 |
Mom | -0.018 |
crib | -0.017 |
um | -0.016 |
End | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
vell | +0.037 |
wheel | +0.034 |
disl | +0.034 |
inations | +0.033 |
od | +0.033 |
Neg logit contributions | |
crib | -0.012 |
ara | -0.011 |
mom | -0.011 |
Mom | -0.010 |
Sunny | -0.010 |
Token | build |
Token ID | 1382 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
vell | +0.016 |
wheel | +0.014 |
od | +0.014 |
inations | +0.013 |
disl | +0.013 |
Neg logit contributions | |
crib | -0.008 |
ara | -0.008 |
mom | -0.008 |
Mom | -0.008 |
Sunny | -0.007 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.04e-02 |
Pos logit contributions | |
vell | +0.237 |
wheel | +0.222 |
disl | +0.211 |
asing | +0.207 |
inations | +0.205 |
Neg logit contributions | |
crib | -0.132 |
mom | -0.126 |
ara | -0.123 |
Mom | -0.118 |
Mom | -0.117 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
disl | +0.102 |
vell | +0.102 |
wheel | +0.099 |
asing | +0.092 |
inations | +0.089 |
Neg logit contributions | |
mom | -0.148 |
crib | -0.145 |
ara | -0.144 |
blanket | -0.141 |
basket | -0.140 |
Token | les |
Token ID | 829 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
vell | +0.608 |
wheel | +0.555 |
disl | +0.527 |
inations | +0.517 |
od | +0.511 |
Neg logit contributions | |
crib | -0.465 |
ara | -0.462 |
Mom | -0.445 |
mom | -0.422 |
Sunny | -0.411 |
Token | . |
Token ID | 13 |
Feature activation | -5.71e-03 |
Pos logit contributions | |
vell | +0.185 |
wheel | +0.170 |
disl | +0.168 |
inations | +0.165 |
ologist | +0.158 |
Neg logit contributions | |
crib | -0.068 |
ara | -0.063 |
mom | -0.061 |
Mom | -0.060 |
bunny | -0.056 |
Token | |
Token ID | 220 |
Feature activation | +4.26e-03 |
Pos logit contributions | |
vell | +0.015 |
wheel | +0.014 |
disl | +0.013 |
inations | +0.013 |
od | +0.013 |
Neg logit contributions | |
crib | -0.006 |
ara | -0.006 |
Mom | -0.006 |
mom | -0.005 |
Sunny | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
ara | +0.003 |
Mom | +0.003 |
crib | +0.003 |
mom | +0.002 |
Mom | +0.002 |
Neg logit contributions | |
vell | -0.013 |
wheel | -0.012 |
disl | -0.012 |
inations | -0.012 |
ologist | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
vell | +0.045 |
wheel | +0.043 |
disl | +0.041 |
inations | +0.041 |
od | +0.041 |
Neg logit contributions | |
crib | -0.018 |
ara | -0.017 |
Mom | -0.016 |
mom | -0.015 |
bunny | -0.015 |
Token | went |
Token ID | 1816 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
vell | +0.029 |
wheel | +0.027 |
inations | +0.026 |
disl | +0.025 |
od | +0.025 |
Neg logit contributions | |
crib | -0.016 |
ara | -0.016 |
Mom | -0.015 |
mom | -0.015 |
Sunny | -0.014 |
Token | back |
Token ID | 736 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
vell | +0.087 |
wheel | +0.080 |
disl | +0.078 |
od | +0.077 |
inations | +0.077 |
Neg logit contributions | |
crib | -0.042 |
ara | -0.041 |
Mom | -0.040 |
mom | -0.038 |
Sunny | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | -6.62e-03 |
Pos logit contributions | |
crib | +0.013 |
mom | +0.012 |
ara | +0.011 |
Mom | +0.011 |
Mom | +0.010 |
Neg logit contributions | |
vell | -0.036 |
wheel | -0.033 |
inations | -0.031 |
disl | -0.031 |
od | -0.031 |
Token | building |
Token ID | 2615 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
vell | +0.017 |
wheel | +0.015 |
inations | +0.014 |
disl | +0.014 |
od | +0.014 |
Neg logit contributions | |
crib | -0.009 |
ara | -0.008 |
mom | -0.008 |
Mom | -0.008 |
Mom | -0.007 |
Token | sand |
Token ID | 6450 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
vell | +0.234 |
wheel | +0.214 |
inations | +0.209 |
disl | +0.208 |
asing | +0.206 |
Neg logit contributions | |
crib | -0.075 |
mom | -0.071 |
ara | -0.066 |
Mom | -0.065 |
Mom | -0.063 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
vell | +0.140 |
inations | +0.136 |
disl | +0.136 |
wheel | +0.132 |
asing | +0.130 |
Neg logit contributions | |
crib | -0.109 |
mom | -0.108 |
ara | -0.102 |
shop | -0.097 |
Mom | -0.097 |
Token | les |
Token ID | 829 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
vell | +0.616 |
wheel | +0.563 |
disl | +0.536 |
inations | +0.525 |
od | +0.518 |
Neg logit contributions | |
ara | -0.460 |
crib | -0.459 |
Mom | -0.439 |
mom | -0.417 |
Sunny | -0.406 |
Token | with |
Token ID | 351 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
vell | +0.196 |
wheel | +0.178 |
disl | +0.178 |
inations | +0.176 |
od | +0.168 |
Neg logit contributions | |
crib | -0.073 |
ara | -0.066 |
mom | -0.064 |
Mom | -0.063 |
bunny | -0.059 |
Token | his |
Token ID | 465 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
crib | +0.041 |
ara | +0.040 |
Mom | +0.039 |
mom | +0.039 |
Mom | +0.036 |
Neg logit contributions | |
vell | -0.072 |
wheel | -0.067 |
disl | -0.063 |
inations | -0.063 |
od | -0.062 |
Token | family |
Token ID | 1641 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
vell | +0.040 |
wheel | +0.039 |
od | +0.036 |
disl | +0.036 |
inations | +0.035 |
Neg logit contributions | |
crib | -0.012 |
mom | -0.012 |
ara | -0.012 |
Mom | -0.011 |
Mom | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -8.94e-03 |
Pos logit contributions | |
vell | +0.073 |
wheel | +0.067 |
disl | +0.064 |
inations | +0.064 |
od | +0.063 |
Neg logit contributions | |
crib | -0.035 |
ara | -0.034 |
Mom | -0.033 |
mom | -0.031 |
Sunny | -0.029 |
Token | � |
Token ID | 95 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
vell | +0.012 |
wheel | +0.011 |
disl | +0.010 |
inations | +0.010 |
od | +0.010 |
Neg logit contributions | |
crib | -0.011 |
ara | -0.010 |
Mom | -0.010 |
mom | -0.010 |
Sunny | -0.009 |
Token | € |
Token ID | 26391 |
Feature activation | +4.78e-03 |
Pos logit contributions | |
ara | +0.039 |
crib | +0.038 |
Mom | +0.037 |
mom | +0.034 |
Sunny | +0.034 |
Neg logit contributions | |
vell | -0.044 |
wheel | -0.038 |
inations | -0.038 |
od | -0.037 |
disl | -0.036 |
Token | � |
Token ID | 129 |
Feature activation | +7.46e-03 |
Pos logit contributions | |
ara | +0.008 |
crib | +0.008 |
Mom | +0.008 |
mom | +0.008 |
Mom | +0.007 |
Neg logit contributions | |
vell | -0.010 |
wheel | -0.009 |
inations | -0.008 |
disl | -0.008 |
od | -0.008 |
Token | � |
Token ID | 241 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
crib | +0.011 |
ara | +0.011 |
Mom | +0.011 |
mom | +0.010 |
Sunny | +0.010 |
Neg logit contributions | |
vell | -0.016 |
wheel | -0.015 |
inations | -0.014 |
disl | -0.014 |
od | -0.014 |
Token | Yes |
Token ID | 5297 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
crib | +0.036 |
ara | +0.033 |
Mom | +0.031 |
mom | +0.030 |
Sunny | +0.029 |
Neg logit contributions | |
vell | -0.088 |
wheel | -0.084 |
disl | -0.080 |
inations | -0.079 |
od | -0.078 |
Token | please |
Token ID | 3387 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
crib | +0.024 |
ara | +0.023 |
Mom | +0.022 |
mom | +0.020 |
Sunny | +0.020 |
Neg logit contributions | |
vell | -0.039 |
wheel | -0.036 |
disl | -0.034 |
inations | -0.034 |
od | -0.034 |
Token | ! |
Token ID | 0 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
ara | +0.165 |
Mom | +0.161 |
crib | +0.160 |
mom | +0.157 |
Mom | +0.147 |
Neg logit contributions | |
vell | -0.211 |
wheel | -0.190 |
disl | -0.185 |
inations | -0.182 |
od | -0.179 |
Token | â |
Token ID | 22940 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
vell | +0.057 |
wheel | +0.054 |
disl | +0.051 |
od | +0.050 |
inations | +0.049 |
Neg logit contributions | |
crib | -0.032 |
ara | -0.030 |
Mom | -0.029 |
mom | -0.027 |
End | -0.027 |
Token | € |
Token ID | 26391 |
Feature activation | +6.05e-03 |
Pos logit contributions | |
ara | +0.025 |
Mom | +0.024 |
crib | +0.024 |
End | +0.023 |
um | +0.022 |
Neg logit contributions | |
vell | -0.023 |
inations | -0.019 |
od | -0.019 |
wheel | -0.019 |
disl | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
ara | +0.010 |
crib | +0.009 |
Mom | +0.009 |
mom | +0.009 |
Mom | +0.008 |
Neg logit contributions | |
vell | -0.013 |
wheel | -0.012 |
inations | -0.011 |
od | -0.011 |
disl | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
vell | +0.054 |
wheel | +0.051 |
disl | +0.049 |
inations | +0.048 |
od | +0.048 |
Neg logit contributions | |
crib | -0.019 |
ara | -0.018 |
Mom | -0.017 |
mom | -0.016 |
Sunny | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | -7.77e-03 |
Pos logit contributions | |
vell | +0.026 |
wheel | +0.023 |
ologist | +0.023 |
inations | +0.023 |
od | +0.023 |
Neg logit contributions | |
crib | -0.014 |
mom | -0.014 |
Mom | -0.014 |
ara | -0.014 |
Mom | -0.013 |
Token | worries |
Token ID | 18572 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
vell | +0.018 |
wheel | +0.017 |
disl | +0.016 |
inations | +0.016 |
od | +0.016 |
Neg logit contributions | |
crib | -0.010 |
ara | -0.010 |
Mom | -0.010 |
mom | -0.009 |
Sunny | -0.009 |
Token | were |
Token ID | 547 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
vell | +0.100 |
wheel | +0.090 |
disl | +0.089 |
inations | +0.088 |
od | +0.087 |
Neg logit contributions | |
crib | -0.053 |
ara | -0.050 |
Mom | -0.048 |
mom | -0.048 |
bunny | -0.046 |
Token | gone |
Token ID | 3750 |
Feature activation | -4.82e-03 |
Pos logit contributions | |
vell | +0.061 |
wheel | +0.055 |
disl | +0.053 |
inations | +0.052 |
od | +0.052 |
Neg logit contributions | |
crib | -0.037 |
Mom | -0.035 |
mom | -0.034 |
ara | -0.034 |
Sunny | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
vell | +0.013 |
wheel | +0.012 |
disl | +0.012 |
inations | +0.011 |
od | +0.011 |
Neg logit contributions | |
crib | -0.005 |
ara | -0.005 |
mom | -0.005 |
Mom | -0.005 |
bunny | -0.004 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
vell | +0.033 |
wheel | +0.030 |
inations | +0.030 |
disl | +0.029 |
ologist | +0.029 |
Neg logit contributions | |
ara | -0.007 |
Mom | -0.007 |
crib | -0.007 |
Mom | -0.006 |
mom | -0.006 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.67e-03 |
Pos logit contributions | |
crib | +0.097 |
ara | +0.096 |
Mom | +0.092 |
mom | +0.085 |
Sunny | +0.081 |
Neg logit contributions | |
vell | -0.220 |
wheel | -0.203 |
disl | -0.195 |
inations | -0.194 |
od | -0.191 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.61e-03 |
Pos logit contributions | |
ara | +0.010 |
crib | +0.009 |
mom | +0.009 |
Mom | +0.009 |
Mom | +0.008 |
Neg logit contributions | |
vell | -0.023 |
wheel | -0.022 |
disl | -0.021 |
inations | -0.020 |
cher | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
ara | +0.002 |
crib | +0.002 |
Mom | +0.002 |
mom | +0.001 |
um | +0.001 |
Neg logit contributions | |
vell | -0.004 |
wheel | -0.004 |
inations | -0.004 |
disl | -0.004 |
od | -0.004 |
Token | time |
Token ID | 640 |
Feature activation | +8.83e-03 |
Pos logit contributions | |
crib | +0.017 |
bunny | +0.016 |
cash | +0.016 |
ham | +0.016 |
Mom | +0.016 |
Neg logit contributions | |
vell | -0.027 |
inations | -0.027 |
disl | -0.026 |
wheel | -0.025 |
od | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
crib | +0.006 |
ara | +0.006 |
Mom | +0.006 |
mom | +0.005 |
Sunny | +0.005 |
Neg logit contributions | |
vell | -0.026 |
wheel | -0.025 |
disl | -0.024 |
inations | -0.024 |
od | -0.023 |
Token | him |
Token ID | 683 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
vell | +0.203 |
wheel | +0.190 |
disl | +0.181 |
inations | +0.179 |
od | +0.176 |
Neg logit contributions | |
ara | -0.094 |
crib | -0.094 |
Mom | -0.089 |
mom | -0.080 |
Sunny | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | -6.17e-03 |
Pos logit contributions | |
mom | +0.034 |
crib | +0.033 |
bunny | +0.027 |
Mom | +0.027 |
end | +0.026 |
Neg logit contributions | |
vell | -0.115 |
wheel | -0.104 |
disl | -0.103 |
od | -0.103 |
inations | -0.101 |
Token | She |
Token ID | 1375 |
Feature activation | +7.22e-03 |
Pos logit contributions | |
vell | +0.015 |
wheel | +0.014 |
disl | +0.014 |
smart | +0.013 |
od | +0.013 |
Neg logit contributions | |
ara | -0.007 |
crib | -0.007 |
Mom | -0.006 |
End | -0.006 |
chicken | -0.006 |
Token | found |
Token ID | 1043 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
crib | +0.013 |
ara | +0.012 |
Mom | +0.012 |
Sunny | +0.011 |
beef | +0.011 |
Neg logit contributions | |
vell | -0.014 |
wheel | -0.013 |
inations | -0.012 |
disl | -0.012 |
od | -0.012 |
Token | him |
Token ID | 683 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
vell | +0.144 |
wheel | +0.134 |
disl | +0.127 |
inations | +0.125 |
od | +0.125 |
Neg logit contributions | |
ara | -0.071 |
crib | -0.070 |
Mom | -0.066 |
mom | -0.060 |
End | -0.058 |
Token | lying |
Token ID | 9105 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
crib | +0.048 |
ara | +0.047 |
Mom | +0.045 |
mom | +0.043 |
Sunny | +0.041 |
Neg logit contributions | |
vell | -0.100 |
wheel | -0.093 |
disl | -0.089 |
inations | -0.088 |
od | -0.087 |
Token | on |
Token ID | 319 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
crib | +0.146 |
ara | +0.144 |
Mom | +0.140 |
mom | +0.130 |
Sunny | +0.126 |
Neg logit contributions | |
vell | -0.249 |
wheel | -0.229 |
disl | -0.214 |
inations | -0.214 |
od | -0.212 |
Token | the |
Token ID | 262 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
vell | +0.062 |
wheel | +0.059 |
disl | +0.056 |
od | +0.055 |
inations | +0.054 |
Neg logit contributions | |
ara | -0.034 |
crib | -0.033 |
Mom | -0.032 |
End | -0.029 |
mom | -0.029 |
Token | ground |
Token ID | 2323 |
Feature activation | +6.52e-03 |
Pos logit contributions | |
vell | +0.039 |
wheel | +0.036 |
disl | +0.034 |
inations | +0.034 |
od | +0.034 |
Neg logit contributions | |
crib | -0.019 |
ara | -0.018 |
Mom | -0.018 |
mom | -0.017 |
Sunny | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
crib | +0.006 |
ara | +0.006 |
Mom | +0.006 |
mom | +0.005 |
Sunny | +0.005 |
Neg logit contributions | |
vell | -0.018 |
wheel | -0.017 |
disl | -0.016 |
inations | -0.016 |
od | -0.016 |
Token | not |
Token ID | 407 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
crib | +0.034 |
ara | +0.033 |
Mom | +0.032 |
mom | +0.031 |
Sunny | +0.029 |
Neg logit contributions | |
vell | -0.054 |
wheel | -0.049 |
disl | -0.046 |
inations | -0.046 |
od | -0.046 |
Token | cooperate |
Token ID | 21270 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
vell | +0.004 |
wheel | +0.004 |
inations | +0.003 |
od | +0.003 |
disl | +0.003 |
Neg logit contributions | |
crib | -0.002 |
ara | -0.002 |
Mom | -0.002 |
mom | -0.002 |
bunny | -0.002 |
Token | than |
Token ID | 621 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
crib | +0.011 |
ara | +0.011 |
Mom | +0.010 |
mom | +0.010 |
end | +0.008 |
Neg logit contributions | |
vell | -0.042 |
wheel | -0.040 |
disl | -0.037 |
inations | -0.036 |
cher | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | -1.71e-03 |
Pos logit contributions | |
vell | +0.166 |
wheel | +0.150 |
disl | +0.141 |
od | +0.140 |
inations | +0.139 |
Neg logit contributions | |
crib | -0.096 |
mom | -0.094 |
Mom | -0.092 |
ara | -0.091 |
Sunny | -0.087 |
Token | compete |
Token ID | 9320 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
vell | +0.004 |
wheel | +0.003 |
inations | +0.003 |
od | +0.003 |
disl | +0.003 |
Neg logit contributions | |
ara | -0.002 |
Mom | -0.002 |
crib | -0.002 |
mom | -0.002 |
Mom | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
vell | +0.064 |
wheel | +0.059 |
disl | +0.059 |
inations | +0.058 |
ologist | +0.055 |
Neg logit contributions | |
mom | -0.017 |
Mom | -0.016 |
crib | -0.016 |
ara | -0.016 |
Mom | -0.015 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
crib | +0.002 |
ara | +0.002 |
Mom | +0.002 |
mom | +0.002 |
bunny | +0.001 |
Neg logit contributions | |
vell | -0.003 |
wheel | -0.003 |
disl | -0.003 |
od | -0.003 |
inations | -0.003 |
Token | L |
Token ID | 43 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
crib | +0.112 |
ara | +0.107 |
Mom | +0.107 |
mom | +0.102 |
nurse | +0.096 |
Neg logit contributions | |
vell | -0.188 |
wheel | -0.175 |
od | -0.167 |
disl | -0.163 |
inations | -0.161 |
Token | ily |
Token ID | 813 |
Feature activation | +2.66e-03 |
Pos logit contributions | |
vell | +0.057 |
od | +0.052 |
wheel | +0.051 |
inations | +0.051 |
asing | +0.047 |
Neg logit contributions | |
crib | -0.045 |
Mom | -0.044 |
bunny | -0.041 |
ara | -0.040 |
Sunny | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -9.57e-03 |
Pos logit contributions | |
crib | +0.003 |
ara | +0.003 |
Mom | +0.003 |
mom | +0.003 |
Sunny | +0.003 |
Neg logit contributions | |
vell | -0.007 |
wheel | -0.006 |
disl | -0.006 |
inations | -0.006 |
od | -0.006 |
Token | Sam |
Token ID | 3409 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
vell | +0.024 |
wheel | +0.022 |
disl | +0.022 |
od | +0.021 |
inations | +0.021 |
Neg logit contributions | |
crib | -0.011 |
ara | -0.011 |
Mom | -0.010 |
End | -0.009 |
beef | -0.009 |
Token | were |
Token ID | 547 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
vell | +0.162 |
wheel | +0.147 |
inations | +0.140 |
disl | +0.135 |
od | +0.135 |
Neg logit contributions | |
ara | -0.116 |
crib | -0.113 |
Mom | -0.110 |
mom | -0.105 |
Sunny | -0.101 |
Token | longer |
Token ID | 2392 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
crib | +0.007 |
Mom | +0.006 |
ara | +0.006 |
Sunny | +0.006 |
End | +0.005 |
Neg logit contributions | |
vell | -0.015 |
wheel | -0.014 |
inations | -0.014 |
asing | -0.013 |
od | -0.013 |
Token | sad |
Token ID | 6507 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
crib | +0.062 |
ara | +0.057 |
mom | +0.056 |
Mom | +0.055 |
bunny | +0.053 |
Neg logit contributions | |
vell | -0.107 |
wheel | -0.098 |
inations | -0.093 |
disl | -0.091 |
cher | -0.090 |
Token | or |
Token ID | 393 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
vell | +0.038 |
wheel | +0.035 |
inations | +0.033 |
disl | +0.033 |
od | +0.032 |
Neg logit contributions | |
crib | -0.016 |
ara | -0.016 |
Mom | -0.015 |
mom | -0.014 |
bunny | -0.013 |
Token | hungry |
Token ID | 14720 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
vell | +0.259 |
wheel | +0.233 |
inations | +0.223 |
od | +0.221 |
disl | +0.220 |
Neg logit contributions | |
crib | -0.152 |
ara | -0.145 |
Mom | -0.143 |
mom | -0.141 |
Sunny | -0.134 |
Token | ! |
Token ID | 0 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
vell | +0.018 |
wheel | +0.016 |
inations | +0.016 |
disl | +0.016 |
od | +0.015 |
Neg logit contributions | |
crib | -0.008 |
ara | -0.008 |
Mom | -0.007 |
mom | -0.007 |
Sunny | -0.007 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
vell | +0.079 |
wheel | +0.074 |
disl | +0.071 |
od | +0.070 |
inations | +0.070 |
Neg logit contributions | |
crib | -0.029 |
ara | -0.028 |
Mom | -0.027 |
mom | -0.024 |
Sunny | -0.023 |
Token | Tom |
Token ID | 13787 |
Feature activation | -1.11e-03 |
Pos logit contributions | |
crib | +0.089 |
ara | +0.085 |
Mom | +0.084 |
mom | +0.079 |
Sunny | +0.074 |
Neg logit contributions | |
vell | -0.183 |
wheel | -0.170 |
od | -0.161 |
disl | -0.160 |
inations | -0.159 |
Token | my |
Token ID | 1820 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
vell | +0.002 |
wheel | +0.002 |
disl | +0.002 |
inations | +0.002 |
od | +0.002 |
Neg logit contributions | |
crib | -0.002 |
ara | -0.002 |
Mom | -0.002 |
mom | -0.002 |
Sunny | -0.002 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
vell | +0.138 |
wheel | +0.129 |
disl | +0.124 |
inations | +0.122 |
od | +0.122 |
Neg logit contributions | |
crib | -0.069 |
ara | -0.066 |
Mom | -0.065 |
mom | -0.060 |
Sunny | -0.057 |
Token | riding |
Token ID | 10311 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
ara | +0.155 |
Mom | +0.148 |
crib | +0.147 |
End | +0.132 |
um | +0.131 |
Neg logit contributions | |
vell | -0.217 |
wheel | -0.203 |
disl | -0.198 |
inations | -0.191 |
od | -0.191 |
Token | his |
Token ID | 465 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
vell | +0.024 |
wheel | +0.022 |
disl | +0.021 |
inations | +0.021 |
od | +0.020 |
Neg logit contributions | |
crib | -0.015 |
ara | -0.014 |
Mom | -0.014 |
mom | -0.013 |
Sunny | -0.013 |
Token | Bob |
Token ID | 18861 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
vell | +0.048 |
wheel | +0.045 |
od | +0.043 |
inations | +0.043 |
disl | +0.043 |
Neg logit contributions | |
crib | -0.033 |
ara | -0.030 |
mom | -0.029 |
eyes | -0.027 |
ham | -0.027 |
Token | smiled |
Token ID | 13541 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
crib | +0.090 |
ara | +0.086 |
Mom | +0.084 |
mom | +0.076 |
Sunny | +0.073 |
Neg logit contributions | |
vell | -0.208 |
wheel | -0.194 |
disl | -0.185 |
inations | -0.183 |
od | -0.183 |
Token | and |
Token ID | 290 |
Feature activation | -8.52e-03 |
Pos logit contributions | |
ara | +0.078 |
crib | +0.077 |
Mom | +0.072 |
nurse | +0.066 |
beef | +0.066 |
Neg logit contributions | |
vell | -0.115 |
wheel | -0.101 |
od | -0.100 |
cast | -0.097 |
smart | -0.094 |
Token | said |
Token ID | 531 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
vell | +0.020 |
wheel | +0.019 |
inations | +0.018 |
disl | +0.018 |
od | +0.018 |
Neg logit contributions | |
crib | -0.011 |
ara | -0.011 |
Mom | -0.011 |
mom | -0.010 |
Sunny | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
ara | +0.011 |
crib | +0.010 |
Mom | +0.010 |
mom | +0.008 |
nurse | +0.008 |
Neg logit contributions | |
vell | -0.028 |
wheel | -0.026 |
od | -0.025 |
disl | -0.025 |
inations | -0.024 |
Token | " |
Token ID | 366 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
crib | +0.014 |
ara | +0.014 |
Mom | +0.013 |
mom | +0.011 |
Sunny | +0.011 |
Neg logit contributions | |
vell | -0.042 |
wheel | -0.040 |
disl | -0.038 |
od | -0.038 |
inations | -0.037 |
Token | We |
Token ID | 1135 |
Feature activation | -3.97e-03 |
Pos logit contributions | |
crib | +0.038 |
ara | +0.037 |
Mom | +0.036 |
mom | +0.033 |
Sunny | +0.032 |
Neg logit contributions | |
vell | -0.084 |
wheel | -0.078 |
disl | -0.075 |
inations | -0.074 |
od | -0.073 |
Token | have |
Token ID | 423 |
Feature activation | -9.99e-03 |
Pos logit contributions | |
vell | +0.009 |
wheel | +0.008 |
disl | +0.008 |
inations | +0.008 |
od | +0.008 |
Neg logit contributions | |
crib | -0.005 |
Mom | -0.005 |
mom | -0.005 |
ara | -0.005 |
end | -0.005 |
Token | gained |
Token ID | 8618 |
Feature activation | +2.60e-03 |
Pos logit contributions | |
vell | +0.026 |
wheel | +0.024 |
disl | +0.023 |
inations | +0.023 |
od | +0.023 |
Neg logit contributions | |
crib | -0.011 |
ara | -0.010 |
Mom | -0.010 |
mom | -0.009 |
Sunny | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
crib | +0.002 |
mom | +0.002 |
Sunny | +0.002 |
Mom | +0.002 |
ara | +0.002 |
Neg logit contributions | |
vell | -0.008 |
wheel | -0.007 |
inations | -0.007 |
od | -0.007 |
ologist | -0.007 |
Token | new |
Token ID | 649 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ara | +0.017 |
Mom | +0.016 |
crib | +0.016 |
Sunny | +0.014 |
End | +0.014 |
Neg logit contributions | |
vell | -0.036 |
wheel | -0.033 |
disl | -0.031 |
inations | -0.031 |
od | -0.030 |
Token | someone |
Token ID | 2130 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
vell | +0.168 |
wheel | +0.154 |
disl | +0.148 |
inations | +0.146 |
od | +0.144 |
Neg logit contributions | |
crib | -0.057 |
mom | -0.057 |
ara | -0.056 |
Mom | -0.054 |
me | -0.053 |
Token | more |
Token ID | 517 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
vell | +0.112 |
wheel | +0.105 |
inations | +0.098 |
disl | +0.098 |
od | +0.097 |
Neg logit contributions | |
bunny | -0.039 |
True | -0.039 |
crib | -0.039 |
mom | -0.038 |
Sunny | -0.038 |
Token | powerful |
Token ID | 3665 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
crib | +0.050 |
mom | +0.049 |
True | +0.046 |
End | +0.045 |
beef | +0.045 |
Neg logit contributions | |
vell | -0.103 |
wheel | -0.097 |
od | -0.089 |
ount | -0.088 |
cher | -0.088 |
Token | than |
Token ID | 621 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
vell | +0.184 |
wheel | +0.167 |
inations | +0.155 |
od | +0.154 |
disl | +0.153 |
Neg logit contributions | |
crib | -0.093 |
bunny | -0.086 |
mom | -0.086 |
End | -0.084 |
ara | -0.084 |
Token | yourself |
Token ID | 3511 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
vell | +0.197 |
wheel | +0.181 |
disl | +0.170 |
inations | +0.169 |
od | +0.168 |
Neg logit contributions | |
crib | -0.101 |
mom | -0.099 |
Sunny | -0.096 |
bunny | -0.094 |
beef | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
vell | +0.228 |
wheel | +0.213 |
inations | +0.208 |
disl | +0.206 |
od | +0.198 |
Neg logit contributions | |
crib | -0.074 |
bunny | -0.066 |
ara | -0.065 |
Sunny | -0.063 |
mom | -0.062 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
vell | +0.021 |
wheel | +0.019 |
inations | +0.018 |
disl | +0.018 |
od | +0.018 |
Neg logit contributions | |
crib | -0.007 |
ara | -0.007 |
Mom | -0.007 |
mom | -0.006 |
Sunny | -0.006 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.14e-04 |
Pos logit contributions | |
crib | +0.083 |
ara | +0.081 |
Mom | +0.078 |
mom | +0.071 |
Sunny | +0.068 |
Neg logit contributions | |
vell | -0.210 |
wheel | -0.195 |
disl | -0.187 |
inations | -0.186 |
od | -0.184 |
Token | there |
Token ID | 612 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
vell | +0.000 |
wheel | +0.000 |
disl | +0.000 |
inations | +0.000 |
od | +0.000 |
Neg logit contributions | |
crib | -0.000 |
ara | -0.000 |
Mom | -0.000 |
mom | -0.000 |
Sunny | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | +3.47e-03 |
Pos logit contributions | |
vell | +0.077 |
wheel | +0.072 |
disl | +0.069 |
od | +0.069 |
inations | +0.068 |
Neg logit contributions | |
crib | -0.029 |
ara | -0.028 |
Mom | -0.027 |
mom | -0.023 |
beef | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +4.95e-03 |
Pos logit contributions | |
ara | +0.005 |
crib | +0.005 |
Mom | +0.004 |
nurse | +0.004 |
cash | +0.004 |
Neg logit contributions | |
vell | -0.007 |
wheel | -0.007 |
od | -0.007 |
disl | -0.007 |
inations | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
vell | +0.045 |
wheel | +0.042 |
disl | +0.040 |
inations | +0.040 |
od | +0.039 |
Neg logit contributions | |
crib | -0.023 |
ara | -0.023 |
Mom | -0.021 |
mom | -0.020 |
Sunny | -0.019 |
Token | letter |
Token ID | 3850 |
Feature activation | +6.48e-02 |
Pos logit contributions | |
Mom | +0.016 |
ara | +0.016 |
crib | +0.015 |
Sunny | +0.014 |
End | +0.014 |
Neg logit contributions | |
vell | -0.025 |
wheel | -0.023 |
inations | -0.021 |
disl | -0.021 |
od | -0.021 |
Token | in |
Token ID | 287 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
crib | +0.086 |
ara | +0.086 |
Mom | +0.081 |
mom | +0.075 |
Sunny | +0.074 |
Neg logit contributions | |
vell | -0.152 |
wheel | -0.142 |
od | -0.131 |
inations | -0.130 |
disl | -0.130 |
Token | the |
Token ID | 262 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
crib | +0.032 |
ara | +0.031 |
Mom | +0.030 |
mom | +0.028 |
Sunny | +0.027 |
Neg logit contributions | |
vell | -0.051 |
wheel | -0.047 |
disl | -0.045 |
inations | -0.044 |
od | -0.044 |
Token | mail |
Token ID | 6920 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
vell | +0.050 |
wheel | +0.047 |
disl | +0.045 |
ologist | +0.043 |
od | +0.043 |
Neg logit contributions | |
ara | -0.025 |
Sunny | -0.022 |
crib | -0.022 |
Mom | -0.021 |
Goose | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -8.20e-03 |
Pos logit contributions | |
crib | +0.075 |
ara | +0.074 |
Mom | +0.071 |
Sunny | +0.065 |
mom | +0.065 |
Neg logit contributions | |
vell | -0.143 |
wheel | -0.134 |
od | -0.124 |
disl | -0.123 |
inations | -0.123 |
Token | It |
Token ID | 632 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
vell | +0.020 |
wheel | +0.019 |
disl | +0.018 |
od | +0.017 |
inations | +0.017 |
Neg logit contributions | |
crib | -0.010 |
ara | -0.010 |
Mom | -0.010 |
mom | -0.009 |
Sunny | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +8.89e-03 |
Pos logit contributions | |
crib | +0.031 |
ara | +0.030 |
Mom | +0.028 |
mom | +0.026 |
Sunny | +0.025 |
Neg logit contributions | |
vell | -0.076 |
wheel | -0.071 |
disl | -0.067 |
inations | -0.067 |
od | -0.066 |
Token | from |
Token ID | 422 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
ara | +0.012 |
crib | +0.011 |
Mom | +0.010 |
bunny | +0.009 |
Sunny | +0.009 |
Neg logit contributions | |
vell | -0.021 |
wheel | -0.020 |
od | -0.018 |
inations | -0.018 |
disl | -0.018 |
Token | his |
Token ID | 465 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
vell | +0.136 |
wheel | +0.127 |
disl | +0.120 |
inations | +0.118 |
od | +0.118 |
Neg logit contributions | |
ara | -0.075 |
crib | -0.073 |
Mom | -0.071 |
bunny | -0.063 |
mom | -0.063 |
Token | grandma |
Token ID | 49890 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
vell | +0.031 |
wheel | +0.029 |
disl | +0.028 |
od | +0.028 |
inations | +0.028 |
Neg logit contributions | |
ara | -0.010 |
Mom | -0.009 |
crib | -0.008 |
Sunny | -0.008 |
End | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
vell | +0.046 |
wheel | +0.044 |
disl | +0.041 |
od | +0.040 |
inations | +0.040 |
Neg logit contributions | |
ara | -0.029 |
crib | -0.028 |
Mom | -0.027 |
End | -0.025 |
um | -0.024 |
Token | might |
Token ID | 1244 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
crib | +0.030 |
ara | +0.029 |
Mom | +0.028 |
mom | +0.027 |
bunny | +0.027 |
Neg logit contributions | |
vell | -0.117 |
wheel | -0.107 |
inations | -0.106 |
disl | -0.104 |
od | -0.103 |
Token | not |
Token ID | 407 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
crib | +0.025 |
ara | +0.025 |
Mom | +0.024 |
mom | +0.023 |
Sunny | +0.023 |
Neg logit contributions | |
vell | -0.041 |
wheel | -0.037 |
inations | -0.035 |
od | -0.035 |
disl | -0.035 |
Token | be |
Token ID | 307 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
vell | +0.081 |
wheel | +0.074 |
disl | +0.070 |
inations | +0.070 |
od | +0.070 |
Neg logit contributions | |
crib | -0.052 |
ara | -0.051 |
Mom | -0.050 |
mom | -0.048 |
Sunny | -0.046 |
Token | good |
Token ID | 922 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
crib | +0.021 |
ara | +0.020 |
mom | +0.019 |
beef | +0.019 |
Sunny | +0.019 |
Neg logit contributions | |
vell | -0.039 |
wheel | -0.036 |
disl | -0.034 |
inations | -0.034 |
od | -0.033 |
Token | for |
Token ID | 329 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
vell | +0.144 |
wheel | +0.132 |
inations | +0.126 |
disl | +0.126 |
od | +0.123 |
Neg logit contributions | |
crib | -0.054 |
ara | -0.052 |
mom | -0.050 |
Mom | -0.047 |
bunny | -0.047 |
Token | him |
Token ID | 683 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
ara | +0.035 |
crib | +0.035 |
Mom | +0.034 |
mom | +0.030 |
nurse | +0.030 |
Neg logit contributions | |
vell | -0.055 |
wheel | -0.051 |
disl | -0.048 |
inations | -0.048 |
od | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
crib | +0.029 |
mom | +0.026 |
ara | +0.026 |
Mom | +0.025 |
Sunny | +0.025 |
Neg logit contributions | |
vell | -0.081 |
wheel | -0.074 |
disl | -0.071 |
inations | -0.071 |
od | -0.070 |
Token | Max |
Token ID | 5436 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
vell | +0.038 |
wheel | +0.038 |
disl | +0.036 |
od | +0.034 |
inations | +0.034 |
Neg logit contributions | |
crib | -0.019 |
ara | -0.018 |
Mom | -0.018 |
beef | -0.016 |
End | -0.016 |
Token | listened |
Token ID | 16399 |
Feature activation | +7.83e-02 |
Pos logit contributions | |
crib | +0.032 |
ara | +0.028 |
Mom | +0.028 |
beef | +0.027 |
End | +0.026 |
Neg logit contributions | |
wheel | -0.030 |
vell | -0.029 |
disl | -0.028 |
od | -0.027 |
achieve | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
crib | +0.103 |
ara | +0.100 |
Mom | +0.095 |
End | +0.085 |
Sunny | +0.084 |
Neg logit contributions | |
vell | -0.184 |
wheel | -0.174 |
od | -0.164 |
disl | -0.163 |
inations | -0.161 |
Token | they |
Token ID | 484 |
Feature activation | -9.39e-03 |
Pos logit contributions | |
vell | +0.159 |
wheel | +0.147 |
disl | +0.146 |
inations | +0.140 |
od | +0.138 |
Neg logit contributions | |
crib | -0.104 |
ara | -0.104 |
Mom | -0.099 |
End | -0.089 |
mom | -0.088 |
Token | hugged |
Token ID | 41130 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
vell | +0.023 |
wheel | +0.021 |
disl | +0.020 |
od | +0.020 |
inations | +0.019 |
Neg logit contributions | |
ara | -0.011 |
crib | -0.011 |
Mom | -0.011 |
mom | -0.011 |
bunny | -0.011 |
Token | him |
Token ID | 683 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
crib | +0.043 |
ara | +0.043 |
End | +0.041 |
um | +0.039 |
Mom | +0.039 |
Neg logit contributions | |
vell | -0.046 |
disl | -0.042 |
od | -0.042 |
wheel | -0.041 |
smart | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -8.32e-04 |
Pos logit contributions | |
ara | +0.039 |
Mom | +0.038 |
crib | +0.038 |
End | +0.033 |
um | +0.032 |
Neg logit contributions | |
vell | -0.070 |
wheel | -0.064 |
od | -0.060 |
inations | -0.060 |
disl | -0.059 |
Token | They |
Token ID | 1119 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
disl | +0.002 |
vell | +0.001 |
cast | +0.001 |
od | +0.001 |
wheel | +0.001 |
Neg logit contributions | |
End | -0.001 |
end | -0.001 |
crib | -0.001 |
ara | -0.001 |
bunny | -0.001 |
Token | drank |
Token ID | 24070 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
crib | +0.052 |
ara | +0.051 |
Mom | +0.050 |
mom | +0.048 |
Sunny | +0.045 |
Neg logit contributions | |
vell | -0.083 |
wheel | -0.076 |
disl | -0.072 |
inations | -0.071 |
od | -0.071 |
Token | their |
Token ID | 511 |
Feature activation | +9.60e-03 |
Pos logit contributions | |
ara | +0.082 |
crib | +0.077 |
Mom | +0.073 |
End | +0.072 |
nurse | +0.068 |
Neg logit contributions | |
vell | -0.118 |
wheel | -0.113 |
disl | -0.108 |
cast | -0.107 |
od | -0.102 |
Token | hot |
Token ID | 3024 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
ara | +0.012 |
crib | +0.012 |
Mom | +0.011 |
End | +0.010 |
nurse | +0.010 |
Neg logit contributions | |
vell | -0.022 |
inations | -0.020 |
disl | -0.020 |
wheel | -0.020 |
cast | -0.019 |
Token | chocolate |
Token ID | 11311 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
crib | +0.046 |
ara | +0.045 |
Mom | +0.045 |
vet | +0.041 |
End | +0.041 |
Neg logit contributions | |
vell | -0.085 |
disl | -0.082 |
wheel | -0.081 |
inations | -0.079 |
cast | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | -5.48e-03 |
Pos logit contributions | |
ara | +0.121 |
crib | +0.116 |
Mom | +0.116 |
End | +0.110 |
nurse | +0.100 |
Neg logit contributions | |
vell | -0.234 |
wheel | -0.223 |
cast | -0.207 |
od | -0.204 |
disl | -0.202 |
Token | ate |
Token ID | 15063 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
vell | +0.012 |
wheel | +0.011 |
disl | +0.011 |
inations | +0.011 |
od | +0.010 |
Neg logit contributions | |
ara | -0.008 |
crib | -0.008 |
Mom | -0.007 |
um | -0.007 |
End | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
vell | +0.057 |
wheel | +0.055 |
od | +0.049 |
cher | +0.048 |
ologist | +0.047 |
Neg logit contributions | |
ara | -0.036 |
crib | -0.036 |
Mom | -0.034 |
Sunny | -0.032 |
mom | -0.031 |
Token | He |
Token ID | 679 |
Feature activation | -9.85e-03 |
Pos logit contributions | |
vell | +0.033 |
wheel | +0.029 |
inations | +0.029 |
disl | +0.029 |
od | +0.028 |
Neg logit contributions | |
ara | -0.015 |
crib | -0.015 |
Mom | -0.015 |
mom | -0.014 |
Mom | -0.013 |
Token | shouted |
Token ID | 17293 |
Feature activation | +1.93e-03 |
Pos logit contributions | |
vell | +0.019 |
wheel | +0.018 |
od | +0.017 |
disl | +0.017 |
inations | +0.017 |
Neg logit contributions | |
crib | -0.017 |
ara | -0.015 |
Sunny | -0.014 |
beef | -0.014 |
Mom | -0.014 |
Token | with |
Token ID | 351 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
ara | +0.002 |
crib | +0.002 |
Mom | +0.002 |
End | +0.002 |
Sunny | +0.002 |
Neg logit contributions | |
vell | -0.005 |
wheel | -0.005 |
od | -0.004 |
disl | -0.004 |
inations | -0.004 |
Token | g |
Token ID | 308 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
crib | +0.043 |
ara | +0.043 |
Mom | +0.041 |
mom | +0.038 |
Sunny | +0.037 |
Neg logit contributions | |
vell | -0.081 |
wheel | -0.075 |
disl | -0.071 |
inations | -0.070 |
od | -0.070 |
Token | lee |
Token ID | 7197 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
vell | +0.042 |
wheel | +0.037 |
cher | +0.033 |
inations | +0.032 |
disl | +0.032 |
Neg logit contributions | |
ara | -0.067 |
crib | -0.067 |
Mom | -0.065 |
mom | -0.064 |
um | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
vell | +0.427 |
wheel | +0.401 |
od | +0.378 |
disl | +0.378 |
inations | +0.374 |
Neg logit contributions | |
crib | -0.175 |
ara | -0.172 |
Mom | -0.167 |
mom | -0.147 |
Sunny | -0.140 |
Token | " |
Token ID | 366 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
crib | +0.014 |
ara | +0.013 |
Mom | +0.012 |
mom | +0.011 |
Sunny | +0.010 |
Neg logit contributions | |
vell | -0.041 |
wheel | -0.039 |
disl | -0.037 |
od | -0.037 |
inations | -0.036 |
Token | Look |
Token ID | 8567 |
Feature activation | +8.90e-03 |
Pos logit contributions | |
ara | +0.028 |
Mom | +0.028 |
crib | +0.027 |
mom | +0.023 |
bunny | +0.021 |
Neg logit contributions | |
vell | -0.087 |
wheel | -0.080 |
disl | -0.078 |
inations | -0.078 |
od | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
mom | +0.009 |
ara | +0.009 |
Mom | +0.008 |
Mom | +0.008 |
um | +0.008 |
Neg logit contributions | |
vell | -0.024 |
wheel | -0.023 |
disl | -0.023 |
inations | -0.022 |
achieve | -0.021 |
Token | Molly |
Token ID | 30236 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
mom | +0.022 |
Mom | +0.021 |
ara | +0.019 |
Mom | +0.019 |
bunny | +0.019 |
Neg logit contributions | |
vell | -0.037 |
inations | -0.034 |
wheel | -0.033 |
disl | -0.033 |
asing | -0.032 |
Token | alright |
Token ID | 23036 |
Feature activation | -4.25e-03 |
Pos logit contributions | |
crib | +0.070 |
ara | +0.069 |
Mom | +0.067 |
mom | +0.062 |
Sunny | +0.060 |
Neg logit contributions | |
vell | -0.123 |
wheel | -0.114 |
disl | -0.108 |
inations | -0.107 |
od | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | +1.43e-03 |
Pos logit contributions | |
vell | +0.010 |
disl | +0.009 |
wheel | +0.009 |
od | +0.009 |
inations | +0.009 |
Neg logit contributions | |
crib | -0.005 |
ara | -0.005 |
Mom | -0.005 |
End | -0.004 |
nurse | -0.004 |
Token | Lucky |
Token ID | 27963 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
crib | +0.002 |
ara | +0.002 |
Mom | +0.002 |
mom | +0.002 |
Sunny | +0.001 |
Neg logit contributions | |
vell | -0.003 |
wheel | -0.003 |
disl | -0.003 |
inations | -0.003 |
od | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
ara | +0.026 |
crib | +0.026 |
Mom | +0.024 |
mom | +0.023 |
Sunny | +0.022 |
Neg logit contributions | |
vell | -0.057 |
wheel | -0.052 |
inations | -0.050 |
disl | -0.050 |
od | -0.049 |
Token | You |
Token ID | 921 |
Feature activation | -9.76e-03 |
Pos logit contributions | |
vell | +0.046 |
wheel | +0.043 |
disl | +0.042 |
inations | +0.040 |
od | +0.040 |
Neg logit contributions | |
crib | -0.031 |
ara | -0.030 |
Mom | -0.029 |
mom | -0.027 |
beef | -0.026 |
Token | don |
Token ID | 836 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
vell | +0.020 |
wheel | +0.018 |
disl | +0.018 |
cast | +0.017 |
od | +0.017 |
Neg logit contributions | |
mom | -0.015 |
bunny | -0.015 |
crib | -0.015 |
Sunny | -0.014 |
Mom | -0.014 |
Token | 't |
Token ID | 470 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
vell | +0.159 |
disl | +0.142 |
wheel | +0.141 |
inations | +0.139 |
od | +0.135 |
Neg logit contributions | |
Mom | -0.075 |
crib | -0.073 |
ara | -0.071 |
mom | -0.066 |
um | -0.063 |
Token | need |
Token ID | 761 |
Feature activation | +6.44e-03 |
Pos logit contributions | |
vell | +0.099 |
wheel | +0.083 |
inations | +0.081 |
cher | +0.080 |
od | +0.079 |
Neg logit contributions | |
crib | -0.067 |
ara | -0.067 |
Mom | -0.067 |
mom | -0.064 |
bunny | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | -4.52e-03 |
Pos logit contributions | |
crib | +0.008 |
ara | +0.008 |
Mom | +0.008 |
mom | +0.007 |
End | +0.007 |
Neg logit contributions | |
vell | -0.015 |
wheel | -0.014 |
disl | -0.014 |
inations | -0.014 |
od | -0.013 |
Token | work |
Token ID | 670 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
vell | +0.011 |
wheel | +0.010 |
inations | +0.009 |
disl | +0.009 |
od | +0.009 |
Neg logit contributions | |
crib | -0.006 |
ara | -0.006 |
Mom | -0.006 |
mom | -0.006 |
Sunny | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
vell | +0.163 |
wheel | +0.147 |
disl | +0.142 |
od | +0.142 |
ologist | +0.138 |
Neg logit contributions | |
crib | -0.065 |
ara | -0.062 |
Mom | -0.061 |
mom | -0.060 |
beef | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | +6.60e-03 |
Pos logit contributions | |
ara | +0.021 |
crib | +0.020 |
Mom | +0.019 |
um | +0.016 |
Sunny | +0.016 |
Neg logit contributions | |
vell | -0.048 |
wheel | -0.046 |
disl | -0.043 |
od | -0.043 |
inations | -0.043 |
Token | drawer |
Token ID | 33451 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
ara | +0.009 |
Mom | +0.008 |
um | +0.008 |
Sunny | +0.008 |
crib | +0.008 |
Neg logit contributions | |
vell | -0.015 |
wheel | -0.014 |
inations | -0.013 |
disl | -0.013 |
cher | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
crib | +0.017 |
ara | +0.016 |
Mom | +0.016 |
mom | +0.015 |
bunny | +0.014 |
Neg logit contributions | |
vell | -0.042 |
wheel | -0.039 |
disl | -0.038 |
inations | -0.037 |
od | -0.037 |
Token | stayed |
Token ID | 9658 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
vell | +0.038 |
wheel | +0.035 |
disl | +0.034 |
inations | +0.034 |
od | +0.033 |
Neg logit contributions | |
crib | -0.022 |
ara | -0.021 |
Mom | -0.021 |
mom | -0.020 |
Sunny | -0.019 |
Token | away |
Token ID | 1497 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
crib | +0.065 |
ara | +0.063 |
Mom | +0.062 |
mom | +0.058 |
Sunny | +0.055 |
Neg logit contributions | |
vell | -0.117 |
wheel | -0.108 |
disl | -0.103 |
inations | -0.102 |
od | -0.101 |
Token | from |
Token ID | 422 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
vell | +0.045 |
wheel | +0.041 |
disl | +0.040 |
inations | +0.040 |
ologist | +0.039 |
Neg logit contributions | |
crib | -0.023 |
mom | -0.021 |
Mom | -0.020 |
ara | -0.020 |
Sunny | -0.020 |
Token | it |
Token ID | 340 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
vell | +0.162 |
wheel | +0.151 |
disl | +0.143 |
inations | +0.142 |
od | +0.142 |
Neg logit contributions | |
ara | -0.071 |
crib | -0.070 |
Mom | -0.068 |
mom | -0.060 |
Sunny | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
crib | +0.049 |
ara | +0.045 |
Mom | +0.045 |
mom | +0.043 |
Sunny | +0.041 |
Neg logit contributions | |
vell | -0.111 |
wheel | -0.102 |
disl | -0.100 |
inations | -0.098 |
od | -0.097 |
Token | Days |
Token ID | 12579 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
vell | +0.043 |
wheel | +0.041 |
disl | +0.040 |
od | +0.039 |
inations | +0.038 |
Neg logit contributions | |
crib | -0.017 |
ara | -0.016 |
Mom | -0.016 |
mom | -0.014 |
beef | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +9.54e-03 |
Pos logit contributions | |
vell | +0.140 |
wheel | +0.132 |
od | +0.123 |
inations | +0.120 |
cher | +0.119 |
Neg logit contributions | |
crib | -0.089 |
Mom | -0.084 |
ara | -0.083 |
mom | -0.076 |
Sunny | -0.075 |
Token | weeks |
Token ID | 2745 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
crib | +0.010 |
ara | +0.010 |
Mom | +0.009 |
mom | +0.009 |
bunny | +0.008 |
Neg logit contributions | |
vell | -0.025 |
wheel | -0.024 |
disl | -0.023 |
inations | -0.023 |
od | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +6.23e-03 |
Pos logit contributions | |
crib | +0.033 |
ara | +0.032 |
End | +0.029 |
beef | +0.028 |
um | +0.028 |
Neg logit contributions | |
vell | -0.044 |
wheel | -0.043 |
od | -0.038 |
disl | -0.037 |
cher | -0.036 |
Token | much |
Token ID | 881 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
ara | +0.011 |
Mom | +0.009 |
crib | +0.009 |
End | +0.009 |
� | +0.009 |
Neg logit contributions | |
vell | -0.012 |
wheel | -0.012 |
supposed | -0.010 |
od | -0.010 |
disl | -0.009 |
Token | com |
Token ID | 401 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
vell | +0.076 |
wheel | +0.073 |
inations | +0.065 |
smart | +0.063 |
disl | +0.061 |
Neg logit contributions | |
ara | -0.063 |
Mom | -0.056 |
crib | -0.056 |
Sunny | -0.053 |
End | -0.053 |
Token | f |
Token ID | 69 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
vell | +0.127 |
wheel | +0.116 |
inations | +0.108 |
disl | +0.107 |
od | +0.104 |
Neg logit contributions | |
crib | -0.105 |
ara | -0.100 |
Mom | -0.100 |
mom | -0.096 |
Sunny | -0.092 |
Token | ier |
Token ID | 959 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
vell | +0.065 |
wheel | +0.058 |
disl | +0.056 |
inations | +0.054 |
od | +0.053 |
Neg logit contributions | |
crib | -0.070 |
ara | -0.069 |
Mom | -0.067 |
mom | -0.064 |
Sunny | -0.063 |
Token | than |
Token ID | 621 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
vell | +0.268 |
wheel | +0.249 |
inations | +0.234 |
disl | +0.234 |
od | +0.226 |
Neg logit contributions | |
crib | -0.182 |
ara | -0.175 |
mom | -0.166 |
Mom | -0.163 |
bunny | -0.159 |
Token | any |
Token ID | 597 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
vell | +0.203 |
wheel | +0.188 |
disl | +0.178 |
inations | +0.178 |
od | +0.177 |
Neg logit contributions | |
crib | -0.097 |
ara | -0.096 |
Mom | -0.094 |
mom | -0.084 |
bunny | -0.080 |
Token | of |
Token ID | 286 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
vell | +0.064 |
wheel | +0.060 |
inations | +0.057 |
cher | +0.054 |
od | +0.054 |
Neg logit contributions | |
ara | -0.038 |
Mom | -0.038 |
crib | -0.034 |
um | -0.032 |
End | -0.032 |
Token | her |
Token ID | 607 |
Feature activation | +2.62e-03 |
Pos logit contributions | |
Mom | +0.034 |
ara | +0.034 |
um | +0.031 |
crib | +0.031 |
End | +0.029 |
Neg logit contributions | |
vell | -0.053 |
disl | -0.050 |
wheel | -0.050 |
od | -0.048 |
inations | -0.047 |
Token | l |
Token ID | 300 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
Mom | +0.003 |
ara | +0.003 |
crib | +0.003 |
End | +0.003 |
beef | +0.003 |
Neg logit contributions | |
vell | -0.006 |
wheel | -0.005 |
inations | -0.005 |
od | -0.005 |
disl | -0.005 |
Token | ilies |
Token ID | 3922 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
crib | +0.115 |
ara | +0.114 |
Mom | +0.111 |
mom | +0.106 |
Sunny | +0.104 |
Neg logit contributions | |
vell | -0.095 |
wheel | -0.084 |
disl | -0.081 |
inations | -0.078 |
od | -0.076 |
Token | couldn |
Token ID | 3521 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
vell | +0.019 |
wheel | +0.018 |
disl | +0.017 |
inations | +0.017 |
od | +0.016 |
Neg logit contributions | |
crib | -0.011 |
ara | -0.011 |
Mom | -0.010 |
mom | -0.010 |
Sunny | -0.009 |
Token | 't |
Token ID | 470 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
vell | +0.086 |
wheel | +0.080 |
disl | +0.075 |
inations | +0.074 |
od | +0.074 |
Neg logit contributions | |
crib | -0.058 |
ara | -0.057 |
Mom | -0.055 |
mom | -0.052 |
Sunny | -0.050 |
Token | hear |
Token ID | 3285 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
vell | +0.105 |
disl | +0.094 |
wheel | +0.091 |
asing | +0.090 |
inations | +0.089 |
Neg logit contributions | |
mom | -0.061 |
Mom | -0.060 |
end | -0.060 |
crib | -0.057 |
bunny | -0.057 |
Token | any |
Token ID | 597 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
vell | +0.150 |
wheel | +0.140 |
inations | +0.133 |
disl | +0.133 |
od | +0.130 |
Neg logit contributions | |
crib | -0.059 |
ara | -0.057 |
Mom | -0.055 |
mom | -0.052 |
Sunny | -0.049 |
Token | cars |
Token ID | 5006 |
Feature activation | -9.43e-02 |
Pos logit contributions | |
vell | +0.064 |
wheel | +0.059 |
disl | +0.056 |
inations | +0.056 |
od | +0.056 |
Neg logit contributions | |
crib | -0.035 |
ara | -0.034 |
Mom | -0.033 |
mom | -0.031 |
Sunny | -0.030 |
Token | or |
Token ID | 393 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
vell | +0.256 |
disl | +0.232 |
inations | +0.223 |
ont | +0.215 |
asing | +0.213 |
Neg logit contributions | |
end | -0.086 |
crib | -0.084 |
mom | -0.080 |
bunny | -0.076 |
nurse | -0.075 |
Token | people |
Token ID | 661 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
vell | +0.259 |
wheel | +0.235 |
inations | +0.219 |
od | +0.219 |
asing | +0.215 |
Neg logit contributions | |
crib | -0.144 |
mom | -0.138 |
bunny | -0.128 |
Sunny | -0.127 |
Mom | -0.127 |
Token | talking |
Token ID | 3375 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
vell | +0.178 |
wheel | +0.157 |
disl | +0.154 |
inations | +0.153 |
asing | +0.148 |
Neg logit contributions | |
crib | -0.076 |
mom | -0.069 |
bunny | -0.066 |
Sunny | -0.064 |
nurse | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
vell | +0.032 |
wheel | +0.030 |
inations | +0.029 |
disl | +0.029 |
cher | +0.028 |
Neg logit contributions | |
crib | -0.011 |
mom | -0.010 |
Mom | -0.009 |
Mom | -0.009 |
ara | -0.009 |
Token | |
Token ID | 220 |
Feature activation | +1.63e-03 |
Pos logit contributions | |
vell | +0.039 |
wheel | +0.037 |
disl | +0.036 |
od | +0.035 |
inations | +0.035 |
Neg logit contributions | |
crib | -0.016 |
ara | -0.015 |
Mom | -0.015 |
mom | -0.013 |
bunny | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
ara | +0.001 |
crib | +0.001 |
Mom | +0.001 |
mom | +0.001 |
Mom | +0.001 |
Neg logit contributions | |
vell | -0.005 |
wheel | -0.005 |
inations | -0.005 |
disl | -0.005 |
ologist | -0.005 |
Token | sharing |
Token ID | 7373 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
crib | +0.017 |
ara | +0.017 |
Mom | +0.016 |
mom | +0.016 |
Sunny | +0.015 |
Neg logit contributions | |
vell | -0.030 |
wheel | -0.028 |
inations | -0.026 |
disl | -0.026 |
od | -0.026 |
Token | is |
Token ID | 318 |
Feature activation | +4.55e-03 |
Pos logit contributions | |
crib | +0.026 |
mom | +0.025 |
Mom | +0.024 |
ara | +0.024 |
True | +0.022 |
Neg logit contributions | |
vell | -0.102 |
wheel | -0.093 |
inations | -0.091 |
od | -0.089 |
disl | -0.089 |
Token | important |
Token ID | 1593 |
Feature activation | +9.80e-03 |
Pos logit contributions | |
mom | +0.005 |
Mom | +0.005 |
crib | +0.005 |
Mom | +0.004 |
End | +0.004 |
Neg logit contributions | |
vell | -0.012 |
wheel | -0.011 |
od | -0.011 |
inations | -0.010 |
ologist | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
crib | +0.010 |
ara | +0.009 |
Mom | +0.009 |
mom | +0.009 |
beef | +0.008 |
Neg logit contributions | |
vell | -0.027 |
wheel | -0.025 |
inations | -0.024 |
disl | -0.024 |
od | -0.024 |
Token | qu |
Token ID | 627 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
vell | +0.034 |
wheel | +0.030 |
od | +0.029 |
inations | +0.029 |
ologist | +0.029 |
Neg logit contributions | |
crib | -0.016 |
mom | -0.016 |
Mom | -0.015 |
Mom | -0.015 |
ara | -0.014 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
vell | +0.063 |
wheel | +0.055 |
cher | +0.051 |
disl | +0.051 |
inations | +0.049 |
Neg logit contributions | |
ara | -0.082 |
Mom | -0.081 |
crib | -0.081 |
um | -0.078 |
End | -0.074 |
Token | lling |
Token ID | 2680 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
vell | +0.470 |
wheel | +0.439 |
disl | +0.426 |
ooters | +0.409 |
cher | +0.402 |
Neg logit contributions | |
crib | -0.201 |
girl | -0.190 |
end | -0.188 |
Mom | -0.185 |
End | -0.182 |
Token | is |
Token ID | 318 |
Feature activation | +4.86e-03 |
Pos logit contributions | |
vell | +0.301 |
wheel | +0.278 |
inations | +0.268 |
disl | +0.264 |
od | +0.262 |
Neg logit contributions | |
crib | -0.105 |
ara | -0.096 |
mom | -0.094 |
Mom | -0.091 |
bunny | -0.086 |
Token | not |
Token ID | 407 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
mom | +0.005 |
crib | +0.005 |
Mom | +0.005 |
ara | +0.005 |
End | +0.005 |
Neg logit contributions | |
vell | -0.013 |
wheel | -0.011 |
inations | -0.011 |
od | -0.011 |
disl | -0.011 |
Token | good |
Token ID | 922 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
vell | +0.085 |
wheel | +0.076 |
inations | +0.073 |
od | +0.072 |
disl | +0.072 |
Neg logit contributions | |
crib | -0.039 |
mom | -0.037 |
beef | -0.035 |
bunny | -0.034 |
Sunny | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
vell | +0.134 |
wheel | +0.123 |
inations | +0.119 |
cher | +0.116 |
disl | +0.116 |
Neg logit contributions | |
crib | -0.043 |
mom | -0.043 |
ara | -0.040 |
Mom | -0.038 |
bunny | -0.036 |
Token | it |
Token ID | 340 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
vell | +0.076 |
wheel | +0.071 |
disl | +0.070 |
inations | +0.069 |
ologist | +0.068 |
Neg logit contributions | |
crib | -0.023 |
mom | -0.023 |
Mom | -0.021 |
ara | -0.021 |
Mom | -0.021 |
Token | - |
Token ID | 532 |
Feature activation | +6.91e-03 |
Pos logit contributions | |
crib | +0.036 |
mom | +0.032 |
Mom | +0.029 |
Mom | +0.029 |
one | +0.028 |
Neg logit contributions | |
vell | -0.144 |
disl | -0.140 |
inations | -0.135 |
wheel | -0.131 |
ologist | -0.131 |
Token | not |
Token ID | 407 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
crib | +0.007 |
ara | +0.007 |
Mom | +0.007 |
mom | +0.006 |
Sunny | +0.006 |
Neg logit contributions | |
vell | -0.018 |
wheel | -0.017 |
disl | -0.016 |
inations | -0.016 |
od | -0.016 |
Token | even |
Token ID | 772 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
vell | +0.082 |
wheel | +0.074 |
disl | +0.074 |
inations | +0.073 |
cher | +0.072 |
Neg logit contributions | |
crib | -0.032 |
mom | -0.032 |
one | -0.029 |
Mom | -0.028 |
bunny | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
vell | +0.146 |
wheel | +0.132 |
inations | +0.127 |
ologist | +0.127 |
disl | +0.126 |
Neg logit contributions | |
mom | -0.052 |
crib | -0.050 |
one | -0.049 |
bunny | -0.048 |
Sunny | -0.045 |
Token | tallest |
Token ID | 38760 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
vell | +0.041 |
wheel | +0.038 |
disl | +0.036 |
inations | +0.036 |
od | +0.035 |
Neg logit contributions | |
ara | -0.020 |
crib | -0.019 |
Mom | -0.019 |
mom | -0.017 |
Sunny | -0.016 |
Token | tree |
Token ID | 5509 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
vell | +0.517 |
wheel | +0.480 |
disl | +0.457 |
inations | +0.454 |
od | +0.451 |
Neg logit contributions | |
crib | -0.235 |
ara | -0.233 |
Mom | -0.225 |
mom | -0.204 |
Sunny | -0.198 |
Token | . |
Token ID | 13 |
Feature activation | -9.38e-03 |
Pos logit contributions | |
crib | +0.028 |
ara | +0.026 |
mom | +0.026 |
bunny | +0.025 |
Sunny | +0.024 |
Neg logit contributions | |
vell | -0.068 |
disl | -0.063 |
inations | -0.062 |
wheel | -0.061 |
ologist | -0.060 |
Token | |
Token ID | 220 |
Feature activation | +4.79e-03 |
Pos logit contributions | |
vell | +0.022 |
wheel | +0.021 |
disl | +0.020 |
od | +0.020 |
inations | +0.019 |
Neg logit contributions | |
ara | -0.011 |
crib | -0.010 |
Mom | -0.010 |
chicken | -0.009 |
End | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
Mom | +0.003 |
ara | +0.002 |
mom | +0.002 |
crib | +0.002 |
Mom | +0.002 |
Neg logit contributions | |
vell | -0.016 |
wheel | -0.015 |
disl | -0.015 |
inations | -0.014 |
ologist | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
vell | +0.053 |
wheel | +0.050 |
disl | +0.047 |
inations | +0.047 |
od | +0.047 |
Neg logit contributions | |
crib | -0.019 |
ara | -0.019 |
Mom | -0.018 |
mom | -0.016 |
Sunny | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
vell | +0.117 |
disl | +0.108 |
wheel | +0.108 |
inations | +0.105 |
ologist | +0.101 |
Neg logit contributions | |
crib | -0.031 |
mom | -0.027 |
ara | -0.025 |
Mom | -0.023 |
one | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
crib | +0.030 |
ara | +0.027 |
Mom | +0.027 |
mom | +0.026 |
beef | +0.024 |
Neg logit contributions | |
vell | -0.074 |
wheel | -0.069 |
inations | -0.066 |
disl | -0.065 |
od | -0.065 |
Token | forest |
Token ID | 8222 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
vell | +0.039 |
wheel | +0.036 |
inations | +0.034 |
od | +0.034 |
disl | +0.034 |
Neg logit contributions | |
crib | -0.021 |
Mom | -0.020 |
ara | -0.019 |
mom | -0.019 |
beef | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -7.52e-03 |
Pos logit contributions | |
vell | +0.045 |
disl | +0.041 |
wheel | +0.041 |
inations | +0.040 |
asing | +0.039 |
Neg logit contributions | |
crib | -0.013 |
mom | -0.011 |
shop | -0.010 |
beef | -0.010 |
bunny | -0.010 |
Token | Bub |
Token ID | 19645 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
vell | +0.011 |
wheel | +0.010 |
disl | +0.009 |
inations | +0.009 |
od | +0.009 |
Neg logit contributions | |
crib | -0.017 |
ara | -0.016 |
Mom | -0.016 |
mom | -0.015 |
Sunny | -0.015 |
Token | bles |
Token ID | 7689 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
disl | +0.168 |
wheel | +0.165 |
vell | +0.152 |
inations | +0.146 |
opl | +0.140 |
Neg logit contributions | |
ara | -0.206 |
Mom | -0.186 |
friend | -0.180 |
um | -0.180 |
me | -0.179 |
Token | told |
Token ID | 1297 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
vell | +0.540 |
wheel | +0.496 |
disl | +0.478 |
inations | +0.473 |
od | +0.459 |
Neg logit contributions | |
crib | -0.271 |
ara | -0.269 |
Mom | -0.266 |
mom | -0.253 |
bunny | -0.238 |
Token | him |
Token ID | 683 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
vell | +0.043 |
wheel | +0.040 |
inations | +0.038 |
disl | +0.038 |
od | +0.037 |
Neg logit contributions | |
crib | -0.024 |
ara | -0.023 |
Mom | -0.022 |
mom | -0.022 |
Sunny | -0.021 |
Token | that |
Token ID | 326 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
crib | +0.049 |
ara | +0.047 |
mom | +0.046 |
Mom | +0.045 |
Sunny | +0.043 |
Neg logit contributions | |
vell | -0.094 |
wheel | -0.086 |
disl | -0.082 |
inations | -0.081 |
od | -0.079 |
Token | he |
Token ID | 339 |
Feature activation | -9.85e-03 |
Pos logit contributions | |
mom | +0.023 |
crib | +0.023 |
bunny | +0.022 |
beef | +0.022 |
Sunny | +0.022 |
Neg logit contributions | |
vell | -0.053 |
wheel | -0.047 |
inations | -0.046 |
asing | -0.044 |
disl | -0.044 |
Token | was |
Token ID | 373 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
vell | +0.023 |
wheel | +0.021 |
disl | +0.021 |
inations | +0.020 |
od | +0.020 |
Neg logit contributions | |
ara | -0.013 |
crib | -0.013 |
Mom | -0.012 |
mom | -0.012 |
bunny | -0.011 |
Token | 't |
Token ID | 470 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
vell | +0.087 |
wheel | +0.080 |
disl | +0.076 |
inations | +0.075 |
od | +0.075 |
Neg logit contributions | |
crib | -0.058 |
ara | -0.057 |
Mom | -0.055 |
mom | -0.052 |
Sunny | -0.050 |
Token | play |
Token ID | 711 |
Feature activation | +9.84e-03 |
Pos logit contributions | |
vell | +0.088 |
wheel | +0.078 |
disl | +0.076 |
inations | +0.075 |
od | +0.075 |
Neg logit contributions | |
crib | -0.048 |
Mom | -0.048 |
ara | -0.046 |
mom | -0.046 |
Mom | -0.042 |
Token | with |
Token ID | 351 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
crib | +0.010 |
ara | +0.009 |
Mom | +0.009 |
mom | +0.008 |
Sunny | +0.008 |
Neg logit contributions | |
vell | -0.027 |
wheel | -0.025 |
inations | -0.024 |
disl | -0.024 |
od | -0.024 |
Token | your |
Token ID | 534 |
Feature activation | +9.88e-03 |
Pos logit contributions | |
crib | +0.043 |
ara | +0.042 |
Mom | +0.040 |
mom | +0.037 |
Sunny | +0.035 |
Neg logit contributions | |
vell | -0.092 |
wheel | -0.085 |
disl | -0.081 |
inations | -0.080 |
od | -0.080 |
Token | mar |
Token ID | 1667 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
crib | +0.012 |
ara | +0.012 |
Mom | +0.011 |
mom | +0.010 |
Sunny | +0.010 |
Neg logit contributions | |
vell | -0.024 |
wheel | -0.022 |
disl | -0.022 |
inations | -0.021 |
od | -0.021 |
Token | bles |
Token ID | 7689 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
disl | +0.244 |
wheel | +0.197 |
recognise | +0.194 |
smart | +0.192 |
achieve | +0.189 |
Neg logit contributions | |
ara | -0.312 |
um | -0.289 |
Mom | -0.282 |
crib | -0.278 |
ham | -0.273 |
Token | ." |
Token ID | 526 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
vell | +0.526 |
disl | +0.507 |
wheel | +0.478 |
inations | +0.474 |
od | +0.463 |
Neg logit contributions | |
crib | -0.301 |
ara | -0.287 |
mom | -0.268 |
bunny | -0.262 |
Mom | -0.262 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
vell | +0.058 |
wheel | +0.054 |
disl | +0.053 |
od | +0.051 |
inations | +0.051 |
Neg logit contributions | |
crib | -0.025 |
ara | -0.024 |
Mom | -0.023 |
mom | -0.021 |
End | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
vell | +0.030 |
wheel | +0.028 |
disl | +0.027 |
inations | +0.027 |
od | +0.027 |
Neg logit contributions | |
crib | -0.012 |
ara | -0.011 |
Mom | -0.010 |
mom | -0.010 |
bunny | -0.009 |
Token | Tim |
Token ID | 14967 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
vell | +0.025 |
wheel | +0.023 |
disl | +0.022 |
inations | +0.021 |
od | +0.021 |
Neg logit contributions | |
crib | -0.014 |
ara | -0.014 |
Mom | -0.013 |
mom | -0.013 |
Sunny | -0.012 |
Token | my |
Token ID | 1820 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
vell | +0.028 |
wheel | +0.025 |
disl | +0.024 |
inations | +0.024 |
od | +0.023 |
Neg logit contributions | |
ara | -0.019 |
crib | -0.018 |
Mom | -0.018 |
mom | -0.017 |
bunny | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
vell | +0.040 |
wheel | +0.038 |
od | +0.037 |
inations | +0.035 |
cher | +0.034 |
Neg logit contributions | |
ara | -0.026 |
crib | -0.026 |
Mom | -0.025 |
End | -0.023 |
kitten | -0.022 |
Token | She |
Token ID | 1375 |
Feature activation | -2.23e-03 |
Pos logit contributions | |
vell | +0.031 |
wheel | +0.029 |
disl | +0.028 |
od | +0.027 |
inations | +0.027 |
Neg logit contributions | |
crib | -0.012 |
ara | -0.012 |
Mom | -0.011 |
End | -0.010 |
bunny | -0.010 |
Token | built |
Token ID | 3170 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
vell | +0.006 |
wheel | +0.005 |
disl | +0.005 |
inations | +0.005 |
od | +0.005 |
Neg logit contributions | |
crib | -0.003 |
ara | -0.003 |
Mom | -0.003 |
mom | -0.002 |
Sunny | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +5.29e-03 |
Pos logit contributions | |
vell | +0.084 |
wheel | +0.078 |
disl | +0.074 |
od | +0.074 |
inations | +0.074 |
Neg logit contributions | |
crib | -0.039 |
ara | -0.038 |
Mom | -0.037 |
mom | -0.033 |
Sunny | -0.032 |
Token | sand |
Token ID | 6450 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
ara | +0.008 |
crib | +0.008 |
Mom | +0.007 |
Sunny | +0.007 |
End | +0.007 |
Neg logit contributions | |
vell | -0.012 |
wheel | -0.011 |
inations | -0.010 |
disl | -0.010 |
od | -0.010 |
Token | castle |
Token ID | 18676 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
vell | +0.102 |
wheel | +0.090 |
disl | +0.088 |
inations | +0.084 |
od | +0.079 |
Neg logit contributions | |
crib | -0.156 |
ara | -0.156 |
Mom | -0.151 |
mom | -0.149 |
bunny | -0.143 |
Token | and |
Token ID | 290 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
vell | +0.591 |
disl | +0.558 |
inations | +0.537 |
wheel | +0.535 |
od | +0.517 |
Neg logit contributions | |
crib | -0.135 |
ara | -0.134 |
Mom | -0.123 |
mom | -0.121 |
Mom | -0.104 |
Token | decorated |
Token ID | 24789 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
vell | +0.040 |
wheel | +0.036 |
disl | +0.034 |
inations | +0.034 |
od | +0.033 |
Neg logit contributions | |
crib | -0.023 |
ara | -0.023 |
Mom | -0.023 |
mom | -0.022 |
bunny | -0.020 |
Token | it |
Token ID | 340 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
vell | +0.036 |
wheel | +0.034 |
disl | +0.032 |
od | +0.032 |
inations | +0.032 |
Neg logit contributions | |
crib | -0.015 |
ara | -0.014 |
Mom | -0.014 |
mom | -0.012 |
Sunny | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
ara | +0.046 |
crib | +0.045 |
Mom | +0.044 |
mom | +0.038 |
Sunny | +0.037 |
Neg logit contributions | |
vell | -0.111 |
wheel | -0.103 |
od | -0.098 |
inations | -0.097 |
disl | -0.097 |
Token | seas |
Token ID | 21547 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
crib | +0.044 |
ara | +0.043 |
Mom | +0.042 |
mom | +0.039 |
Sunny | +0.038 |
Neg logit contributions | |
vell | -0.064 |
wheel | -0.059 |
disl | -0.055 |
inations | -0.055 |
od | -0.055 |