Token | cream |
Token ID | 8566 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
berry | +0.069 |
Will | +0.069 |
wherever | +0.068 |
stuffed | +0.068 |
mine | +0.067 |
Neg logit contributions | |
site | -0.052 |
her | -0.049 |
ia | -0.042 |
wasteful | -0.042 |
office | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
site | +0.242 |
her | +0.239 |
office | +0.224 |
ia | +0.210 |
wasteful | +0.205 |
Neg logit contributions | |
mine | -0.281 |
wherever | -0.281 |
Benny | -0.278 |
Will | -0.277 |
berry | -0.275 |
Token | available |
Token ID | 1695 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
site | +0.063 |
office | +0.056 |
her | +0.055 |
ia | +0.054 |
ups | +0.051 |
Neg logit contributions | |
Benny | -0.054 |
wherever | -0.054 |
ease | -0.053 |
mattered | -0.052 |
Will | -0.052 |
Token | at |
Token ID | 379 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
her | +0.164 |
site | +0.164 |
office | +0.155 |
wasteful | +0.143 |
ia | +0.143 |
Neg logit contributions | |
mine | -0.148 |
berry | -0.144 |
Will | -0.143 |
superstar | -0.141 |
mattered | -0.139 |
Token | the |
Token ID | 262 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
mine | +0.061 |
Benny | +0.060 |
wherever | +0.059 |
Will | +0.059 |
berry | +0.058 |
Neg logit contributions | |
site | -0.062 |
her | -0.060 |
office | -0.057 |
ia | -0.055 |
wasteful | -0.054 |
Token | pharmacy |
Token ID | 32763 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
site | +0.013 |
her | +0.012 |
ia | +0.012 |
wasteful | +0.011 |
ups | +0.010 |
Neg logit contributions | |
berry | -0.017 |
wherever | -0.017 |
mine | -0.016 |
superstar | -0.016 |
ease | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
site | +1.071 |
her | +1.055 |
office | +0.990 |
ia | +0.963 |
wasteful | +0.954 |
Neg logit contributions | |
mine | -0.777 |
wherever | -0.767 |
Benny | -0.759 |
berry | -0.755 |
Will | -0.755 |
Token | so |
Token ID | 523 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
her | +0.025 |
site | +0.025 |
office | +0.024 |
wasteful | +0.022 |
ia | +0.022 |
Neg logit contributions | |
mine | -0.021 |
berry | -0.020 |
mattered | -0.020 |
superstar | -0.020 |
ease | -0.020 |
Token | they |
Token ID | 484 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
site | +0.129 |
her | +0.128 |
office | +0.121 |
ia | +0.117 |
wasteful | +0.115 |
Neg logit contributions | |
mine | -0.092 |
berry | -0.089 |
wherever | -0.088 |
Will | -0.087 |
Benny | -0.086 |
Token | went |
Token ID | 1816 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
her | +0.005 |
site | +0.005 |
office | +0.005 |
wasteful | +0.004 |
ups | +0.004 |
Neg logit contributions | |
Nice | -0.005 |
berry | -0.005 |
wherever | -0.005 |
superstar | -0.005 |
mattered | -0.005 |
Token | there |
Token ID | 612 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
site | +0.249 |
her | +0.246 |
office | +0.234 |
ia | +0.222 |
wasteful | +0.220 |
Neg logit contributions | |
mine | -0.168 |
berry | -0.164 |
Will | -0.163 |
Benny | -0.163 |
wherever | -0.162 |
Token | They |
Token ID | 1119 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Will | +0.001 |
Benny | +0.001 |
wherever | +0.001 |
mine | +0.001 |
berry | +0.001 |
Neg logit contributions | |
site | -0.001 |
her | -0.001 |
office | -0.001 |
wasteful | -0.001 |
ia | -0.001 |
Token | help |
Token ID | 1037 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
her | +0.157 |
site | +0.157 |
office | +0.149 |
ia | +0.143 |
wasteful | +0.141 |
Neg logit contributions | |
berry | -0.124 |
mine | -0.123 |
Benny | -0.122 |
Will | -0.122 |
wherever | -0.121 |
Token | him |
Token ID | 683 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
mine | +0.151 |
Will | +0.148 |
Benny | +0.145 |
wherever | +0.142 |
berry | +0.142 |
Neg logit contributions | |
site | -0.350 |
her | -0.343 |
office | -0.328 |
wasteful | -0.318 |
ia | -0.317 |
Token | fix |
Token ID | 4259 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
mine | +0.031 |
berry | +0.031 |
Benny | +0.031 |
Will | +0.030 |
wherever | +0.030 |
Neg logit contributions | |
site | -0.040 |
her | -0.040 |
office | -0.038 |
ia | -0.036 |
wasteful | -0.035 |
Token | his |
Token ID | 465 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
site | +0.024 |
her | +0.024 |
office | +0.023 |
wasteful | +0.022 |
ia | +0.022 |
Neg logit contributions | |
mine | -0.015 |
Benny | -0.015 |
wherever | -0.015 |
Will | -0.015 |
berry | -0.015 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
wherever | +0.174 |
berry | +0.172 |
stuffed | +0.171 |
mine | +0.168 |
mattered | +0.167 |
Neg logit contributions | |
her | -0.184 |
site | -0.182 |
ia | -0.162 |
wasteful | -0.159 |
office | -0.155 |
Token | . |
Token ID | 13 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
site | +1.146 |
her | +1.125 |
wasteful | +1.110 |
ia | +1.094 |
yourselves | +1.058 |
Neg logit contributions | |
wherever | -0.623 |
mine | -0.619 |
mattered | -0.549 |
whenever | -0.541 |
berry | -0.535 |
Token | They |
Token ID | 1119 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Will | +0.001 |
Benny | +0.001 |
wherever | +0.001 |
mine | +0.001 |
berry | +0.001 |
Neg logit contributions | |
site | -0.001 |
her | -0.001 |
office | -0.001 |
wasteful | -0.001 |
ia | -0.001 |
Token | put |
Token ID | 1234 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
site | +0.162 |
her | +0.161 |
office | +0.152 |
ia | +0.145 |
wasteful | +0.144 |
Neg logit contributions | |
mine | -0.119 |
berry | -0.117 |
Benny | -0.116 |
wherever | -0.116 |
Will | -0.116 |
Token | back |
Token ID | 736 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
site | +0.368 |
her | +0.366 |
office | +0.345 |
ia | +0.324 |
wasteful | +0.324 |
Neg logit contributions | |
mine | -0.291 |
berry | -0.288 |
superstar | -0.285 |
mattered | -0.285 |
Will | -0.284 |
Token | his |
Token ID | 465 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
mine | +0.084 |
berry | +0.082 |
Benny | +0.082 |
Will | +0.082 |
wherever | +0.081 |
Neg logit contributions | |
site | -0.091 |
her | -0.090 |
office | -0.085 |
ia | -0.080 |
wasteful | -0.079 |
Token | can |
Token ID | 460 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
site | +0.033 |
her | +0.032 |
office | +0.032 |
ia | +0.030 |
wasteful | +0.030 |
Neg logit contributions | |
mine | -0.022 |
berry | -0.021 |
superstar | -0.021 |
mattered | -0.021 |
ease | -0.021 |
Token | I |
Token ID | 314 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
superstar | +0.261 |
berry | +0.259 |
ease | +0.257 |
mine | +0.256 |
mattered | +0.250 |
Neg logit contributions | |
site | -0.265 |
office | -0.250 |
her | -0.248 |
ia | -0.231 |
yourselves | -0.224 |
Token | go |
Token ID | 467 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
mattered | +0.155 |
superstar | +0.154 |
Benny | +0.152 |
mine | +0.152 |
berry | +0.150 |
Neg logit contributions | |
office | -0.138 |
her | -0.137 |
site | -0.137 |
ia | -0.124 |
gate | -0.114 |
Token | in |
Token ID | 287 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
site | +0.351 |
her | +0.348 |
ia | +0.322 |
office | +0.322 |
wasteful | +0.319 |
Neg logit contributions | |
wherever | -0.234 |
mine | -0.231 |
Will | -0.228 |
Benny | -0.228 |
berry | -0.226 |
Token | the |
Token ID | 262 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
wherever | +0.021 |
Benny | +0.021 |
Will | +0.021 |
mine | +0.020 |
berry | +0.020 |
Neg logit contributions | |
her | -0.032 |
site | -0.032 |
wasteful | -0.030 |
ia | -0.030 |
office | -0.029 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
ia | +0.011 |
her | +0.010 |
site | +0.009 |
ooked | +0.009 |
iders | +0.009 |
Neg logit contributions | |
play | -0.024 |
wherever | -0.024 |
Happy | -0.024 |
g | -0.024 |
Ros | -0.023 |
Token | ?" |
Token ID | 1701 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
her | +1.036 |
site | +1.034 |
ia | +1.015 |
wasteful | +0.987 |
ups | +0.917 |
Neg logit contributions | |
mine | -0.771 |
wherever | -0.741 |
Will | -0.718 |
berry | -0.708 |
Benny | -0.700 |
Token | He |
Token ID | 679 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
mine | +0.005 |
wherever | +0.005 |
berry | +0.005 |
superstar | +0.005 |
ease | +0.005 |
Neg logit contributions | |
site | -0.007 |
her | -0.007 |
office | -0.006 |
ia | -0.006 |
wasteful | -0.006 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
site | +0.136 |
wasteful | +0.134 |
her | +0.133 |
yourselves | +0.125 |
office | +0.124 |
Neg logit contributions | |
Will | -0.067 |
stuffed | -0.057 |
Benny | -0.057 |
Grac | -0.056 |
mine | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
site | +0.085 |
her | +0.084 |
office | +0.080 |
ia | +0.075 |
wasteful | +0.072 |
Neg logit contributions | |
superstar | -0.076 |
berry | -0.076 |
mine | -0.076 |
wherever | -0.074 |
mattered | -0.074 |
Token |
|
Token ID | 198 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
mine | +0.002 |
wherever | +0.002 |
berry | +0.002 |
mattered | +0.001 |
superstar | +0.001 |
Neg logit contributions | |
site | -0.002 |
her | -0.002 |
office | -0.002 |
ia | -0.002 |
wasteful | -0.002 |
Token | went |
Token ID | 1816 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
her | +0.063 |
office | +0.062 |
site | +0.061 |
ia | +0.055 |
wasteful | +0.055 |
Neg logit contributions | |
superstar | -0.037 |
mattered | -0.037 |
Benny | -0.037 |
Will | -0.037 |
Nice | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
site | +0.251 |
her | +0.248 |
office | +0.236 |
ia | +0.223 |
wasteful | +0.221 |
Neg logit contributions | |
mine | -0.173 |
berry | -0.169 |
Will | -0.168 |
Benny | -0.167 |
wherever | -0.167 |
Token | the |
Token ID | 262 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
mattered | +0.005 |
mine | +0.005 |
superstar | +0.005 |
berry | +0.005 |
Nice | +0.005 |
Neg logit contributions | |
site | -0.006 |
her | -0.005 |
office | -0.005 |
wasteful | -0.005 |
ia | -0.005 |
Token | doctor |
Token ID | 6253 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
site | +0.019 |
her | +0.018 |
ia | +0.018 |
wasteful | +0.017 |
office | +0.016 |
Neg logit contributions | |
Benny | -0.018 |
wherever | -0.018 |
Will | -0.018 |
berry | -0.018 |
stuffed | -0.018 |
Token | 's |
Token ID | 338 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
site | +0.329 |
her | +0.326 |
office | +0.313 |
ia | +0.288 |
wasteful | +0.286 |
Neg logit contributions | |
mine | -0.272 |
Benny | -0.265 |
berry | -0.265 |
Will | -0.264 |
wherever | -0.263 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
berry | +0.083 |
stuffed | +0.083 |
wherever | +0.083 |
Will | +0.082 |
g | +0.081 |
Neg logit contributions | |
her | -0.026 |
site | -0.024 |
ia | -0.023 |
wasteful | -0.023 |
yourselves | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
site | +1.030 |
her | +1.013 |
office | +0.947 |
ia | +0.927 |
wasteful | +0.920 |
Neg logit contributions | |
mine | -0.803 |
wherever | -0.788 |
berry | -0.778 |
Benny | -0.776 |
Will | -0.774 |
Token |
|
Token ID | 198 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
mattered | +0.001 |
mine | +0.001 |
superstar | +0.001 |
wherever | +0.001 |
ease | +0.001 |
Neg logit contributions | |
site | -0.001 |
her | -0.001 |
office | -0.001 |
ia | -0.001 |
wasteful | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
mine | +0.022 |
Will | +0.021 |
Benny | +0.021 |
wherever | +0.021 |
berry | +0.021 |
Neg logit contributions | |
site | -0.033 |
her | -0.032 |
office | -0.031 |
wasteful | -0.030 |
ia | -0.030 |
Token | At |
Token ID | 2953 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
mine | +0.028 |
Will | +0.027 |
wherever | +0.027 |
berry | +0.027 |
Benny | +0.027 |
Neg logit contributions | |
site | -0.026 |
her | -0.025 |
office | -0.024 |
ia | -0.023 |
wasteful | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
her | +0.233 |
site | +0.230 |
ia | +0.217 |
wasteful | +0.214 |
ups | +0.210 |
Neg logit contributions | |
wherever | -0.141 |
Benny | -0.135 |
mine | -0.134 |
Will | -0.132 |
ease | -0.129 |
Token | something |
Token ID | 1223 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
site | +0.029 |
her | +0.029 |
office | +0.029 |
ia | +0.027 |
wasteful | +0.026 |
Neg logit contributions | |
mine | -0.026 |
berry | -0.025 |
superstar | -0.025 |
ease | -0.025 |
wherever | -0.024 |
Token | bad |
Token ID | 2089 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
site | +0.150 |
her | +0.146 |
office | +0.138 |
ia | +0.128 |
wasteful | +0.127 |
Neg logit contributions | |
Benny | -0.176 |
mine | -0.175 |
mattered | -0.175 |
Will | -0.174 |
wherever | -0.174 |
Token | is |
Token ID | 318 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
site | +0.258 |
her | +0.253 |
office | +0.237 |
ia | +0.225 |
wasteful | +0.223 |
Neg logit contributions | |
mine | -0.253 |
Benny | -0.248 |
wherever | -0.248 |
berry | -0.248 |
Will | -0.248 |
Token | in |
Token ID | 287 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
site | +0.146 |
office | +0.136 |
her | +0.136 |
ia | +0.128 |
wasteful | +0.120 |
Neg logit contributions | |
Benny | -0.214 |
wherever | -0.209 |
mattered | -0.207 |
Will | -0.203 |
stuffed | -0.196 |
Token | the |
Token ID | 262 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Benny | +0.024 |
Will | +0.023 |
wherever | +0.023 |
berry | +0.023 |
mine | +0.023 |
Neg logit contributions | |
site | -0.030 |
her | -0.029 |
ia | -0.028 |
office | -0.027 |
wasteful | -0.026 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
site | +0.018 |
her | +0.017 |
ia | +0.016 |
office | +0.015 |
wasteful | +0.015 |
Neg logit contributions | |
berry | -0.021 |
Benny | -0.021 |
wherever | -0.021 |
mine | -0.021 |
Will | -0.020 |
Token | ." |
Token ID | 526 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
site | +1.070 |
her | +1.059 |
ia | +0.991 |
office | +0.980 |
wasteful | +0.978 |
Neg logit contributions | |
mine | -0.749 |
wherever | -0.723 |
berry | -0.709 |
Will | -0.706 |
Benny | -0.702 |
Token |
|
Token ID | 198 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
mine | +0.153 |
Benny | +0.149 |
berry | +0.149 |
Will | +0.149 |
wherever | +0.148 |
Neg logit contributions | |
site | -0.286 |
her | -0.282 |
office | -0.268 |
wasteful | -0.258 |
ia | -0.257 |
Token |
|
Token ID | 198 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
Benny | +0.018 |
Will | +0.018 |
mine | +0.018 |
berry | +0.017 |
wherever | +0.017 |
Neg logit contributions | |
site | -0.036 |
her | -0.035 |
office | -0.034 |
wasteful | -0.034 |
men | -0.031 |
Token | His |
Token ID | 6653 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
mine | +0.024 |
Benny | +0.023 |
Will | +0.023 |
berry | +0.023 |
mattered | +0.023 |
Neg logit contributions | |
site | -0.030 |
her | -0.028 |
office | -0.028 |
wasteful | -0.027 |
men | -0.025 |
Token | mom |
Token ID | 1995 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
Will | +0.120 |
Benny | +0.119 |
stuffed | +0.118 |
mattered | +0.116 |
wherever | +0.116 |
Neg logit contributions | |
site | -0.142 |
her | -0.138 |
wasteful | -0.125 |
yourselves | -0.122 |
office | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
mine | +0.020 |
Will | +0.020 |
Benny | +0.020 |
berry | +0.020 |
wherever | +0.020 |
Neg logit contributions | |
site | -0.032 |
her | -0.032 |
office | -0.030 |
wasteful | -0.029 |
ia | -0.029 |
Token | At |
Token ID | 2953 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
mine | +0.027 |
Will | +0.027 |
Benny | +0.026 |
berry | +0.026 |
wherever | +0.026 |
Neg logit contributions | |
site | -0.028 |
her | -0.027 |
office | -0.026 |
wasteful | -0.025 |
ia | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
her | +0.234 |
site | +0.231 |
wasteful | +0.216 |
ia | +0.216 |
ups | +0.213 |
Neg logit contributions | |
wherever | -0.144 |
Benny | -0.142 |
Will | -0.134 |
mine | -0.129 |
Grac | -0.129 |
Token | vet |
Token ID | 20202 |
Feature activation | +7.19e+00 |
Pos logit contributions | |
site | +0.015 |
ia | +0.015 |
her | +0.015 |
cks | +0.014 |
wasteful | +0.014 |
Neg logit contributions | |
bunny | -0.021 |
wherever | -0.021 |
berry | -0.020 |
stuffed | -0.020 |
Will | -0.020 |
Token | 's |
Token ID | 338 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
site | +0.616 |
her | +0.607 |
office | +0.563 |
wasteful | +0.555 |
ia | +0.554 |
Neg logit contributions | |
Will | -0.407 |
Benny | -0.406 |
mine | -0.402 |
wherever | -0.401 |
berry | -0.397 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
wherever | +0.055 |
companion | +0.053 |
Will | +0.053 |
bunny | +0.052 |
stuffed | +0.052 |
Neg logit contributions | |
site | -0.054 |
her | -0.053 |
ia | -0.050 |
wasteful | -0.049 |
yourselves | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
site | +1.112 |
her | +1.100 |
wasteful | +1.021 |
ia | +1.018 |
office | +1.013 |
Neg logit contributions | |
mine | -0.692 |
wherever | -0.691 |
Benny | -0.678 |
Will | -0.668 |
mattered | -0.665 |
Token | the |
Token ID | 262 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
site | +0.032 |
her | +0.032 |
office | +0.030 |
ia | +0.029 |
wasteful | +0.029 |
Neg logit contributions | |
mine | -0.021 |
berry | -0.020 |
wherever | -0.020 |
Benny | -0.020 |
Will | -0.020 |
Token | doctor |
Token ID | 6253 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
site | +0.016 |
her | +0.015 |
ia | +0.014 |
cks | +0.013 |
ews | +0.013 |
Neg logit contributions | |
bunny | -0.021 |
stuffed | -0.021 |
Will | -0.020 |
wherever | -0.020 |
Benny | -0.020 |
Token | did |
Token ID | 750 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
site | +0.354 |
her | +0.349 |
office | +0.329 |
ia | +0.317 |
wasteful | +0.315 |
Neg logit contributions | |
mine | -0.247 |
Will | -0.241 |
berry | -0.241 |
Benny | -0.240 |
wherever | -0.240 |
Token | a |
Token ID | 257 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
site | +0.080 |
her | +0.078 |
office | +0.072 |
ia | +0.069 |
wasteful | +0.068 |
Neg logit contributions | |
wherever | -0.112 |
mine | -0.112 |
Benny | -0.111 |
Will | -0.111 |
mattered | -0.109 |
Token |
|
Token ID | 198 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
mine | +0.020 |
Will | +0.020 |
Benny | +0.020 |
berry | +0.020 |
wherever | +0.020 |
Neg logit contributions | |
site | -0.032 |
her | -0.032 |
office | -0.031 |
wasteful | -0.029 |
ia | -0.029 |
Token | At |
Token ID | 2953 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
mine | +0.028 |
Will | +0.027 |
berry | +0.026 |
wherever | +0.026 |
Benny | +0.026 |
Neg logit contributions | |
site | -0.026 |
her | -0.024 |
office | -0.024 |
ia | -0.023 |
wasteful | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
her | +0.241 |
site | +0.236 |
ia | +0.225 |
wasteful | +0.225 |
ups | +0.218 |
Neg logit contributions | |
wherever | -0.134 |
Benny | -0.130 |
Will | -0.128 |
mine | -0.127 |
Grac | -0.123 |
Token | doctor |
Token ID | 6253 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
ia | +0.016 |
cks | +0.016 |
site | +0.016 |
wasteful | +0.015 |
yourselves | +0.015 |
Neg logit contributions | |
Will | -0.020 |
wherever | -0.020 |
berry | -0.020 |
superstar | -0.020 |
stuffed | -0.019 |
Token | 's |
Token ID | 338 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
site | +0.353 |
her | +0.348 |
office | +0.325 |
ia | +0.318 |
wasteful | +0.316 |
Neg logit contributions | |
mine | -0.249 |
Will | -0.246 |
berry | -0.244 |
Benny | -0.244 |
wherever | -0.244 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
Will | +0.083 |
berry | +0.081 |
stuffed | +0.080 |
wherever | +0.080 |
join | +0.079 |
Neg logit contributions | |
her | -0.026 |
site | -0.024 |
wasteful | -0.024 |
ia | -0.023 |
yourselves | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
site | +1.129 |
her | +1.116 |
wasteful | +1.056 |
ia | +1.036 |
office | +1.020 |
Neg logit contributions | |
mine | -0.676 |
wherever | -0.670 |
Will | -0.650 |
Benny | -0.648 |
mattered | -0.646 |
Token | Lisa |
Token ID | 15378 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
site | +0.031 |
her | +0.030 |
office | +0.029 |
ia | +0.027 |
wasteful | +0.027 |
Neg logit contributions | |
mine | -0.023 |
berry | -0.022 |
wherever | -0.022 |
mattered | -0.021 |
Benny | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
site | +0.331 |
her | +0.326 |
office | +0.309 |
ia | +0.296 |
wasteful | +0.294 |
Neg logit contributions | |
mine | -0.226 |
berry | -0.221 |
wherever | -0.220 |
Will | -0.220 |
Benny | -0.220 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
site | +0.071 |
ia | +0.068 |
her | +0.064 |
wasteful | +0.062 |
yourselves | +0.060 |
Neg logit contributions | |
Will | -0.050 |
wherever | -0.047 |
stuffed | -0.046 |
mine | -0.046 |
Grac | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
site | +0.094 |
her | +0.092 |
office | +0.086 |
ia | +0.084 |
wasteful | +0.083 |
Neg logit contributions | |
mine | -0.069 |
wherever | -0.069 |
Will | -0.069 |
Benny | -0.068 |
berry | -0.067 |
Token | you |
Token ID | 345 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
site | +0.111 |
her | +0.111 |
office | +0.104 |
ia | +0.099 |
wasteful | +0.099 |
Neg logit contributions | |
mine | -0.083 |
Benny | -0.082 |
Will | -0.082 |
wherever | -0.082 |
mattered | -0.080 |
Token | learn |
Token ID | 2193 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
her | +0.015 |
site | +0.015 |
office | +0.014 |
wasteful | +0.013 |
ia | +0.013 |
Neg logit contributions | |
berry | -0.014 |
mine | -0.014 |
Benny | -0.014 |
superstar | -0.014 |
wherever | -0.014 |
Token | at |
Token ID | 379 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
site | +0.013 |
her | +0.013 |
office | +0.012 |
ia | +0.011 |
wasteful | +0.011 |
Neg logit contributions | |
mine | -0.014 |
wherever | -0.014 |
Benny | -0.014 |
berry | -0.014 |
Will | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
mine | +0.050 |
wherever | +0.049 |
Benny | +0.049 |
Will | +0.049 |
berry | +0.049 |
Neg logit contributions | |
site | -0.063 |
her | -0.062 |
office | -0.058 |
ia | -0.056 |
wasteful | -0.056 |
Token | post |
Token ID | 1281 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
site | +0.018 |
her | +0.018 |
office | +0.016 |
ia | +0.016 |
wasteful | +0.016 |
Neg logit contributions | |
wherever | -0.019 |
mine | -0.019 |
berry | -0.019 |
Will | -0.019 |
Benny | -0.019 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
her | +0.265 |
site | +0.261 |
ia | +0.228 |
wasteful | +0.228 |
office | +0.209 |
Neg logit contributions | |
mine | -0.550 |
berry | -0.546 |
wherever | -0.544 |
Will | -0.532 |
Benny | -0.528 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
site | +0.935 |
her | +0.921 |
ia | +0.857 |
office | +0.836 |
wasteful | +0.835 |
Neg logit contributions | |
mine | -0.880 |
wherever | -0.866 |
berry | -0.849 |
Will | -0.847 |
Benny | -0.842 |
Token |
|
Token ID | 198 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
mine | +0.006 |
berry | +0.006 |
wherever | +0.006 |
mattered | +0.006 |
Benny | +0.006 |
Neg logit contributions | |
site | -0.008 |
her | -0.008 |
office | -0.008 |
ia | -0.008 |
wasteful | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
Will | +0.020 |
mine | +0.019 |
wherever | +0.019 |
Benny | +0.019 |
berry | +0.018 |
Neg logit contributions | |
site | -0.033 |
her | -0.033 |
wasteful | -0.031 |
office | -0.031 |
ia | -0.029 |
Token | Jonathan |
Token ID | 30365 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Will | +0.024 |
mine | +0.024 |
wherever | +0.023 |
berry | +0.023 |
Benny | +0.023 |
Neg logit contributions | |
site | -0.029 |
her | -0.029 |
wasteful | -0.027 |
office | -0.027 |
ia | -0.026 |
Token | thought |
Token ID | 1807 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
mine | +0.014 |
berry | +0.013 |
Will | +0.013 |
Benny | +0.013 |
wherever | +0.013 |
Neg logit contributions | |
site | -0.020 |
her | -0.020 |
office | -0.019 |
ia | -0.018 |
wasteful | -0.018 |
Token | man |
Token ID | 582 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
mine | +0.027 |
wherever | +0.027 |
Will | +0.026 |
mattered | +0.026 |
ease | +0.026 |
Neg logit contributions | |
site | -0.029 |
her | -0.028 |
office | -0.027 |
ia | -0.026 |
wasteful | -0.025 |
Token | who |
Token ID | 508 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
site | +0.300 |
her | +0.300 |
office | +0.290 |
ia | +0.262 |
wasteful | +0.254 |
Neg logit contributions | |
ease | -0.276 |
mine | -0.275 |
Grac | -0.269 |
superstar | -0.268 |
Benny | -0.268 |
Token | worked |
Token ID | 3111 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
her | +0.019 |
site | +0.019 |
office | +0.018 |
wasteful | +0.017 |
ia | +0.017 |
Neg logit contributions | |
berry | -0.011 |
mine | -0.011 |
wherever | -0.011 |
Will | -0.011 |
Benny | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
site | +0.139 |
her | +0.134 |
office | +0.130 |
ia | +0.127 |
wasteful | +0.121 |
Neg logit contributions | |
wherever | -0.113 |
Benny | -0.110 |
mattered | -0.108 |
mine | -0.108 |
Will | -0.106 |
Token | an |
Token ID | 281 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
wherever | +0.021 |
Benny | +0.021 |
Will | +0.021 |
mine | +0.021 |
ease | +0.020 |
Neg logit contributions | |
site | -0.032 |
her | -0.032 |
ia | -0.030 |
office | -0.029 |
wasteful | -0.029 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
berry | +0.070 |
mine | +0.070 |
Benny | +0.070 |
ease | +0.070 |
wherever | +0.069 |
Neg logit contributions | |
her | -0.060 |
site | -0.059 |
ia | -0.055 |
ups | -0.052 |
fighters | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
site | +1.066 |
her | +1.053 |
ia | +1.005 |
wasteful | +0.998 |
office | +0.957 |
Neg logit contributions | |
wherever | -0.744 |
mine | -0.739 |
mattered | -0.699 |
Will | -0.685 |
Benny | -0.682 |
Token | Everyday |
Token ID | 48154 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
mine | +0.002 |
Will | +0.002 |
Benny | +0.002 |
berry | +0.002 |
wherever | +0.002 |
Neg logit contributions | |
site | -0.003 |
her | -0.003 |
office | -0.003 |
ia | -0.002 |
wasteful | -0.002 |
Token | he |
Token ID | 339 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
mine | +0.167 |
ease | +0.163 |
Grac | +0.162 |
superstar | +0.158 |
berry | +0.156 |
Neg logit contributions | |
site | -0.148 |
office | -0.140 |
her | -0.132 |
men | -0.128 |
ia | -0.126 |
Token | would |
Token ID | 561 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
mine | +0.061 |
berry | +0.059 |
wherever | +0.059 |
Benny | +0.059 |
Will | +0.057 |
Neg logit contributions | |
site | -0.117 |
her | -0.116 |
office | -0.111 |
wasteful | -0.105 |
ia | -0.105 |
Token | come |
Token ID | 1282 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
mine | +0.154 |
berry | +0.153 |
Benny | +0.152 |
wherever | +0.151 |
Will | +0.150 |
Neg logit contributions | |
site | -0.204 |
her | -0.201 |
office | -0.193 |
ia | -0.178 |
wasteful | -0.178 |
Token | Once |
Token ID | 7454 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
site | +0.142 |
her | +0.140 |
office | +0.126 |
ia | +0.125 |
men | +0.104 |
Neg logit contributions | |
superstar | -0.197 |
stuffed | -0.194 |
mine | -0.193 |
mattered | -0.191 |
Grac | -0.186 |
Token | , |
Token ID | 11 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
mine | +0.261 |
berry | +0.256 |
Will | +0.253 |
superstar | +0.252 |
wherever | +0.251 |
Neg logit contributions | |
site | -0.404 |
her | -0.399 |
office | -0.378 |
ia | -0.373 |
wasteful | -0.357 |
Token | there |
Token ID | 612 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
site | +0.028 |
her | +0.028 |
office | +0.026 |
ia | +0.026 |
wasteful | +0.025 |
Neg logit contributions | |
mine | -0.026 |
berry | -0.026 |
wherever | -0.025 |
Will | -0.025 |
superstar | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
site | +0.012 |
her | +0.012 |
office | +0.011 |
ia | +0.011 |
wasteful | +0.010 |
Neg logit contributions | |
superstar | -0.014 |
mine | -0.013 |
Grac | -0.013 |
wherever | -0.013 |
berry | -0.013 |
Token | an |
Token ID | 281 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
her | +0.054 |
site | +0.052 |
office | +0.049 |
ia | +0.047 |
wasteful | +0.044 |
Neg logit contributions | |
mine | -0.067 |
wherever | -0.065 |
superstar | -0.065 |
berry | -0.065 |
mattered | -0.065 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
berry | +0.072 |
Benny | +0.072 |
mine | +0.071 |
Will | +0.070 |
wherever | +0.067 |
Neg logit contributions | |
site | -0.066 |
her | -0.063 |
ups | -0.058 |
wasteful | -0.057 |
office | -0.056 |
Token | full |
Token ID | 1336 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
site | +1.184 |
her | +1.174 |
wasteful | +1.127 |
ia | +1.107 |
office | +1.072 |
Neg logit contributions | |
mine | -0.623 |
wherever | -0.613 |
berry | -0.585 |
Will | -0.581 |
Benny | -0.579 |
Token | of |
Token ID | 286 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
site | +0.010 |
her | +0.010 |
wasteful | +0.009 |
ia | +0.009 |
yourselves | +0.009 |
Neg logit contributions | |
berry | -0.004 |
mine | -0.004 |
wherever | -0.004 |
Will | -0.004 |
Benny | -0.004 |
Token | staff |
Token ID | 3085 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
Will | +0.042 |
wherever | +0.042 |
stuffed | +0.041 |
Benny | +0.040 |
ease | +0.040 |
Neg logit contributions | |
her | -0.042 |
site | -0.042 |
ia | -0.040 |
wasteful | -0.036 |
office | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
mine | +0.004 |
wherever | +0.003 |
berry | +0.003 |
Will | +0.003 |
Benny | +0.003 |
Neg logit contributions | |
site | -0.004 |
her | -0.004 |
ia | -0.004 |
wasteful | -0.004 |
office | -0.004 |
Token | The |
Token ID | 383 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
mine | +0.001 |
berry | +0.001 |
wherever | +0.001 |
Benny | +0.001 |
Will | +0.001 |
Neg logit contributions | |
site | -0.002 |
her | -0.002 |
office | -0.002 |
ia | -0.002 |
wasteful | -0.002 |
Token | went |
Token ID | 1816 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
site | +0.124 |
her | +0.123 |
office | +0.116 |
ia | +0.112 |
wasteful | +0.109 |
Neg logit contributions | |
mine | -0.093 |
wherever | -0.091 |
berry | -0.091 |
Benny | -0.090 |
Will | -0.090 |
Token | to |
Token ID | 284 |
Feature activation | -6.34e-02 |
Pos logit contributions | |
site | +0.253 |
her | +0.250 |
office | +0.237 |
ia | +0.228 |
wasteful | +0.226 |
Neg logit contributions | |
mine | -0.170 |
wherever | -0.167 |
Benny | -0.166 |
berry | -0.166 |
Will | -0.165 |
Token | the |
Token ID | 262 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
mine | +0.004 |
berry | +0.004 |
mattered | +0.004 |
superstar | +0.004 |
wherever | +0.004 |
Neg logit contributions | |
site | -0.005 |
her | -0.005 |
office | -0.005 |
ia | -0.004 |
wasteful | -0.004 |
Token | veterinarian |
Token ID | 41404 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
site | +0.019 |
her | +0.019 |
ia | +0.017 |
wasteful | +0.017 |
office | +0.017 |
Neg logit contributions | |
Benny | -0.018 |
wherever | -0.018 |
berry | -0.018 |
Will | -0.018 |
stuffed | -0.018 |
Token | 's |
Token ID | 338 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
site | +0.027 |
her | +0.027 |
office | +0.025 |
ia | +0.024 |
wasteful | +0.023 |
Neg logit contributions | |
mine | -0.023 |
berry | -0.022 |
Benny | -0.022 |
Will | -0.022 |
mattered | -0.022 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
wherever | +0.065 |
berry | +0.063 |
stuffed | +0.062 |
Benny | +0.062 |
Will | +0.062 |
Neg logit contributions | |
her | -0.046 |
site | -0.045 |
wasteful | -0.041 |
ia | -0.041 |
yourselves | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
site | +1.031 |
her | +1.014 |
office | +0.945 |
ia | +0.929 |
wasteful | +0.927 |
Neg logit contributions | |
mine | -0.798 |
wherever | -0.786 |
berry | -0.771 |
Benny | -0.769 |
Will | -0.766 |
Token | When |
Token ID | 1649 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
mine | +0.002 |
berry | +0.002 |
mattered | +0.002 |
wherever | +0.002 |
Benny | +0.002 |
Neg logit contributions | |
site | -0.003 |
her | -0.003 |
office | -0.002 |
ia | -0.002 |
wasteful | -0.002 |
Token | he |
Token ID | 339 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
site | +0.355 |
her | +0.347 |
office | +0.334 |
ia | +0.316 |
wasteful | +0.314 |
Neg logit contributions | |
mine | -0.236 |
berry | -0.230 |
wherever | -0.226 |
Benny | -0.225 |
Will | -0.224 |
Token | arrived |
Token ID | 5284 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
mine | +0.070 |
wherever | +0.069 |
berry | +0.068 |
Benny | +0.068 |
Will | +0.068 |
Neg logit contributions | |
site | -0.107 |
her | -0.106 |
office | -0.100 |
ia | -0.096 |
wasteful | -0.095 |
Token | , |
Token ID | 11 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
mine | +0.031 |
wherever | +0.030 |
Benny | +0.030 |
berry | +0.030 |
Will | +0.030 |
Neg logit contributions | |
site | -0.044 |
her | -0.044 |
office | -0.041 |
ia | -0.039 |
wasteful | -0.039 |
Token | learn |
Token ID | 2193 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
mine | +0.005 |
Benny | +0.004 |
wherever | +0.004 |
Will | +0.004 |
berry | +0.004 |
Neg logit contributions | |
site | -0.006 |
her | -0.006 |
office | -0.006 |
ia | -0.005 |
wasteful | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
site | +0.013 |
her | +0.013 |
office | +0.012 |
ia | +0.012 |
wasteful | +0.012 |
Neg logit contributions | |
mine | -0.012 |
wherever | -0.012 |
Benny | -0.012 |
berry | -0.012 |
Will | -0.012 |
Token | behave |
Token ID | 17438 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
mine | +0.005 |
wherever | +0.005 |
Benny | +0.005 |
Will | +0.005 |
berry | +0.005 |
Neg logit contributions | |
site | -0.007 |
her | -0.006 |
office | -0.006 |
ia | -0.006 |
wasteful | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
mine | +0.006 |
wherever | +0.006 |
Benny | +0.006 |
Will | +0.006 |
berry | +0.006 |
Neg logit contributions | |
site | -0.008 |
her | -0.008 |
office | -0.007 |
ia | -0.007 |
wasteful | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
mine | +0.026 |
wherever | +0.026 |
Benny | +0.026 |
Will | +0.025 |
berry | +0.025 |
Neg logit contributions | |
site | -0.028 |
her | -0.027 |
office | -0.025 |
ia | -0.024 |
wasteful | -0.024 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
her | +0.017 |
site | +0.017 |
ia | +0.016 |
office | +0.015 |
wasteful | +0.015 |
Neg logit contributions | |
wherever | -0.019 |
berry | -0.019 |
Benny | -0.019 |
mine | -0.019 |
Will | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
site | +1.060 |
her | +1.042 |
office | +0.966 |
ia | +0.965 |
wasteful | +0.950 |
Neg logit contributions | |
mine | -0.758 |
wherever | -0.757 |
Will | -0.726 |
berry | -0.722 |
Benny | -0.718 |
Token | You |
Token ID | 921 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
mine | +0.001 |
Will | +0.001 |
berry | +0.001 |
Benny | +0.001 |
wherever | +0.001 |
Neg logit contributions | |
site | -0.002 |
her | -0.001 |
office | -0.001 |
ia | -0.001 |
wasteful | -0.001 |
Token | have |
Token ID | 423 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
berry | +0.108 |
Nice | +0.106 |
superstar | +0.102 |
mine | +0.102 |
Benny | +0.100 |
Neg logit contributions | |
her | -0.143 |
site | -0.136 |
office | -0.135 |
wasteful | -0.131 |
ia | -0.122 |
Token | to |
Token ID | 284 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
mine | +0.132 |
berry | +0.129 |
Benny | +0.128 |
wherever | +0.127 |
Will | +0.127 |
Neg logit contributions | |
site | -0.199 |
her | -0.197 |
office | -0.187 |
ia | -0.178 |
wasteful | -0.178 |
Token | respect |
Token ID | 2461 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
mine | +0.004 |
wherever | +0.004 |
Benny | +0.004 |
ease | +0.004 |
Will | +0.004 |
Neg logit contributions | |
site | -0.005 |
her | -0.005 |
office | -0.005 |
wasteful | -0.005 |
ia | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
mine | +0.021 |
Benny | +0.020 |
Will | +0.020 |
wherever | +0.020 |
berry | +0.020 |
Neg logit contributions | |
site | -0.034 |
her | -0.032 |
office | -0.032 |
wasteful | -0.031 |
ia | -0.030 |
Token | At |
Token ID | 2953 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
mine | +0.029 |
Benny | +0.029 |
wherever | +0.028 |
Will | +0.028 |
berry | +0.028 |
Neg logit contributions | |
site | -0.026 |
her | -0.024 |
office | -0.024 |
wasteful | -0.023 |
ia | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
her | +0.216 |
site | +0.214 |
wasteful | +0.199 |
office | +0.196 |
ia | +0.193 |
Neg logit contributions | |
wherever | -0.157 |
Benny | -0.152 |
mine | -0.150 |
ease | -0.149 |
Will | -0.145 |
Token | doctor |
Token ID | 6253 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
site | +0.018 |
her | +0.017 |
wasteful | +0.016 |
ia | +0.016 |
office | +0.015 |
Neg logit contributions | |
wherever | -0.018 |
berry | -0.018 |
Benny | -0.018 |
Will | -0.018 |
mine | -0.018 |
Token | 's |
Token ID | 338 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
site | +0.341 |
her | +0.337 |
office | +0.318 |
ia | +0.304 |
wasteful | +0.301 |
Neg logit contributions | |
mine | -0.260 |
berry | -0.254 |
wherever | -0.254 |
Benny | -0.253 |
Will | -0.253 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
Will | +0.063 |
wherever | +0.062 |
berry | +0.062 |
stuffed | +0.060 |
g | +0.060 |
Neg logit contributions | |
her | -0.048 |
site | -0.047 |
wasteful | -0.043 |
ia | -0.042 |
yourselves | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
site | +1.110 |
her | +1.101 |
wasteful | +1.031 |
office | +1.013 |
ia | +1.011 |
Neg logit contributions | |
mine | -0.698 |
wherever | -0.685 |
mattered | -0.669 |
Benny | -0.666 |
Will | -0.666 |
Token | the |
Token ID | 262 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
site | +0.032 |
her | +0.031 |
office | +0.030 |
ia | +0.028 |
wasteful | +0.028 |
Neg logit contributions | |
mine | -0.023 |
berry | -0.023 |
wherever | -0.022 |
mattered | -0.022 |
superstar | -0.022 |
Token | doctor |
Token ID | 6253 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
site | +0.018 |
her | +0.017 |
ia | +0.016 |
wasteful | +0.015 |
yourselves | +0.015 |
Neg logit contributions | |
Will | -0.019 |
stuffed | -0.019 |
berry | -0.019 |
wherever | -0.019 |
Benny | -0.019 |
Token | had |
Token ID | 550 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
site | +0.339 |
her | +0.334 |
office | +0.316 |
ia | +0.302 |
wasteful | +0.299 |
Neg logit contributions | |
mine | -0.263 |
berry | -0.257 |
wherever | -0.256 |
Benny | -0.256 |
Will | -0.256 |
Token | a |
Token ID | 257 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
mine | +0.040 |
wherever | +0.039 |
Benny | +0.039 |
Will | +0.039 |
berry | +0.039 |
Neg logit contributions | |
site | -0.051 |
her | -0.050 |
office | -0.047 |
ia | -0.046 |
wasteful | -0.045 |
Token | ran |
Token ID | 4966 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
her | +0.407 |
site | +0.407 |
office | +0.384 |
ia | +0.367 |
wasteful | +0.358 |
Neg logit contributions | |
mine | -0.331 |
berry | -0.324 |
wherever | -0.322 |
Benny | -0.318 |
Will | -0.318 |
Token | back |
Token ID | 736 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
site | +0.185 |
her | +0.185 |
office | +0.173 |
ia | +0.165 |
wasteful | +0.161 |
Neg logit contributions | |
mine | -0.139 |
berry | -0.137 |
mattered | -0.135 |
Will | -0.134 |
superstar | -0.133 |
Token | out |
Token ID | 503 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
mine | +0.078 |
superstar | +0.075 |
berry | +0.075 |
mattered | +0.074 |
Will | +0.074 |
Neg logit contributions | |
site | -0.100 |
her | -0.098 |
office | -0.095 |
ia | -0.088 |
wasteful | -0.085 |
Token | of |
Token ID | 286 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
site | +0.061 |
her | +0.061 |
office | +0.057 |
ia | +0.055 |
ups | +0.052 |
Neg logit contributions | |
mine | -0.056 |
mattered | -0.054 |
superstar | -0.054 |
berry | -0.054 |
Benny | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
mine | +0.042 |
superstar | +0.042 |
mattered | +0.041 |
berry | +0.040 |
're | +0.040 |
Neg logit contributions | |
site | -0.044 |
her | -0.043 |
office | -0.042 |
ia | -0.038 |
wasteful | -0.037 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
her | +0.016 |
site | +0.016 |
ia | +0.015 |
wasteful | +0.015 |
office | +0.014 |
Neg logit contributions | |
berry | -0.021 |
Benny | -0.020 |
wherever | -0.020 |
Will | -0.020 |
Grac | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
site | +1.032 |
her | +1.020 |
office | +0.948 |
wasteful | +0.943 |
ia | +0.935 |
Neg logit contributions | |
mine | -0.799 |
wherever | -0.781 |
berry | -0.769 |
Benny | -0.760 |
Will | -0.758 |
Token | She |
Token ID | 1375 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
mine | +0.001 |
mattered | +0.001 |
superstar | +0.001 |
stuffed | +0.001 |
wherever | +0.001 |
Neg logit contributions | |
her | -0.001 |
site | -0.001 |
office | -0.001 |
ia | -0.001 |
wasteful | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
site | +0.102 |
her | +0.102 |
office | +0.096 |
ia | +0.092 |
wasteful | +0.089 |
Neg logit contributions | |
mine | -0.076 |
wherever | -0.075 |
berry | -0.074 |
Benny | -0.074 |
Will | -0.072 |
Token | so |
Token ID | 523 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
site | +0.069 |
her | +0.067 |
office | +0.063 |
ia | +0.061 |
wasteful | +0.060 |
Neg logit contributions | |
mine | -0.053 |
Will | -0.052 |
wherever | -0.052 |
Benny | -0.051 |
berry | -0.051 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
site | +0.132 |
her | +0.131 |
office | +0.123 |
ia | +0.118 |
wasteful | +0.117 |
Neg logit contributions | |
mine | -0.097 |
berry | -0.095 |
wherever | -0.095 |
Benny | -0.095 |
Will | -0.095 |
Token | went |
Token ID | 1816 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
mine | +0.051 |
Will | +0.051 |
Benny | +0.050 |
berry | +0.050 |
wherever | +0.049 |
Neg logit contributions | |
site | -0.082 |
her | -0.080 |
office | -0.075 |
wasteful | -0.073 |
ia | -0.073 |
Token | to |
Token ID | 284 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
site | +0.241 |
her | +0.239 |
office | +0.232 |
ia | +0.213 |
wasteful | +0.210 |
Neg logit contributions | |
mine | -0.182 |
berry | -0.176 |
mattered | -0.175 |
Will | -0.173 |
superstar | -0.172 |
Token | the |
Token ID | 262 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
mine | +0.006 |
mattered | +0.005 |
berry | +0.005 |
superstar | +0.005 |
wherever | +0.005 |
Neg logit contributions | |
site | -0.006 |
her | -0.006 |
office | -0.006 |
ia | -0.005 |
wasteful | -0.005 |
Token | doctor |
Token ID | 6253 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
site | +0.018 |
her | +0.017 |
ia | +0.017 |
wasteful | +0.016 |
ups | +0.015 |
Neg logit contributions | |
Benny | -0.018 |
wherever | -0.018 |
berry | -0.018 |
Will | -0.018 |
stuffed | -0.017 |
Token | 's |
Token ID | 338 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
site | +0.337 |
her | +0.332 |
office | +0.314 |
ia | +0.299 |
wasteful | +0.297 |
Neg logit contributions | |
mine | -0.265 |
berry | -0.259 |
wherever | -0.259 |
Benny | -0.259 |
Will | -0.258 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
berry | +0.081 |
wherever | +0.079 |
Will | +0.079 |
stuffed | +0.079 |
Benny | +0.076 |
Neg logit contributions | |
her | -0.030 |
site | -0.029 |
wasteful | -0.027 |
ia | -0.026 |
yourselves | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
site | +1.069 |
her | +1.040 |
wasteful | +0.981 |
ia | +0.980 |
office | +0.962 |
Neg logit contributions | |
mine | -0.762 |
wherever | -0.747 |
berry | -0.727 |
Will | -0.721 |
Benny | -0.719 |
Token | She |
Token ID | 1375 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
mine | +0.001 |
mattered | +0.001 |
wherever | +0.001 |
berry | +0.001 |
superstar | +0.001 |
Neg logit contributions | |
site | -0.001 |
her | -0.001 |
office | -0.001 |
ia | -0.001 |
wasteful | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
site | +0.105 |
her | +0.103 |
office | +0.098 |
ia | +0.094 |
wasteful | +0.094 |
Neg logit contributions | |
mine | -0.073 |
Will | -0.072 |
Benny | -0.071 |
berry | -0.071 |
wherever | -0.071 |
Token | very |
Token ID | 845 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
site | +0.071 |
ia | +0.067 |
her | +0.065 |
wasteful | +0.061 |
ups | +0.060 |
Neg logit contributions | |
Will | -0.054 |
stuffed | -0.050 |
Grac | -0.049 |
Benny | -0.048 |
wherever | -0.048 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
site | +0.176 |
ia | +0.157 |
her | +0.155 |
office | +0.147 |
yourselves | +0.144 |
Neg logit contributions | |
Will | -0.128 |
g | -0.127 |
stuffed | -0.124 |
Grac | -0.122 |
mattered | -0.120 |
Token | He |
Token ID | 679 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Benny | +0.002 |
Will | +0.002 |
mine | +0.002 |
wherever | +0.002 |
berry | +0.002 |
Neg logit contributions | |
site | -0.003 |
her | -0.003 |
office | -0.003 |
wasteful | -0.003 |
ia | -0.003 |
Token | took |
Token ID | 1718 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
site | +0.124 |
office | +0.117 |
her | +0.116 |
ia | +0.104 |
wasteful | +0.104 |
Neg logit contributions | |
Will | -0.073 |
Benny | -0.070 |
stuffed | -0.068 |
g | -0.067 |
mine | -0.066 |
Token | them |
Token ID | 606 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
site | +0.046 |
her | +0.045 |
office | +0.043 |
ia | +0.041 |
wasteful | +0.040 |
Neg logit contributions | |
mine | -0.032 |
Benny | -0.031 |
Will | -0.031 |
wherever | -0.031 |
berry | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
mine | +0.009 |
berry | +0.009 |
Will | +0.009 |
Benny | +0.009 |
wherever | +0.009 |
Neg logit contributions | |
site | -0.013 |
her | -0.013 |
office | -0.012 |
ia | -0.012 |
wasteful | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
Benny | +0.004 |
Will | +0.004 |
wherever | +0.004 |
mine | +0.004 |
ease | +0.004 |
Neg logit contributions | |
site | -0.006 |
her | -0.006 |
office | -0.005 |
wasteful | -0.005 |
ia | -0.005 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
her | +0.017 |
site | +0.017 |
ia | +0.016 |
wasteful | +0.015 |
ups | +0.014 |
Neg logit contributions | |
wherever | -0.020 |
berry | -0.020 |
Benny | -0.020 |
stuffed | -0.020 |
Will | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
her | +1.121 |
wasteful | +1.108 |
site | +1.098 |
ia | +1.071 |
yourselves | +1.035 |
Neg logit contributions | |
mine | -0.653 |
wherever | -0.643 |
berry | -0.572 |
Benny | -0.560 |
whenever | -0.557 |
Token | the |
Token ID | 262 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Benny | +0.033 |
wherever | +0.032 |
Will | +0.032 |
mine | +0.032 |
ease | +0.031 |
Neg logit contributions | |
her | -0.052 |
site | -0.052 |
ia | -0.049 |
office | -0.048 |
wasteful | -0.047 |
Token | boss |
Token ID | 6478 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ia | +0.009 |
her | +0.009 |
site | +0.008 |
ooked | +0.008 |
wasteful | +0.007 |
Neg logit contributions | |
wherever | -0.027 |
stuffed | -0.026 |
berry | -0.025 |
Will | -0.025 |
Benny | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
mine | +0.078 |
berry | +0.075 |
Will | +0.074 |
wherever | +0.073 |
Benny | +0.073 |
Neg logit contributions | |
site | -0.128 |
her | -0.126 |
office | -0.119 |
wasteful | -0.115 |
ia | -0.115 |
Token | The |
Token ID | 383 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
Will | +0.001 |
Benny | +0.001 |
wherever | +0.001 |
mine | +0.001 |
Grac | +0.001 |
Neg logit contributions | |
site | -0.001 |
her | -0.001 |
office | -0.001 |
wasteful | -0.001 |
ia | -0.001 |
Token | were |
Token ID | 547 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
site | +0.066 |
her | +0.066 |
office | +0.063 |
ia | +0.060 |
wasteful | +0.060 |
Neg logit contributions | |
mine | -0.032 |
wherever | -0.032 |
Benny | -0.031 |
berry | -0.031 |
Will | -0.031 |
Token | at |
Token ID | 379 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
Will | +0.190 |
mine | +0.190 |
Benny | +0.189 |
berry | +0.188 |
wherever | +0.188 |
Neg logit contributions | |
site | -0.428 |
her | -0.401 |
ia | -0.392 |
wasteful | -0.383 |
ups | -0.364 |
Token | the |
Token ID | 262 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
mine | +0.053 |
mattered | +0.051 |
berry | +0.051 |
wherever | +0.051 |
superstar | +0.051 |
Neg logit contributions | |
site | -0.062 |
her | -0.061 |
office | -0.059 |
ia | -0.054 |
wasteful | -0.054 |
Token | doctor |
Token ID | 6253 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
site | +0.019 |
her | +0.018 |
ia | +0.018 |
wasteful | +0.018 |
ups | +0.016 |
Neg logit contributions | |
berry | -0.018 |
mine | -0.018 |
wherever | -0.018 |
Will | -0.018 |
Benny | -0.018 |
Token | 's |
Token ID | 338 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
site | +0.333 |
her | +0.328 |
office | +0.310 |
ia | +0.296 |
wasteful | +0.293 |
Neg logit contributions | |
mine | -0.268 |
berry | -0.263 |
wherever | -0.262 |
Benny | -0.262 |
Will | -0.261 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
berry | +0.068 |
wherever | +0.067 |
stuffed | +0.066 |
Will | +0.066 |
g | +0.065 |
Neg logit contributions | |
wasteful | -0.041 |
her | -0.041 |
site | -0.039 |
ia | -0.039 |
yourselves | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
site | +1.043 |
her | +1.024 |
wasteful | +0.952 |
ia | +0.950 |
office | +0.949 |
Neg logit contributions | |
mine | -0.784 |
wherever | -0.767 |
berry | -0.755 |
Will | -0.744 |
Benny | -0.743 |
Token | While |
Token ID | 2893 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
mine | +0.001 |
wherever | +0.001 |
berry | +0.001 |
Benny | +0.001 |
mattered | +0.001 |
Neg logit contributions | |
site | -0.002 |
her | -0.002 |
office | -0.002 |
ia | -0.002 |
wasteful | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
site | +0.028 |
her | +0.028 |
office | +0.026 |
ia | +0.025 |
wasteful | +0.025 |
Neg logit contributions | |
mine | -0.022 |
berry | -0.021 |
wherever | -0.021 |
Benny | -0.021 |
Will | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
mine | +0.021 |
wherever | +0.021 |
Will | +0.021 |
berry | +0.021 |
Benny | +0.021 |
Neg logit contributions | |
her | -0.032 |
site | -0.032 |
office | -0.029 |
wasteful | -0.029 |
ia | -0.029 |
Token | waiting |
Token ID | 4953 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
her | +0.009 |
ia | +0.009 |
site | +0.009 |
wasteful | +0.008 |
cks | +0.007 |
Neg logit contributions | |
Will | -0.028 |
berry | -0.027 |
wherever | -0.027 |
mine | -0.027 |
stuffed | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
mine | +0.166 |
berry | +0.159 |
ease | +0.158 |
superstar | +0.156 |
Grac | +0.155 |
Neg logit contributions | |
site | -0.156 |
her | -0.151 |
office | -0.150 |
ia | -0.141 |
wasteful | -0.136 |
Token | He |
Token ID | 679 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Benny | +0.002 |
Will | +0.002 |
berry | +0.002 |
Grac | +0.002 |
mine | +0.002 |
Neg logit contributions | |
site | -0.003 |
her | -0.003 |
office | -0.003 |
wasteful | -0.003 |
ia | -0.003 |
Token | went |
Token ID | 1816 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
site | +0.113 |
her | +0.109 |
office | +0.105 |
ia | +0.100 |
wasteful | +0.100 |
Neg logit contributions | |
Will | -0.081 |
Benny | -0.081 |
mine | -0.080 |
berry | -0.078 |
mattered | -0.077 |
Token | to |
Token ID | 284 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
site | +0.275 |
her | +0.271 |
ia | +0.256 |
wasteful | +0.253 |
office | +0.252 |
Neg logit contributions | |
wherever | -0.148 |
Benny | -0.145 |
Will | -0.144 |
mine | -0.142 |
berry | -0.138 |
Token | the |
Token ID | 262 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
mine | +0.004 |
berry | +0.004 |
mattered | +0.004 |
wherever | +0.004 |
superstar | +0.004 |
Neg logit contributions | |
site | -0.005 |
her | -0.005 |
office | -0.005 |
ia | -0.005 |
wasteful | -0.005 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
her | +0.017 |
site | +0.017 |
ia | +0.016 |
wasteful | +0.015 |
office | +0.015 |
Neg logit contributions | |
Benny | -0.020 |
wherever | -0.020 |
berry | -0.020 |
stuffed | -0.019 |
Will | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
site | +1.089 |
her | +1.086 |
wasteful | +1.043 |
ia | +1.043 |
office | +0.983 |
Neg logit contributions | |
wherever | -0.709 |
mine | -0.707 |
Will | -0.659 |
Benny | -0.655 |
berry | -0.645 |
Token | looked |
Token ID | 3114 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
Will | +0.035 |
Benny | +0.035 |
mine | +0.034 |
wherever | +0.034 |
Grac | +0.033 |
Neg logit contributions | |
site | -0.045 |
her | -0.044 |
ia | -0.041 |
office | -0.041 |
wasteful | -0.040 |
Token | at |
Token ID | 379 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
mine | +0.007 |
berry | +0.006 |
Will | +0.006 |
Benny | +0.006 |
wherever | +0.006 |
Neg logit contributions | |
site | -0.006 |
her | -0.006 |
office | -0.006 |
wasteful | -0.005 |
ia | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
mine | +0.047 |
berry | +0.047 |
superstar | +0.046 |
mattered | +0.046 |
Will | +0.045 |
Neg logit contributions | |
her | -0.065 |
site | -0.065 |
office | -0.062 |
ia | -0.059 |
wasteful | -0.058 |
Token | computer |
Token ID | 3644 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
site | +0.017 |
her | +0.016 |
ia | +0.015 |
wasteful | +0.014 |
office | +0.014 |
Neg logit contributions | |
wherever | -0.021 |
stuffed | -0.021 |
mine | -0.021 |
Will | -0.020 |
berry | -0.020 |
Token | she |
Token ID | 673 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
mine | +0.121 |
berry | +0.120 |
superstar | +0.115 |
Benny | +0.114 |
Will | +0.114 |
Neg logit contributions | |
site | -0.180 |
her | -0.178 |
office | -0.173 |
ia | -0.161 |
wasteful | -0.159 |
Token | would |
Token ID | 561 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
berry | +0.061 |
mine | +0.058 |
wherever | +0.058 |
ease | +0.057 |
berries | +0.056 |
Neg logit contributions | |
her | -0.075 |
site | -0.070 |
office | -0.067 |
ia | -0.065 |
wasteful | -0.064 |
Token | miss |
Token ID | 2051 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
berry | +0.215 |
mine | +0.205 |
superstar | +0.203 |
Benny | +0.203 |
Will | +0.203 |
Neg logit contributions | |
site | -0.147 |
her | -0.146 |
office | -0.137 |
wasteful | -0.124 |
ia | -0.123 |
Token | her |
Token ID | 607 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
berry | +0.148 |
mine | +0.148 |
superstar | +0.145 |
oft | +0.137 |
mattered | +0.136 |
Neg logit contributions | |
site | -0.177 |
her | -0.175 |
office | -0.172 |
wasteful | -0.157 |
yourselves | -0.153 |
Token | old |
Token ID | 1468 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
mine | +0.179 |
berry | +0.167 |
Will | +0.164 |
ease | +0.162 |
superstar | +0.162 |
Neg logit contributions | |
office | -0.150 |
site | -0.147 |
her | -0.143 |
ia | -0.122 |
wasteful | -0.120 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
site | +0.404 |
her | +0.392 |
office | +0.383 |
ia | +0.333 |
wasteful | +0.331 |
Neg logit contributions | |
mine | -0.622 |
Will | -0.609 |
berry | -0.608 |
Benny | -0.607 |
wherever | -0.603 |
Token | . |
Token ID | 13 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
her | +0.921 |
site | +0.911 |
office | +0.896 |
ia | +0.779 |
ups | +0.776 |
Neg logit contributions | |
berry | -0.920 |
Will | -0.913 |
mine | -0.903 |
Benny | -0.902 |
Grac | -0.889 |
Token |
|
Token ID | 198 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
mine | +0.001 |
berry | +0.001 |
mattered | +0.001 |
superstar | +0.001 |
wherever | +0.001 |
Neg logit contributions | |
her | -0.002 |
site | -0.002 |
office | -0.002 |
ia | -0.002 |
wasteful | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
Benny | +0.019 |
mine | +0.019 |
Will | +0.019 |
wherever | +0.019 |
berry | +0.018 |
Neg logit contributions | |
site | -0.034 |
her | -0.033 |
office | -0.032 |
wasteful | -0.031 |
ia | -0.030 |
Token | L |
Token ID | 43 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
mine | +0.024 |
wherever | +0.023 |
Benny | +0.023 |
Will | +0.023 |
mattered | +0.023 |
Neg logit contributions | |
site | -0.028 |
office | -0.026 |
her | -0.025 |
wasteful | -0.025 |
men | -0.024 |
Token | ily |
Token ID | 813 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
site | +0.164 |
her | +0.145 |
office | +0.137 |
wasteful | +0.133 |
men | +0.132 |
Neg logit contributions | |
mine | -0.194 |
berry | -0.185 |
Benny | -0.180 |
mattered | -0.179 |
Will | -0.178 |
Token | to |
Token ID | 284 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
site | +0.069 |
her | +0.068 |
office | +0.064 |
ia | +0.062 |
wasteful | +0.061 |
Neg logit contributions | |
mine | -0.049 |
berry | -0.048 |
Benny | -0.047 |
Will | -0.047 |
wherever | -0.047 |
Token | each |
Token ID | 1123 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
mine | +0.004 |
berry | +0.004 |
mattered | +0.004 |
Benny | +0.004 |
wherever | +0.004 |
Neg logit contributions | |
site | -0.005 |
her | -0.005 |
office | -0.005 |
ia | -0.004 |
wasteful | -0.004 |
Token | person |
Token ID | 1048 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
mine | +0.048 |
Benny | +0.047 |
mattered | +0.047 |
Will | +0.047 |
berry | +0.047 |
Neg logit contributions | |
site | -0.055 |
her | -0.054 |
office | -0.052 |
ia | -0.048 |
wasteful | -0.047 |
Token | in |
Token ID | 287 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
her | +0.160 |
site | +0.159 |
office | +0.153 |
ia | +0.137 |
ups | +0.136 |
Neg logit contributions | |
mine | -0.161 |
superstar | -0.158 |
Benny | -0.157 |
berry | -0.156 |
Will | -0.155 |
Token | the |
Token ID | 262 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
mine | +0.026 |
berry | +0.026 |
superstar | +0.026 |
Benny | +0.025 |
mattered | +0.025 |
Neg logit contributions | |
site | -0.027 |
her | -0.026 |
office | -0.025 |
ia | -0.023 |
men | -0.022 |
Token | office |
Token ID | 2607 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
site | +0.017 |
her | +0.017 |
ia | +0.016 |
wasteful | +0.015 |
office | +0.015 |
Neg logit contributions | |
mine | -0.020 |
wherever | -0.020 |
berry | -0.019 |
Benny | -0.019 |
Will | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
site | +1.043 |
her | +1.043 |
wasteful | +0.987 |
ia | +0.974 |
office | +0.956 |
Neg logit contributions | |
mine | -0.769 |
wherever | -0.741 |
berry | -0.722 |
Will | -0.709 |
mattered | -0.707 |
Token | He |
Token ID | 679 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
mine | +0.001 |
berry | +0.001 |
wherever | +0.001 |
Benny | +0.001 |
Will | +0.001 |
Neg logit contributions | |
site | -0.002 |
her | -0.002 |
office | -0.002 |
ia | -0.002 |
wasteful | -0.002 |
Token | worked |
Token ID | 3111 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
site | +0.113 |
her | +0.112 |
office | +0.106 |
ia | +0.101 |
wasteful | +0.099 |
Neg logit contributions | |
mine | -0.083 |
wherever | -0.081 |
berry | -0.081 |
Benny | -0.080 |
Will | -0.079 |
Token | hard |
Token ID | 1327 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
site | +0.133 |
her | +0.128 |
office | +0.128 |
ia | +0.124 |
wasteful | +0.121 |
Neg logit contributions | |
wherever | -0.117 |
Benny | -0.113 |
mine | -0.111 |
Will | -0.110 |
ease | -0.110 |
Token | and |
Token ID | 290 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
site | +0.234 |
her | +0.231 |
office | +0.219 |
ia | +0.218 |
wasteful | +0.215 |
Neg logit contributions | |
wherever | -0.157 |
mine | -0.153 |
Will | -0.150 |
Benny | -0.149 |
mattered | -0.145 |
Token | peaceful |
Token ID | 12309 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
site | +0.127 |
her | +0.127 |
office | +0.119 |
ia | +0.115 |
wasteful | +0.113 |
Neg logit contributions | |
mine | -0.090 |
berry | -0.088 |
Will | -0.087 |
Benny | -0.087 |
wherever | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
mine | +0.070 |
berry | +0.068 |
mattered | +0.068 |
Benny | +0.067 |
Will | +0.067 |
Neg logit contributions | |
site | -0.072 |
her | -0.070 |
office | -0.066 |
ia | -0.062 |
wasteful | -0.060 |
Token | like |
Token ID | 588 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
her | +0.022 |
site | +0.022 |
office | +0.021 |
wasteful | +0.019 |
ia | +0.019 |
Neg logit contributions | |
mine | -0.023 |
berry | -0.022 |
Grac | -0.021 |
mattered | -0.020 |
superstar | -0.020 |
Token | nothing |
Token ID | 2147 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
mine | +0.233 |
berry | +0.218 |
superstar | +0.208 |
mattered | +0.205 |
Grac | +0.204 |
Neg logit contributions | |
site | -0.223 |
her | -0.216 |
office | -0.211 |
ia | -0.191 |
men | -0.190 |
Token | else |
Token ID | 2073 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
her | +0.010 |
site | +0.010 |
office | +0.009 |
ia | +0.009 |
wasteful | +0.008 |
Neg logit contributions | |
mine | -0.010 |
berry | -0.010 |
ease | -0.009 |
Will | -0.009 |
Benny | -0.009 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
her | +0.047 |
site | +0.046 |
office | +0.043 |
ia | +0.042 |
wasteful | +0.041 |
Neg logit contributions | |
mine | -0.052 |
berry | -0.049 |
superstar | -0.048 |
Grac | -0.048 |
ease | -0.048 |
Token | except |
Token ID | 2845 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
mine | +0.993 |
superstar | +0.974 |
Grac | +0.950 |
berry | +0.945 |
ease | +0.930 |
Neg logit contributions | |
her | -0.622 |
site | -0.617 |
office | -0.567 |
ia | -0.529 |
ups | -0.526 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
mine | +0.156 |
berry | +0.143 |
superstar | +0.139 |
oft | +0.137 |
tie | +0.136 |
Neg logit contributions | |
site | -0.121 |
office | -0.118 |
her | -0.112 |
wasteful | -0.101 |
mistake | -0.100 |
Token | present |
Token ID | 1944 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
her | +0.013 |
site | +0.013 |
office | +0.012 |
ia | +0.011 |
men | +0.011 |
Neg logit contributions | |
mine | -0.015 |
Will | -0.014 |
Benny | -0.014 |
mattered | -0.014 |
Grac | -0.014 |
Token | moment |
Token ID | 2589 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
mine | +0.229 |
berry | +0.224 |
Will | +0.223 |
Benny | +0.221 |
Grac | +0.219 |
Neg logit contributions | |
site | -0.281 |
her | -0.278 |
office | -0.264 |
ia | -0.251 |
wasteful | -0.234 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
mine | +0.219 |
berry | +0.210 |
superstar | +0.206 |
Grac | +0.204 |
ease | +0.202 |
Neg logit contributions | |
her | -0.231 |
site | -0.227 |
office | -0.209 |
ia | -0.205 |
ups | -0.193 |
Token | and |
Token ID | 290 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
mine | +0.164 |
ease | +0.157 |
Will | +0.156 |
berry | +0.155 |
Benny | +0.155 |
Neg logit contributions | |
site | -0.168 |
office | -0.162 |
her | -0.161 |
ia | -0.149 |
mistake | -0.142 |
Token | that |
Token ID | 326 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
mine | +0.041 |
berry | +0.041 |
Will | +0.038 |
superstar | +0.038 |
Benny | +0.037 |
Neg logit contributions | |
her | -0.050 |
site | -0.049 |
office | -0.048 |
wasteful | -0.045 |
ia | -0.045 |
Token | was |
Token ID | 373 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
office | +0.291 |
her | +0.283 |
site | +0.281 |
wasteful | +0.257 |
ia | +0.255 |
Neg logit contributions | |
mine | -0.265 |
berry | -0.255 |
superstar | -0.245 |
tie | -0.241 |
ease | -0.236 |
Token | all |
Token ID | 477 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
her | +0.057 |
site | +0.057 |
office | +0.053 |
wasteful | +0.051 |
ia | +0.050 |
Neg logit contributions | |
mine | -0.053 |
berry | -0.052 |
Will | -0.051 |
Benny | -0.051 |
wherever | -0.050 |
Token | that |
Token ID | 326 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
mine | +0.460 |
berry | +0.452 |
Will | +0.440 |
superstar | +0.428 |
Benny | +0.422 |
Neg logit contributions | |
her | -0.382 |
office | -0.362 |
site | -0.355 |
wasteful | -0.337 |
ups | -0.300 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
her | +0.281 |
office | +0.276 |
site | +0.275 |
wasteful | +0.253 |
ia | +0.251 |
Neg logit contributions | |
mine | -0.262 |
berry | -0.261 |
superstar | -0.251 |
tie | -0.243 |
Will | -0.236 |
Token | . |
Token ID | 13 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
mine | +0.962 |
superstar | +0.930 |
berry | +0.917 |
Will | +0.912 |
ease | +0.902 |
Neg logit contributions | |
her | -0.685 |
site | -0.643 |
office | -0.639 |
ups | -0.578 |
yourselves | -0.574 |
Token | And |
Token ID | 843 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
stuffed | +0.006 |
mine | +0.006 |
mattered | +0.006 |
superstar | +0.006 |
berry | +0.006 |
Neg logit contributions | |
her | -0.007 |
office | -0.006 |
site | -0.006 |
ia | -0.006 |
wasteful | -0.005 |
Token | so |
Token ID | 523 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
mine | +0.002 |
berry | +0.002 |
ease | +0.001 |
superstar | +0.001 |
stuffed | +0.001 |
Neg logit contributions | |
her | -0.002 |
site | -0.002 |
office | -0.002 |
ia | -0.002 |
wasteful | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
site | +0.122 |
her | +0.121 |
office | +0.116 |
ia | +0.111 |
wasteful | +0.108 |
Neg logit contributions | |
mine | -0.096 |
berry | -0.094 |
Will | -0.092 |
wherever | -0.092 |
Benny | -0.092 |
Token | smiled |
Token ID | 13541 |
Feature activation | -6.12e+00 |
Pos logit contributions | |
wherever | +0.067 |
berry | +0.066 |
mine | +0.066 |
ease | +0.066 |
Nice | +0.066 |
Neg logit contributions | |
her | -0.071 |
office | -0.067 |
ia | -0.067 |
site | -0.066 |
wasteful | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
site | +0.273 |
her | +0.271 |
office | +0.255 |
wasteful | +0.245 |
ia | +0.245 |
Neg logit contributions | |
Benny | -0.173 |
Will | -0.171 |
berry | -0.170 |
wherever | -0.169 |
mine | -0.169 |
Token | that |
Token ID | 326 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
site | +0.023 |
her | +0.021 |
office | +0.021 |
wasteful | +0.020 |
men | +0.019 |
Neg logit contributions | |
mine | -0.023 |
berry | -0.022 |
superstar | -0.021 |
Grac | -0.021 |
berries | -0.020 |
Token | 's |
Token ID | 338 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
her | +0.262 |
office | +0.260 |
site | +0.257 |
mistake | +0.232 |
wasteful | +0.229 |
Neg logit contributions | |
mine | -0.291 |
berry | -0.282 |
Grac | -0.269 |
superstar | -0.268 |
Nice | -0.268 |
Token | all |
Token ID | 477 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
wherever | +0.060 |
mine | +0.060 |
Benny | +0.060 |
Will | +0.059 |
berry | +0.059 |
Neg logit contributions | |
site | -0.062 |
her | -0.060 |
office | -0.056 |
ia | -0.054 |
wasteful | -0.053 |
Token | that |
Token ID | 326 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
berry | +0.429 |
mine | +0.416 |
berries | +0.402 |
Grac | +0.396 |
ease | +0.389 |
Neg logit contributions | |
office | -0.393 |
her | -0.392 |
site | -0.383 |
wasteful | -0.368 |
ia | -0.332 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
site | +0.297 |
office | +0.282 |
her | +0.280 |
wasteful | +0.269 |
mistake | +0.260 |
Neg logit contributions | |
berry | -0.265 |
mine | -0.262 |
superstar | -0.245 |
tie | -0.239 |
berries | -0.235 |
Token | . |
Token ID | 13 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
mine | +0.956 |
berry | +0.911 |
superstar | +0.880 |
Grac | +0.871 |
berries | +0.857 |
Neg logit contributions | |
her | -0.702 |
site | -0.676 |
office | -0.661 |
ups | -0.610 |
yourselves | -0.574 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
mine | +0.007 |
superstar | +0.007 |
stuffed | +0.007 |
berry | +0.007 |
mattered | +0.007 |
Neg logit contributions | |
her | -0.006 |
site | -0.006 |
office | -0.006 |
ia | -0.005 |
wasteful | -0.005 |
Token | Once |
Token ID | 7454 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
site | +0.169 |
her | +0.168 |
office | +0.153 |
ia | +0.150 |
men | +0.132 |
Neg logit contributions | |
mine | -0.160 |
superstar | -0.160 |
mattered | -0.157 |
berry | -0.154 |
Grac | -0.152 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
mine | +0.261 |
berry | +0.254 |
Will | +0.252 |
wherever | +0.250 |
Benny | +0.250 |
Neg logit contributions | |
site | -0.416 |
her | -0.412 |
office | -0.391 |
ia | -0.381 |
wasteful | -0.370 |
Token | a |
Token ID | 257 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
mine | +0.110 |
berry | +0.109 |
Grac | +0.107 |
superstar | +0.106 |
mattered | +0.105 |
Neg logit contributions | |
her | -0.078 |
site | -0.074 |
office | -0.069 |
ia | -0.067 |
wasteful | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
site | +0.192 |
her | +0.183 |
office | +0.181 |
mistake | +0.169 |
wasteful | +0.166 |
Neg logit contributions | |
mine | -0.220 |
berry | -0.212 |
superstar | -0.211 |
Will | -0.205 |
Nice | -0.201 |
Token | mall |
Token ID | 17374 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
site | +0.013 |
her | +0.013 |
office | +0.012 |
wasteful | +0.012 |
ia | +0.011 |
Neg logit contributions | |
mine | -0.014 |
Will | -0.014 |
Grac | -0.014 |
superstar | -0.013 |
berry | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
mine | +0.037 |
Will | +0.036 |
berry | +0.036 |
Benny | +0.036 |
wherever | +0.036 |
Neg logit contributions | |
site | -0.045 |
her | -0.044 |
office | -0.042 |
ia | -0.040 |
wasteful | -0.039 |
Token | All |
Token ID | 1439 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
mine | +0.006 |
berry | +0.006 |
superstar | +0.006 |
stuffed | +0.006 |
mattered | +0.006 |
Neg logit contributions | |
her | -0.008 |
site | -0.008 |
office | -0.007 |
ia | -0.007 |
wasteful | -0.007 |
Token | that |
Token ID | 326 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
mine | +0.407 |
berry | +0.403 |
Will | +0.395 |
superstar | +0.394 |
Grac | +0.384 |
Neg logit contributions | |
site | -0.390 |
her | -0.390 |
office | -0.380 |
ia | -0.358 |
wasteful | -0.354 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
site | +0.304 |
office | +0.298 |
her | +0.292 |
wasteful | +0.276 |
mistake | +0.269 |
Neg logit contributions | |
mine | -0.244 |
berry | -0.241 |
superstar | -0.234 |
Will | -0.229 |
tie | -0.229 |
Token | was |
Token ID | 373 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
mine | +0.871 |
superstar | +0.833 |
Will | +0.830 |
berry | +0.827 |
Grac | +0.804 |
Neg logit contributions | |
her | -0.769 |
site | -0.758 |
office | -0.719 |
ia | -0.661 |
ups | -0.652 |
Token | that |
Token ID | 326 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
her | +0.057 |
site | +0.054 |
office | +0.052 |
wasteful | +0.048 |
ia | +0.047 |
Neg logit contributions | |
mine | -0.056 |
berry | -0.055 |
Will | -0.052 |
superstar | -0.052 |
berries | -0.051 |
Token | they |
Token ID | 484 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
site | +0.291 |
her | +0.288 |
office | +0.276 |
wasteful | +0.260 |
ia | +0.259 |
Neg logit contributions | |
berry | -0.258 |
mine | -0.249 |
superstar | -0.241 |
Will | -0.232 |
berries | -0.229 |
Token | were |
Token ID | 547 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
her | +0.004 |
wasteful | +0.004 |
site | +0.004 |
not | +0.004 |
office | +0.004 |
Neg logit contributions | |
berry | -0.005 |
berries | -0.005 |
Nice | -0.005 |
bird | -0.004 |
superstar | -0.004 |
Token | together |
Token ID | 1978 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
mine | +0.314 |
berry | +0.310 |
Will | +0.303 |
Benny | +0.297 |
Nice | +0.294 |
Neg logit contributions | |
her | -0.326 |
site | -0.313 |
office | -0.302 |
wasteful | -0.282 |
ia | -0.267 |
Token | didn |
Token ID | 1422 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
mine | +0.036 |
Benny | +0.035 |
Will | +0.035 |
berry | +0.035 |
wherever | +0.035 |
Neg logit contributions | |
site | -0.054 |
her | -0.053 |
office | -0.050 |
ia | -0.048 |
wasteful | -0.048 |
Token | 't |
Token ID | 470 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
mine | +0.042 |
Will | +0.042 |
Benny | +0.042 |
wherever | +0.040 |
ease | +0.039 |
Neg logit contributions | |
site | -0.092 |
her | -0.088 |
office | -0.088 |
wasteful | -0.085 |
ia | -0.084 |
Token | understand |
Token ID | 1833 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
berry | +0.180 |
wherever | +0.176 |
mine | +0.174 |
superstar | +0.173 |
Will | +0.168 |
Neg logit contributions | |
her | -0.219 |
site | -0.215 |
office | -0.207 |
wasteful | -0.202 |
ia | -0.201 |
Token | why |
Token ID | 1521 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
mine | +0.186 |
wherever | +0.185 |
Benny | +0.184 |
Will | +0.183 |
berry | +0.183 |
Neg logit contributions | |
site | -0.151 |
her | -0.149 |
office | -0.137 |
ia | -0.130 |
wasteful | -0.128 |
Token | it |
Token ID | 340 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
site | +0.389 |
her | +0.380 |
office | +0.368 |
ia | +0.349 |
wasteful | +0.345 |
Neg logit contributions | |
mine | -0.281 |
berry | -0.273 |
superstar | -0.270 |
wherever | -0.262 |
Will | -0.261 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
mine | +0.066 |
berry | +0.065 |
wherever | +0.064 |
superstar | +0.063 |
ease | +0.062 |
Neg logit contributions | |
her | -0.073 |
site | -0.071 |
office | -0.066 |
ia | -0.065 |
wasteful | -0.063 |
Token | so |
Token ID | 523 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
mine | +0.967 |
superstar | +0.964 |
berry | +0.932 |
Will | +0.921 |
Grac | +0.899 |
Neg logit contributions | |
her | -0.671 |
site | -0.650 |
office | -0.627 |
ups | -0.576 |
ia | -0.544 |
Token | much |
Token ID | 881 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
site | +0.115 |
her | +0.114 |
office | +0.106 |
ia | +0.103 |
wasteful | +0.101 |
Neg logit contributions | |
mine | -0.105 |
berry | -0.103 |
superstar | -0.100 |
wherever | -0.100 |
Will | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
site | +0.130 |
her | +0.127 |
office | +0.120 |
ia | +0.115 |
wasteful | +0.112 |
Neg logit contributions | |
mine | -0.130 |
berry | -0.126 |
superstar | -0.124 |
Will | -0.123 |
Benny | -0.123 |
Token | She |
Token ID | 1375 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
mine | +0.006 |
wherever | +0.006 |
berry | +0.006 |
Will | +0.006 |
Benny | +0.006 |
Neg logit contributions | |
site | -0.007 |
her | -0.007 |
office | -0.007 |
ia | -0.007 |
wasteful | -0.006 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
her | +0.096 |
site | +0.096 |
office | +0.090 |
ia | +0.087 |
wasteful | +0.085 |
Neg logit contributions | |
mine | -0.072 |
wherever | -0.071 |
berry | -0.070 |
Benny | -0.068 |
Will | -0.068 |
Token | and |
Token ID | 290 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
mine | +0.050 |
Grac | +0.047 |
Will | +0.047 |
superstar | +0.047 |
berry | +0.046 |
Neg logit contributions | |
her | -0.034 |
office | -0.033 |
site | -0.032 |
wasteful | -0.028 |
ia | -0.028 |
Token | that |
Token ID | 326 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
mine | +0.047 |
berry | +0.046 |
superstar | +0.042 |
berries | +0.042 |
Grac | +0.042 |
Neg logit contributions | |
site | -0.045 |
her | -0.044 |
office | -0.044 |
wasteful | -0.042 |
ups | -0.039 |
Token | was |
Token ID | 373 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
wasteful | +0.216 |
site | +0.216 |
mistake | +0.212 |
her | +0.212 |
not | +0.211 |
Neg logit contributions | |
mine | -0.335 |
berry | -0.305 |
superstar | -0.300 |
| | -0.290 |
amb | -0.289 |
Token | all |
Token ID | 477 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
her | +0.055 |
site | +0.054 |
office | +0.051 |
wasteful | +0.049 |
ia | +0.047 |
Neg logit contributions | |
mine | -0.059 |
berry | -0.057 |
Will | -0.055 |
superstar | -0.054 |
wherever | -0.054 |
Token | that |
Token ID | 326 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
mine | +0.497 |
berry | +0.479 |
Will | +0.454 |
superstar | +0.449 |
berries | +0.443 |
Neg logit contributions | |
her | -0.369 |
site | -0.342 |
office | -0.342 |
wasteful | -0.334 |
wrong | -0.297 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
her | +0.247 |
site | +0.242 |
wasteful | +0.239 |
not | +0.232 |
wrong | +0.230 |
Neg logit contributions | |
mine | -0.295 |
berry | -0.291 |
superstar | -0.280 |
amb | -0.261 |
Grac | -0.255 |
Token | . |
Token ID | 13 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
mine | +1.029 |
superstar | +1.017 |
berry | +0.962 |
Will | +0.954 |
oft | +0.930 |
Neg logit contributions | |
her | -0.624 |
site | -0.577 |
ups | -0.540 |
office | -0.527 |
yourselves | -0.525 |
Token | The |
Token ID | 383 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
mine | +0.007 |
stuffed | +0.007 |
mattered | +0.007 |
berry | +0.007 |
ease | +0.007 |
Neg logit contributions | |
her | -0.006 |
site | -0.006 |
office | -0.006 |
ia | -0.005 |
wasteful | -0.005 |
Token | moral |
Token ID | 6573 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
mine | +0.072 |
berry | +0.071 |
wherever | +0.071 |
Benny | +0.070 |
Will | +0.070 |
Neg logit contributions | |
site | -0.052 |
her | -0.051 |
office | -0.047 |
ia | -0.044 |
wasteful | -0.044 |
Token | of |
Token ID | 286 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
Benny | +0.008 |
wherever | +0.008 |
Will | +0.008 |
mine | +0.008 |
berry | +0.007 |
Neg logit contributions | |
site | -0.016 |
her | -0.016 |
office | -0.015 |
wasteful | -0.015 |
ia | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
mine | +0.048 |
superstar | +0.048 |
mattered | +0.048 |
berry | +0.047 |
ease | +0.046 |
Neg logit contributions | |
her | -0.048 |
site | -0.047 |
office | -0.045 |
ia | -0.041 |
wasteful | -0.040 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
berry | +0.042 |
mine | +0.042 |
Will | +0.039 |
Benny | +0.039 |
Grac | +0.039 |
Neg logit contributions | |
site | -0.051 |
her | -0.050 |
office | -0.047 |
ia | -0.046 |
wasteful | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
mine | +0.190 |
berry | +0.180 |
Grac | +0.177 |
ease | +0.176 |
Emmy | +0.171 |
Neg logit contributions | |
site | -0.150 |
her | -0.142 |
office | -0.134 |
ia | -0.130 |
men | -0.118 |
Token | like |
Token ID | 588 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
site | +0.021 |
her | +0.021 |
office | +0.020 |
wasteful | +0.018 |
ia | +0.018 |
Neg logit contributions | |
mine | -0.024 |
berry | -0.023 |
Grac | -0.022 |
Will | -0.022 |
mattered | -0.022 |
Token | nothing |
Token ID | 2147 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
mine | +0.263 |
berry | +0.249 |
berries | +0.230 |
Grac | +0.229 |
oft | +0.228 |
Neg logit contributions | |
site | -0.197 |
her | -0.188 |
office | -0.188 |
ia | -0.168 |
men | -0.163 |
Token | else |
Token ID | 2073 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
her | +0.010 |
site | +0.010 |
ia | +0.009 |
office | +0.009 |
wasteful | +0.009 |
Neg logit contributions | |
mine | -0.012 |
berry | -0.012 |
Grac | -0.011 |
ease | -0.011 |
berries | -0.011 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
her | +0.045 |
site | +0.044 |
ia | +0.041 |
office | +0.041 |
wasteful | +0.039 |
Neg logit contributions | |
mine | -0.055 |
berry | -0.052 |
Grac | -0.051 |
superstar | -0.051 |
ease | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
mine | +1.023 |
Grac | +1.004 |
superstar | +0.998 |
berry | +0.995 |
Emmy | +0.983 |
Neg logit contributions | |
her | -0.598 |
site | -0.577 |
ia | -0.531 |
office | -0.526 |
ups | -0.492 |
Token | |
Token ID | 220 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
mine | +0.005 |
berry | +0.005 |
wherever | +0.005 |
superstar | +0.005 |
mattered | +0.005 |
Neg logit contributions | |
site | -0.008 |
her | -0.008 |
office | -0.007 |
ia | -0.007 |
wasteful | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
mine | +0.220 |
wherever | +0.220 |
Benny | +0.218 |
Will | +0.217 |
berry | +0.212 |
Neg logit contributions | |
site | -0.391 |
her | -0.380 |
office | -0.368 |
wasteful | -0.356 |
ia | -0.347 |
Token |
|
Token ID | 198 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
mine | +0.023 |
Will | +0.023 |
wherever | +0.023 |
Benny | +0.023 |
berry | +0.022 |
Neg logit contributions | |
site | -0.041 |
her | -0.040 |
office | -0.039 |
wasteful | -0.038 |
ia | -0.036 |
Token | The |
Token ID | 464 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
mine | +0.032 |
wherever | +0.032 |
Will | +0.032 |
Benny | +0.031 |
superstar | +0.031 |
Neg logit contributions | |
site | -0.030 |
office | -0.029 |
her | -0.028 |
wasteful | -0.027 |
ia | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
mine | +0.215 |
berry | +0.215 |
Will | +0.210 |
wherever | +0.208 |
Benny | +0.208 |
Neg logit contributions | |
her | -0.267 |
site | -0.266 |
office | -0.248 |
ia | -0.237 |
wasteful | -0.236 |
Token | the |
Token ID | 262 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
site | +0.052 |
her | +0.051 |
office | +0.047 |
ia | +0.045 |
wasteful | +0.044 |
Neg logit contributions | |
mine | -0.061 |
Benny | -0.060 |
wherever | -0.060 |
Will | -0.060 |
berry | -0.060 |
Token | only |
Token ID | 691 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
site | +0.014 |
her | +0.014 |
office | +0.013 |
wasteful | +0.012 |
mistake | +0.012 |
Neg logit contributions | |
mine | -0.017 |
berry | -0.016 |
wherever | -0.016 |
Will | -0.016 |
Grac | -0.016 |
Token | one |
Token ID | 530 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
site | +0.002 |
her | +0.002 |
office | +0.002 |
wasteful | +0.002 |
ia | +0.002 |
Neg logit contributions | |
mine | -0.002 |
berry | -0.002 |
wherever | -0.002 |
Benny | -0.002 |
Will | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
mine | +0.320 |
Grac | +0.303 |
ease | +0.303 |
berry | +0.302 |
Will | +0.298 |
Neg logit contributions | |
her | -0.308 |
site | -0.308 |
office | -0.291 |
ia | -0.274 |
wasteful | -0.270 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
her | +0.294 |
site | +0.293 |
office | +0.272 |
wasteful | +0.266 |
men | +0.255 |
Neg logit contributions | |
mine | -0.265 |
berry | -0.265 |
superstar | -0.248 |
Grac | -0.242 |
wherever | -0.239 |
Token | . |
Token ID | 13 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
mine | +0.932 |
superstar | +0.912 |
berry | +0.908 |
Grac | +0.877 |
Will | +0.870 |
Neg logit contributions | |
her | -0.710 |
site | -0.685 |
office | -0.644 |
ups | -0.614 |
ia | -0.588 |
Token | He |
Token ID | 679 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
mine | +0.004 |
superstar | +0.004 |
berry | +0.004 |
wherever | +0.004 |
mattered | +0.004 |
Neg logit contributions | |
site | -0.006 |
her | -0.006 |
office | -0.006 |
ia | -0.006 |
wasteful | -0.005 |
Token | demanded |
Token ID | 12284 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
her | +0.099 |
site | +0.096 |
office | +0.089 |
ia | +0.088 |
wasteful | +0.085 |
Neg logit contributions | |
mine | -0.089 |
wherever | -0.088 |
berry | -0.087 |
ease | -0.085 |
Grac | -0.083 |
Token | that |
Token ID | 326 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
site | +0.206 |
her | +0.200 |
office | +0.187 |
ia | +0.177 |
wasteful | +0.174 |
Neg logit contributions | |
Benny | -0.232 |
mine | -0.230 |
Will | -0.228 |
wherever | -0.228 |
mattered | -0.225 |
Token | everyone |
Token ID | 2506 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
site | +0.282 |
office | +0.263 |
her | +0.254 |
wasteful | +0.244 |
mistake | +0.239 |
Neg logit contributions | |
mine | -0.280 |
berry | -0.274 |
superstar | -0.266 |
oft | -0.266 |
Grac | -0.254 |
Token | organized |
Token ID | 8389 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
site | +0.060 |
her | +0.057 |
office | +0.055 |
ia | +0.052 |
wasteful | +0.051 |
Neg logit contributions | |
wherever | -0.053 |
Benny | -0.053 |
mine | -0.053 |
Will | -0.052 |
mattered | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
her | +0.092 |
site | +0.091 |
office | +0.086 |
ia | +0.080 |
wasteful | +0.078 |
Neg logit contributions | |
mine | -0.085 |
berry | -0.084 |
Will | -0.084 |
Benny | -0.082 |
superstar | -0.082 |
Token | that |
Token ID | 326 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
mine | +0.035 |
berry | +0.035 |
Will | +0.034 |
Benny | +0.034 |
wherever | +0.034 |
Neg logit contributions | |
site | -0.051 |
her | -0.051 |
office | -0.048 |
ia | -0.046 |
wasteful | -0.046 |
Token | 's |
Token ID | 338 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
her | +0.293 |
site | +0.289 |
office | +0.284 |
wasteful | +0.263 |
ia | +0.260 |
Neg logit contributions | |
mine | -0.258 |
berry | -0.255 |
superstar | -0.244 |
Benny | -0.242 |
ease | -0.238 |
Token | what |
Token ID | 644 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
wherever | +0.061 |
mattered | +0.061 |
Benny | +0.060 |
mine | +0.060 |
Will | +0.059 |
Neg logit contributions | |
site | -0.061 |
her | -0.057 |
office | -0.054 |
ia | -0.052 |
wasteful | -0.050 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
her | +0.289 |
site | +0.285 |
office | +0.285 |
ia | +0.267 |
ups | +0.262 |
Neg logit contributions | |
mine | -0.289 |
berry | -0.284 |
ease | -0.268 |
Benny | -0.268 |
superstar | -0.267 |
Token | most |
Token ID | 749 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
mine | +0.854 |
superstar | +0.849 |
berry | +0.846 |
Will | +0.831 |
ease | +0.808 |
Neg logit contributions | |
her | -0.784 |
site | -0.741 |
office | -0.724 |
ups | -0.666 |
ia | -0.657 |
Token | . |
Token ID | 13 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
mine | +0.278 |
Will | +0.259 |
berry | +0.258 |
Benny | +0.255 |
Grac | +0.255 |
Neg logit contributions | |
her | -0.181 |
site | -0.177 |
office | -0.167 |
ia | -0.154 |
ups | -0.152 |
Token | Since |
Token ID | 4619 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
mine | +0.005 |
stuffed | +0.005 |
wherever | +0.005 |
superstar | +0.005 |
ease | +0.005 |
Neg logit contributions | |
her | -0.005 |
site | -0.005 |
office | -0.005 |
ia | -0.005 |
wasteful | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
mine | +0.126 |
Benny | +0.124 |
Will | +0.124 |
wherever | +0.124 |
berry | +0.123 |
Neg logit contributions | |
site | -0.103 |
her | -0.101 |
office | -0.094 |
ia | -0.089 |
wasteful | -0.087 |
Token | couldn |
Token ID | 3521 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
mine | +0.070 |
wherever | +0.069 |
berry | +0.069 |
Benny | +0.068 |
Will | +0.067 |
Neg logit contributions | |
her | -0.068 |
site | -0.068 |
office | -0.064 |
ia | -0.061 |
wasteful | -0.060 |
Token | it |
Token ID | 340 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
site | +0.019 |
office | +0.019 |
her | +0.017 |
men | +0.017 |
wasteful | +0.016 |
Neg logit contributions | |
mine | -0.025 |
berry | -0.024 |
superstar | -0.023 |
oft | -0.023 |
tie | -0.023 |
Token | felt |
Token ID | 2936 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
mine | +0.069 |
berry | +0.067 |
wherever | +0.066 |
ease | +0.066 |
Benny | +0.065 |
Neg logit contributions | |
her | -0.072 |
site | -0.070 |
office | -0.064 |
ia | -0.063 |
ups | -0.061 |
Token | like |
Token ID | 588 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
her | +0.054 |
wasteful | +0.047 |
site | +0.047 |
office | +0.043 |
ia | +0.042 |
Neg logit contributions | |
mine | -0.061 |
berry | -0.059 |
berries | -0.056 |
Will | -0.054 |
superstar | -0.054 |
Token | nothing |
Token ID | 2147 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
mine | +0.240 |
berry | +0.232 |
oft | +0.214 |
superstar | +0.209 |
berries | +0.209 |
Neg logit contributions | |
her | -0.203 |
site | -0.201 |
office | -0.191 |
wasteful | -0.177 |
ia | -0.177 |
Token | else |
Token ID | 2073 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
her | +0.011 |
site | +0.010 |
wasteful | +0.009 |
ia | +0.009 |
office | +0.009 |
Neg logit contributions | |
mine | -0.013 |
berry | -0.012 |
ease | -0.011 |
berries | -0.011 |
Will | -0.011 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
her | +0.046 |
site | +0.044 |
office | +0.042 |
ia | +0.041 |
wasteful | +0.041 |
Neg logit contributions | |
mine | -0.053 |
berry | -0.051 |
superstar | -0.050 |
ease | -0.049 |
Grac | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
mine | +0.977 |
superstar | +0.972 |
berry | +0.953 |
Will | +0.942 |
Grac | +0.941 |
Neg logit contributions | |
her | -0.620 |
site | -0.596 |
office | -0.569 |
ups | -0.533 |
ia | -0.528 |
Token |
|
Token ID | 198 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
mine | +0.007 |
stuffed | +0.007 |
mattered | +0.007 |
superstar | +0.007 |
ease | +0.007 |
Neg logit contributions | |
office | -0.006 |
her | -0.006 |
site | -0.006 |
ia | -0.005 |
wasteful | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
mine | +0.036 |
superstar | +0.035 |
berry | +0.035 |
mattered | +0.035 |
Will | +0.035 |
Neg logit contributions | |
site | -0.026 |
her | -0.026 |
office | -0.024 |
ia | -0.023 |
wasteful | -0.021 |
Token | The |
Token ID | 464 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
mine | +0.035 |
berry | +0.034 |
Benny | +0.034 |
Will | +0.034 |
wherever | +0.034 |
Neg logit contributions | |
her | -0.028 |
site | -0.028 |
office | -0.025 |
ia | -0.024 |
wasteful | -0.023 |
Token | little |
Token ID | 1310 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
site | +0.103 |
her | +0.099 |
office | +0.090 |
wasteful | +0.090 |
yourselves | +0.088 |
Neg logit contributions | |
wherever | -0.095 |
Benny | -0.095 |
Will | -0.094 |
berry | -0.094 |
mine | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
mine | +0.031 |
wherever | +0.031 |
Benny | +0.031 |
Will | +0.031 |
berry | +0.030 |
Neg logit contributions | |
site | -0.032 |
her | -0.032 |
office | -0.030 |
ia | -0.029 |
wasteful | -0.028 |
Token | meeting |
Token ID | 3249 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
her | +0.016 |
ia | +0.016 |
site | +0.016 |
office | +0.014 |
wasteful | +0.014 |
Neg logit contributions | |
wherever | -0.012 |
mine | -0.012 |
Benny | -0.012 |
Will | -0.012 |
berry | -0.012 |
Token | hadn |
Token ID | 8020 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
site | +0.132 |
her | +0.130 |
office | +0.123 |
ia | +0.116 |
wasteful | +0.114 |
Neg logit contributions | |
mine | -0.112 |
berry | -0.110 |
Will | -0.109 |
Benny | -0.109 |
wherever | -0.108 |
Token | 't |
Token ID | 470 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
mine | +0.077 |
berry | +0.076 |
Benny | +0.075 |
wherever | +0.075 |
Will | +0.075 |
Neg logit contributions | |
site | -0.119 |
her | -0.119 |
office | -0.112 |
ia | -0.107 |
wasteful | -0.105 |
Token | really |
Token ID | 1107 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
mine | +0.184 |
wherever | +0.181 |
Benny | +0.180 |
Will | +0.180 |
berry | +0.180 |
Neg logit contributions | |
site | -0.219 |
her | -0.215 |
office | -0.203 |
ia | -0.194 |
wasteful | -0.192 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
site | +0.028 |
her | +0.028 |
office | +0.026 |
ia | +0.025 |
wasteful | +0.024 |
Neg logit contributions | |
mine | -0.027 |
wherever | -0.026 |
Will | -0.026 |
Benny | -0.026 |
mattered | -0.026 |
Token | anyway |
Token ID | 6949 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
mine | +0.964 |
superstar | +0.959 |
berry | +0.952 |
Grac | +0.938 |
Will | +0.911 |
Neg logit contributions | |
site | -0.673 |
her | -0.661 |
office | -0.622 |
ups | -0.557 |
yourselves | -0.555 |
Token | . |
Token ID | 13 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
mine | +0.177 |
wherever | +0.174 |
berry | +0.173 |
Benny | +0.173 |
Will | +0.173 |
Neg logit contributions | |
site | -0.218 |
her | -0.215 |
office | -0.202 |
ia | -0.193 |
wasteful | -0.192 |
Token | They |
Token ID | 1119 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
mine | +0.006 |
berry | +0.005 |
wherever | +0.005 |
mattered | +0.005 |
ease | +0.005 |
Neg logit contributions | |
site | -0.007 |
her | -0.007 |
office | -0.006 |
ia | -0.006 |
wasteful | -0.006 |
Token | had |
Token ID | 550 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
her | +0.146 |
site | +0.135 |
office | +0.130 |
wasteful | +0.127 |
ia | +0.124 |
Neg logit contributions | |
berry | -0.127 |
Nice | -0.127 |
wherever | -0.122 |
berries | -0.118 |
Benny | -0.117 |
Token | still |
Token ID | 991 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
berry | +0.049 |
mine | +0.049 |
Grac | +0.046 |
Will | +0.046 |
wherever | +0.046 |
Neg logit contributions | |
her | -0.052 |
site | -0.051 |
office | -0.048 |
wasteful | -0.045 |
ia | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
mine | +0.016 |
hello | +0.016 |
berry | +0.016 |
ease | +0.016 |
Will | +0.016 |
Neg logit contributions | |
her | -0.013 |
office | -0.012 |
site | -0.011 |
ia | -0.011 |
wasteful | -0.010 |
Token | that |
Token ID | 326 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
mine | +0.046 |
berry | +0.045 |
superstar | +0.042 |
Will | +0.041 |
berries | +0.040 |
Neg logit contributions | |
office | -0.045 |
her | -0.044 |
site | -0.044 |
wasteful | -0.043 |
ups | -0.040 |
Token | 's |
Token ID | 338 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
office | +0.249 |
her | +0.238 |
wasteful | +0.232 |
mistake | +0.226 |
site | +0.224 |
Neg logit contributions | |
mine | -0.299 |
berry | -0.290 |
tie | -0.282 |
amb | -0.279 |
superstar | -0.273 |
Token | all |
Token ID | 477 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
mine | +0.066 |
wherever | +0.065 |
berry | +0.065 |
Benny | +0.065 |
Will | +0.065 |
Neg logit contributions | |
site | -0.055 |
her | -0.054 |
office | -0.050 |
ia | -0.047 |
wasteful | -0.047 |
Token | that |
Token ID | 326 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
berry | +0.477 |
mine | +0.476 |
Will | +0.437 |
berries | +0.437 |
superstar | +0.435 |
Neg logit contributions | |
her | -0.367 |
office | -0.336 |
wasteful | -0.336 |
site | -0.316 |
wrong | -0.304 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
her | +0.251 |
office | +0.238 |
wasteful | +0.233 |
site | +0.230 |
not | +0.229 |
Neg logit contributions | |
berry | -0.290 |
mine | -0.279 |
amb | -0.276 |
superstar | -0.272 |
tie | -0.268 |
Token | . |
Token ID | 13 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
mine | +0.993 |
superstar | +0.969 |
berry | +0.961 |
ease | +0.938 |
Will | +0.918 |
Neg logit contributions | |
her | -0.647 |
office | -0.564 |
ups | -0.563 |
site | -0.549 |
yourselves | -0.531 |
Token | From |
Token ID | 3574 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
mine | +0.006 |
berry | +0.006 |
mattered | +0.006 |
superstar | +0.006 |
ease | +0.006 |
Neg logit contributions | |
her | -0.007 |
site | -0.007 |
office | -0.007 |
ia | -0.006 |
wasteful | -0.006 |
Token | that |
Token ID | 326 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
Benny | +0.089 |
wherever | +0.085 |
Emmy | +0.080 |
mine | +0.078 |
Will | +0.077 |
Neg logit contributions | |
site | -0.105 |
her | -0.092 |
office | -0.092 |
wasteful | -0.088 |
ia | -0.088 |
Token | day |
Token ID | 1110 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
office | +0.228 |
her | +0.218 |
mistake | +0.208 |
site | +0.206 |
ia | +0.189 |
Neg logit contributions | |
mine | -0.310 |
superstar | -0.307 |
berry | -0.306 |
ease | -0.303 |
berries | -0.297 |
Token | on |
Token ID | 319 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
mine | +0.033 |
berry | +0.032 |
wherever | +0.032 |
Benny | +0.032 |
Will | +0.032 |
Neg logit contributions | |
site | -0.053 |
her | -0.052 |
office | -0.049 |
ia | -0.047 |
wasteful | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
her | +0.238 |
site | +0.229 |
office | +0.212 |
wasteful | +0.205 |
ia | +0.198 |
Neg logit contributions | |
mine | -0.255 |
berry | -0.252 |
ease | -0.240 |
Will | -0.238 |
berries | -0.236 |
Token | that |
Token ID | 326 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
mine | +0.046 |
berry | +0.045 |
superstar | +0.041 |
Will | +0.041 |
Grac | +0.041 |
Neg logit contributions | |
site | -0.046 |
her | -0.046 |
office | -0.044 |
wasteful | -0.042 |
ia | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
site | +0.277 |
office | +0.271 |
her | +0.259 |
wasteful | +0.246 |
men | +0.244 |
Neg logit contributions | |
mine | -0.301 |
berry | -0.280 |
superstar | -0.266 |
berries | -0.251 |
Grac | -0.250 |
Token | all |
Token ID | 477 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
site | +0.056 |
her | +0.056 |
office | +0.052 |
ia | +0.049 |
wasteful | +0.049 |
Neg logit contributions | |
mine | -0.056 |
berry | -0.055 |
Will | -0.054 |
wherever | -0.054 |
Benny | -0.054 |
Token | that |
Token ID | 326 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
mine | +0.461 |
berry | +0.456 |
superstar | +0.422 |
berries | +0.420 |
Will | +0.420 |
Neg logit contributions | |
her | -0.386 |
office | -0.370 |
site | -0.369 |
wasteful | -0.339 |
urgent | -0.312 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
site | +0.275 |
her | +0.267 |
office | +0.257 |
wasteful | +0.243 |
men | +0.239 |
Neg logit contributions | |
mine | -0.293 |
berry | -0.286 |
superstar | -0.272 |
berries | -0.256 |
Grac | -0.249 |
Token | . |
Token ID | 13 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
mine | +0.978 |
berry | +0.950 |
superstar | +0.948 |
Grac | +0.898 |
berries | +0.877 |
Neg logit contributions | |
her | -0.670 |
site | -0.641 |
office | -0.618 |
ups | -0.573 |
yourselves | -0.567 |
Token | From |
Token ID | 3574 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
mine | +0.006 |
berry | +0.006 |
superstar | +0.005 |
wherever | +0.005 |
mattered | +0.005 |
Neg logit contributions | |
site | -0.008 |
her | -0.007 |
office | -0.007 |
ia | -0.007 |
wasteful | -0.007 |
Token | that |
Token ID | 326 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
Benny | +0.090 |
wherever | +0.086 |
Hop | +0.082 |
Will | +0.080 |
Bruce | +0.078 |
Neg logit contributions | |
site | -0.101 |
her | -0.092 |
office | -0.091 |
wasteful | -0.089 |
ia | -0.087 |
Token | day |
Token ID | 1110 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
office | +0.238 |
site | +0.230 |
her | +0.226 |
mistake | +0.208 |
ia | +0.200 |
Neg logit contributions | |
mine | -0.309 |
berry | -0.306 |
superstar | -0.294 |
berries | -0.293 |
ease | -0.293 |
Token | on |
Token ID | 319 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
mine | +0.033 |
berry | +0.033 |
Benny | +0.032 |
Will | +0.032 |
wherever | +0.032 |
Neg logit contributions | |
site | -0.052 |
her | -0.052 |
office | -0.049 |
ia | -0.047 |
wasteful | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
mine | +0.198 |
Will | +0.181 |
ease | +0.180 |
berry | +0.177 |
hello | +0.174 |
Neg logit contributions | |
office | -0.137 |
her | -0.132 |
site | -0.129 |
mistake | -0.124 |
ia | -0.119 |
Token | that |
Token ID | 326 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
mine | +0.050 |
berry | +0.049 |
superstar | +0.044 |
berries | +0.043 |
Will | +0.043 |
Neg logit contributions | |
her | -0.040 |
office | -0.039 |
wasteful | -0.038 |
site | -0.038 |
ups | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
her | +0.253 |
office | +0.252 |
site | +0.240 |
wasteful | +0.239 |
ups | +0.228 |
Neg logit contributions | |
mine | -0.308 |
berry | -0.304 |
superstar | -0.278 |
tie | -0.274 |
amb | -0.273 |
Token | all |
Token ID | 477 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
her | +0.053 |
site | +0.050 |
office | +0.048 |
wasteful | +0.046 |
ia | +0.044 |
Neg logit contributions | |
mine | -0.065 |
berry | -0.064 |
Will | -0.061 |
wherever | -0.061 |
superstar | -0.060 |
Token | that |
Token ID | 326 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
mine | +0.500 |
berry | +0.491 |
Will | +0.471 |
superstar | +0.456 |
berries | +0.449 |
Neg logit contributions | |
her | -0.356 |
office | -0.328 |
wasteful | -0.324 |
site | -0.311 |
old | -0.285 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
her | +0.277 |
wasteful | +0.257 |
office | +0.254 |
site | +0.254 |
ups | +0.251 |
Neg logit contributions | |
berry | -0.288 |
mine | -0.279 |
superstar | -0.261 |
amb | -0.251 |
berries | -0.248 |
Token | . |
Token ID | 13 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
mine | +0.993 |
berry | +0.964 |
superstar | +0.963 |
Will | +0.932 |
ease | +0.921 |
Neg logit contributions | |
her | -0.659 |
site | -0.583 |
office | -0.581 |
ups | -0.573 |
yourselves | -0.557 |
Token | From |
Token ID | 3574 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
mine | +0.004 |
berry | +0.004 |
mattered | +0.004 |
ease | +0.004 |
stuffed | +0.004 |
Neg logit contributions | |
her | -0.005 |
site | -0.004 |
office | -0.004 |
ia | -0.004 |
wasteful | -0.004 |
Token | that |
Token ID | 326 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
Benny | +0.088 |
wherever | +0.085 |
Emmy | +0.080 |
mine | +0.079 |
Hop | +0.077 |
Neg logit contributions | |
site | -0.097 |
her | -0.088 |
office | -0.086 |
ia | -0.083 |
wasteful | -0.082 |
Token | day |
Token ID | 1110 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
office | +0.229 |
her | +0.219 |
site | +0.212 |
mistake | +0.197 |
ia | +0.190 |
Neg logit contributions | |
mine | -0.315 |
ease | -0.312 |
berry | -0.312 |
superstar | -0.311 |
berries | -0.306 |
Token | on |
Token ID | 319 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
mine | +0.032 |
berry | +0.031 |
Benny | +0.031 |
Will | +0.031 |
wherever | +0.031 |
Neg logit contributions | |
site | -0.049 |
her | -0.048 |
office | -0.046 |
ia | -0.044 |
wasteful | -0.043 |
Token | her |
Token ID | 607 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
mine | +0.007 |
berry | +0.007 |
superstar | +0.007 |
Will | +0.007 |
Benny | +0.007 |
Neg logit contributions | |
her | -0.009 |
site | -0.009 |
office | -0.009 |
ia | -0.009 |
wasteful | -0.008 |
Token | or |
Token ID | 393 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
mine | +0.170 |
ease | +0.157 |
Will | +0.156 |
berry | +0.154 |
hello | +0.152 |
Neg logit contributions | |
office | -0.153 |
her | -0.152 |
site | -0.147 |
ia | -0.144 |
mistake | -0.134 |
Token | not |
Token ID | 407 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
her | +0.073 |
site | +0.071 |
office | +0.069 |
wasteful | +0.067 |
ia | +0.063 |
Neg logit contributions | |
mine | -0.072 |
berry | -0.072 |
superstar | -0.067 |
Will | -0.066 |
ease | -0.065 |
Token | , |
Token ID | 11 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
her | +0.311 |
site | +0.296 |
office | +0.293 |
wasteful | +0.278 |
ia | +0.266 |
Neg logit contributions | |
mine | -0.296 |
berry | -0.289 |
Will | -0.280 |
superstar | -0.276 |
Benny | -0.275 |
Token | what |
Token ID | 644 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
her | +0.026 |
site | +0.025 |
office | +0.025 |
wasteful | +0.024 |
ia | +0.023 |
Neg logit contributions | |
mine | -0.023 |
berry | -0.022 |
superstar | -0.022 |
ease | -0.021 |
Will | -0.021 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
her | +0.276 |
office | +0.267 |
wasteful | +0.259 |
ups | +0.250 |
site | +0.248 |
Neg logit contributions | |
berry | -0.327 |
mine | -0.323 |
ease | -0.306 |
superstar | -0.293 |
hello | -0.290 |
Token | was |
Token ID | 373 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
mine | +0.876 |
berry | +0.859 |
superstar | +0.854 |
Will | +0.832 |
ease | +0.831 |
Neg logit contributions | |
her | -0.777 |
office | -0.701 |
site | -0.693 |
ups | -0.661 |
yourselves | -0.654 |
Token | being |
Token ID | 852 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
her | +0.058 |
site | +0.052 |
office | +0.052 |
wasteful | +0.048 |
ups | +0.047 |
Neg logit contributions | |
mine | -0.064 |
berry | -0.064 |
superstar | -0.059 |
Will | -0.058 |
ease | -0.058 |
Token | comfortable |
Token ID | 6792 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
her | +0.056 |
wasteful | +0.049 |
office | +0.047 |
site | +0.047 |
yourselves | +0.044 |
Neg logit contributions | |
berry | -0.068 |
mine | -0.067 |
ease | -0.063 |
berries | -0.062 |
wherever | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
mine | +0.107 |
Will | +0.104 |
berry | +0.104 |
ease | +0.104 |
superstar | +0.103 |
Neg logit contributions | |
her | -0.095 |
site | -0.092 |
office | -0.090 |
wasteful | -0.080 |
ia | -0.079 |
Token | having |
Token ID | 1719 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
berry | +0.052 |
mine | +0.052 |
Will | +0.048 |
superstar | +0.048 |
berries | +0.047 |
Neg logit contributions | |
her | -0.039 |
site | -0.035 |
office | -0.034 |
wasteful | -0.034 |
ups | -0.031 |
Token | And |
Token ID | 843 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
mine | +0.004 |
berry | +0.004 |
mattered | +0.004 |
wherever | +0.004 |
ease | +0.004 |
Neg logit contributions | |
her | -0.005 |
site | -0.005 |
office | -0.004 |
ia | -0.004 |
wasteful | -0.004 |
Token | that |
Token ID | 326 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
her | +0.002 |
site | +0.001 |
office | +0.001 |
ia | +0.001 |
wasteful | +0.001 |
Neg logit contributions | |
berry | -0.001 |
mine | -0.001 |
ease | -0.001 |
superstar | -0.001 |
mattered | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
her | +0.263 |
office | +0.258 |
site | +0.248 |
ia | +0.230 |
wasteful | +0.227 |
Neg logit contributions | |
mine | -0.304 |
berry | -0.291 |
ease | -0.286 |
superstar | -0.278 |
wherever | -0.277 |
Token | what |
Token ID | 644 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
wherever | +0.057 |
mine | +0.057 |
Benny | +0.057 |
Will | +0.056 |
mattered | +0.056 |
Neg logit contributions | |
site | -0.062 |
her | -0.060 |
office | -0.056 |
ia | -0.054 |
wasteful | -0.052 |
Token | really |
Token ID | 1107 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
office | +0.259 |
her | +0.250 |
ia | +0.235 |
wasteful | +0.234 |
site | +0.231 |
Neg logit contributions | |
mine | -0.328 |
berry | -0.316 |
hello | -0.302 |
ease | -0.298 |
wherever | -0.295 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
her | +0.029 |
site | +0.029 |
office | +0.027 |
ia | +0.026 |
wasteful | +0.026 |
Neg logit contributions | |
mine | -0.030 |
berry | -0.030 |
wherever | -0.029 |
Benny | -0.029 |
ease | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
mine | +0.899 |
berry | +0.877 |
superstar | +0.853 |
ease | +0.852 |
Will | +0.817 |
Neg logit contributions | |
her | -0.746 |
office | -0.710 |
site | -0.697 |
ups | -0.656 |
ia | -0.623 |
Token | The |
Token ID | 383 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
mine | +0.005 |
stuffed | +0.004 |
mattered | +0.004 |
ease | +0.004 |
berry | +0.004 |
Neg logit contributions | |
her | -0.005 |
site | -0.004 |
office | -0.004 |
ia | -0.004 |
wasteful | -0.004 |
Token | end |
Token ID | 886 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
mine | +0.080 |
berry | +0.077 |
Will | +0.077 |
wherever | +0.077 |
Benny | +0.077 |
Neg logit contributions | |
site | -0.042 |
her | -0.042 |
office | -0.040 |
ia | -0.036 |
wasteful | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
site | +0.248 |
her | +0.243 |
office | +0.229 |
ia | +0.218 |
wasteful | +0.218 |
Neg logit contributions | |
mine | -0.201 |
wherever | -0.198 |
Benny | -0.198 |
berry | -0.198 |
Will | -0.198 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
mine | +0.005 |
mattered | +0.005 |
stuffed | +0.005 |
berry | +0.005 |
ease | +0.005 |
Neg logit contributions | |
her | -0.005 |
site | -0.004 |
office | -0.004 |
ia | -0.004 |
wasteful | -0.004 |
Token | They |
Token ID | 1119 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
mine | +0.003 |
mattered | +0.003 |
berry | +0.003 |
superstar | +0.003 |
stuffed | +0.003 |
Neg logit contributions | |
her | -0.003 |
site | -0.003 |
office | -0.003 |
ia | -0.003 |
wasteful | -0.003 |
Token | both |
Token ID | 1111 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
her | +0.125 |
ia | +0.119 |
wasteful | +0.107 |
office | +0.103 |
ena | +0.101 |
Neg logit contributions | |
Nice | -0.149 |
berry | -0.146 |
berries | -0.140 |
Grac | -0.131 |
Happy | -0.130 |
Token | learned |
Token ID | 4499 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
berry | +0.240 |
berries | +0.237 |
Grac | +0.225 |
Nice | +0.225 |
wherever | +0.219 |
Neg logit contributions | |
her | -0.231 |
ia | -0.229 |
wasteful | -0.207 |
office | -0.202 |
site | -0.201 |
Token | that |
Token ID | 326 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
mine | +0.179 |
wherever | +0.179 |
Benny | +0.179 |
Will | +0.177 |
berry | +0.176 |
Neg logit contributions | |
site | -0.133 |
her | -0.130 |
office | -0.120 |
ia | -0.114 |
wasteful | -0.112 |
Token | what |
Token ID | 644 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
site | +0.257 |
office | +0.247 |
her | +0.245 |
mistake | +0.235 |
wasteful | +0.232 |
Neg logit contributions | |
mine | -0.328 |
berry | -0.297 |
superstar | -0.284 |
tie | -0.280 |
oft | -0.276 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
site | +0.247 |
her | +0.245 |
office | +0.243 |
wasteful | +0.237 |
ups | +0.233 |
Neg logit contributions | |
mine | -0.353 |
berry | -0.327 |
ease | -0.320 |
superstar | -0.306 |
Grac | -0.300 |
Token | was |
Token ID | 373 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
mine | +0.980 |
berry | +0.950 |
superstar | +0.933 |
ease | +0.898 |
Grac | +0.895 |
Neg logit contributions | |
her | -0.690 |
site | -0.634 |
office | -0.610 |
wasteful | -0.587 |
ups | -0.575 |
Token | being |
Token ID | 852 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
her | +0.052 |
site | +0.047 |
office | +0.046 |
wasteful | +0.043 |
ups | +0.042 |
Neg logit contributions | |
mine | -0.070 |
berry | -0.069 |
berries | -0.064 |
superstar | -0.062 |
Grac | -0.062 |
Token | nice |
Token ID | 3621 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
her | +0.049 |
wasteful | +0.043 |
site | +0.043 |
office | +0.041 |
yourselves | +0.039 |
Neg logit contributions | |
mine | -0.074 |
berry | -0.073 |
ease | -0.068 |
berries | -0.068 |
superstar | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
her | +0.072 |
office | +0.069 |
site | +0.069 |
ia | +0.065 |
ups | +0.063 |
Neg logit contributions | |
mine | -0.089 |
ease | -0.083 |
berry | -0.083 |
superstar | -0.082 |
Grac | -0.082 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
mine | +0.056 |
berry | +0.056 |
berries | +0.050 |
superstar | +0.048 |
ease | +0.048 |
Neg logit contributions | |
her | -0.038 |
wasteful | -0.034 |
site | -0.033 |
office | -0.032 |
disrespectful | -0.030 |
Token | their |
Token ID | 511 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
site | +0.281 |
her | +0.268 |
office | +0.265 |
wasteful | +0.246 |
men | +0.239 |
Neg logit contributions | |
mine | -0.292 |
berry | -0.270 |
superstar | -0.268 |
oft | -0.257 |
tie | -0.255 |
Token | l |
Token ID | 300 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
site | +0.072 |
her | +0.072 |
office | +0.068 |
ia | +0.065 |
wasteful | +0.064 |
Neg logit contributions | |
mine | -0.052 |
Benny | -0.050 |
berry | -0.050 |
Will | -0.049 |
wherever | -0.049 |
Token | oll |
Token ID | 692 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
mine | +0.257 |
wherever | +0.255 |
Will | +0.254 |
Benny | +0.254 |
berry | +0.252 |
Neg logit contributions | |
her | -0.185 |
site | -0.182 |
office | -0.169 |
ia | -0.165 |
wasteful | -0.156 |
Token | ip |
Token ID | 541 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
her | +0.237 |
ia | +0.233 |
site | +0.231 |
office | +0.227 |
wasteful | +0.213 |
Neg logit contributions | |
superstar | -0.181 |
mine | -0.180 |
wherever | -0.178 |
ease | -0.177 |
Benny | -0.174 |
Token | ops |
Token ID | 2840 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
her | +0.068 |
site | +0.063 |
ia | +0.062 |
office | +0.062 |
ups | +0.058 |
Neg logit contributions | |
superstar | -0.060 |
wherever | -0.058 |
mine | -0.058 |
Will | -0.057 |
Nice | -0.057 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
superstar | +0.056 |
Will | +0.055 |
berry | +0.054 |
mine | +0.054 |
Grac | +0.053 |
Neg logit contributions | |
her | -0.073 |
site | -0.069 |
office | -0.066 |
ia | -0.064 |
wasteful | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
mine | +0.940 |
superstar | +0.924 |
berry | +0.907 |
Will | +0.881 |
ease | +0.876 |
Neg logit contributions | |
her | -0.697 |
site | -0.655 |
office | -0.614 |
ups | -0.588 |
ia | -0.569 |
Token | By |
Token ID | 2750 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
mine | +0.005 |
berry | +0.005 |
superstar | +0.005 |
stuffed | +0.005 |
wherever | +0.004 |
Neg logit contributions | |
site | -0.005 |
her | -0.005 |
office | -0.005 |
ia | -0.005 |
wasteful | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
site | +0.267 |
her | +0.262 |
office | +0.245 |
wasteful | +0.232 |
ia | +0.228 |
Neg logit contributions | |
mine | -0.245 |
berry | -0.242 |
wherever | -0.236 |
mattered | -0.235 |
superstar | -0.234 |
Token | end |
Token ID | 886 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
site | +0.015 |
her | +0.014 |
office | +0.013 |
ia | +0.013 |
wasteful | +0.013 |
Neg logit contributions | |
mine | -0.017 |
berry | -0.017 |
wherever | -0.017 |
Benny | -0.017 |
Will | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
site | +0.278 |
her | +0.274 |
office | +0.260 |
ia | +0.250 |
wasteful | +0.247 |
Neg logit contributions | |
mine | -0.173 |
wherever | -0.168 |
berry | -0.168 |
Benny | -0.167 |
Will | -0.167 |
Token | , |
Token ID | 11 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
her | +0.322 |
site | +0.316 |
office | +0.300 |
ia | +0.276 |
ups | +0.273 |
Neg logit contributions | |
mine | -0.369 |
Will | -0.356 |
superstar | -0.356 |
berry | -0.348 |
Benny | -0.345 |
Token | and |
Token ID | 290 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
her | +0.024 |
site | +0.023 |
office | +0.023 |
wasteful | +0.020 |
men | +0.020 |
Neg logit contributions | |
mine | -0.027 |
berry | -0.025 |
superstar | -0.024 |
mattered | -0.024 |
Grac | -0.024 |
Token | that |
Token ID | 326 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
mine | +0.043 |
berry | +0.042 |
superstar | +0.039 |
berries | +0.038 |
ease | +0.038 |
Neg logit contributions | |
site | -0.043 |
her | -0.041 |
office | -0.041 |
wasteful | -0.038 |
ia | -0.037 |
Token | 's |
Token ID | 338 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
site | +0.282 |
her | +0.270 |
office | +0.267 |
wasteful | +0.247 |
men | +0.245 |
Neg logit contributions | |
mine | -0.293 |
berry | -0.277 |
superstar | -0.265 |
tie | -0.258 |
Will | -0.253 |
Token | what |
Token ID | 644 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
mine | +0.058 |
wherever | +0.058 |
Benny | +0.058 |
Will | +0.058 |
berry | +0.057 |
Neg logit contributions | |
site | -0.057 |
her | -0.056 |
office | -0.052 |
ia | -0.050 |
wasteful | -0.049 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
site | +0.266 |
her | +0.252 |
office | +0.248 |
men | +0.240 |
ups | +0.239 |
Neg logit contributions | |
mine | -0.338 |
berry | -0.321 |
superstar | -0.300 |
wherever | -0.297 |
ease | -0.296 |
Token | . |
Token ID | 13 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
mine | +0.900 |
superstar | +0.869 |
berry | +0.856 |
Will | +0.843 |
ease | +0.831 |
Neg logit contributions | |
her | -0.743 |
site | -0.723 |
office | -0.667 |
ups | -0.638 |
ia | -0.619 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
stuffed | +0.004 |
mine | +0.004 |
mattered | +0.004 |
superstar | +0.004 |
ease | +0.004 |
Neg logit contributions | |
site | -0.004 |
her | -0.004 |
office | -0.003 |
ia | -0.003 |
wasteful | -0.003 |
Token | One |
Token ID | 3198 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
site | +0.149 |
her | +0.146 |
office | +0.133 |
ia | +0.132 |
men | +0.113 |
Neg logit contributions | |
superstar | -0.184 |
mine | -0.181 |
stuffed | -0.181 |
mattered | -0.180 |
Grac | -0.175 |
Token | day |
Token ID | 1110 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
site | +0.046 |
her | +0.046 |
office | +0.044 |
ia | +0.043 |
wasteful | +0.041 |
Neg logit contributions | |
mine | -0.029 |
berry | -0.028 |
Will | -0.028 |
wherever | -0.028 |
Benny | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
mine | +0.040 |
superstar | +0.039 |
berry | +0.039 |
ease | +0.038 |
wherever | +0.038 |
Neg logit contributions | |
site | -0.040 |
her | -0.039 |
ia | -0.036 |
office | -0.036 |
wasteful | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
mine | +0.420 |
berry | +0.413 |
ease | +0.408 |
Will | +0.401 |
hello | +0.395 |
Neg logit contributions | |
her | -0.380 |
site | -0.365 |
office | -0.364 |
ia | -0.327 |
wasteful | -0.309 |
Token | that |
Token ID | 326 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
mine | +0.045 |
berry | +0.045 |
superstar | +0.041 |
ease | +0.040 |
Will | +0.040 |
Neg logit contributions | |
her | -0.044 |
site | -0.042 |
office | -0.041 |
wasteful | -0.041 |
ia | -0.038 |
Token | 's |
Token ID | 338 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
office | +0.259 |
her | +0.257 |
site | +0.249 |
wasteful | +0.245 |
mistake | +0.227 |
Neg logit contributions | |
mine | -0.304 |
berry | -0.299 |
amb | -0.269 |
superstar | -0.268 |
tie | -0.267 |
Token | all |
Token ID | 477 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
mine | +0.069 |
berry | +0.068 |
Will | +0.066 |
Benny | +0.066 |
wherever | +0.066 |
Neg logit contributions | |
her | -0.050 |
site | -0.049 |
office | -0.046 |
wasteful | -0.043 |
ia | -0.043 |
Token | that |
Token ID | 326 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
berry | +0.498 |
mine | +0.482 |
berries | +0.451 |
superstar | +0.439 |
Will | +0.430 |
Neg logit contributions | |
her | -0.360 |
wasteful | -0.332 |
office | -0.327 |
site | -0.322 |
old | -0.291 |
Token | mattered |
Token ID | 33343 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
her | +0.276 |
office | +0.264 |
site | +0.262 |
wasteful | +0.253 |
ups | +0.237 |
Neg logit contributions | |
berry | -0.292 |
mine | -0.285 |
superstar | -0.265 |
amb | -0.256 |
tie | -0.253 |
Token | . |
Token ID | 13 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
mine | +0.980 |
berry | +0.957 |
superstar | +0.936 |
ease | +0.900 |
Will | +0.885 |
Neg logit contributions | |
her | -0.685 |
site | -0.621 |
office | -0.613 |
ups | -0.588 |
yourselves | -0.575 |
Token | From |
Token ID | 3574 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
mine | +0.004 |
ease | +0.004 |
berry | +0.004 |
wherever | +0.004 |
mattered | +0.004 |
Neg logit contributions | |
her | -0.004 |
site | -0.004 |
office | -0.004 |
ia | -0.004 |
wasteful | -0.004 |
Token | then |
Token ID | 788 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
Benny | +0.091 |
wherever | +0.086 |
Emmy | +0.083 |
mine | +0.081 |
Will | +0.080 |
Neg logit contributions | |
site | -0.096 |
office | -0.085 |
her | -0.085 |
ia | -0.082 |
wasteful | -0.081 |
Token | on |
Token ID | 319 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
site | +0.438 |
her | +0.435 |
office | +0.414 |
ia | +0.393 |
wasteful | +0.390 |
Neg logit contributions | |
mine | -0.298 |
berry | -0.292 |
Benny | -0.288 |
Will | -0.288 |
wherever | -0.286 |
Token | , |
Token ID | 11 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
mine | +0.072 |
berry | +0.071 |
superstar | +0.070 |
Will | +0.070 |
ease | +0.070 |
Neg logit contributions | |
site | -0.076 |
her | -0.075 |
office | -0.071 |
ia | -0.068 |
wasteful | -0.065 |
Token | was |
Token ID | 373 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
site | +0.105 |
her | +0.103 |
office | +0.099 |
wasteful | +0.093 |
ia | +0.093 |
Neg logit contributions | |
mine | -0.066 |
Will | -0.065 |
Benny | -0.064 |
berry | -0.064 |
wherever | -0.063 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
site | +0.060 |
her | +0.053 |
office | +0.052 |
ia | +0.051 |
ups | +0.049 |
Neg logit contributions | |
Will | -0.053 |
Benny | -0.052 |
stuffed | -0.051 |
wherever | -0.051 |
Grac | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
site | +0.164 |
her | +0.158 |
office | +0.146 |
wasteful | +0.143 |
ia | +0.139 |
Neg logit contributions | |
wherever | -0.086 |
Benny | -0.083 |
Will | -0.083 |
berry | -0.082 |
mattered | -0.076 |
Token |
|
Token ID | 198 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
mine | +0.006 |
berry | +0.005 |
superstar | +0.005 |
wherever | +0.005 |
mattered | +0.005 |
Neg logit contributions | |
her | -0.007 |
site | -0.007 |
office | -0.006 |
ia | -0.006 |
wasteful | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Benny | +0.017 |
wherever | +0.017 |
Will | +0.016 |
mine | +0.016 |
ease | +0.015 |
Neg logit contributions | |
site | -0.046 |
wasteful | -0.044 |
office | -0.044 |
her | -0.044 |
disrespectful | -0.041 |
Token | Then |
Token ID | 6423 |
Feature activation | +7.80e+00 |
Pos logit contributions | |
mine | +0.027 |
wherever | +0.025 |
Benny | +0.025 |
mattered | +0.024 |
Will | +0.024 |
Neg logit contributions | |
site | -0.038 |
office | -0.035 |
her | -0.034 |
wasteful | -0.033 |
men | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
site | +0.612 |
her | +0.598 |
office | +0.578 |
ia | +0.558 |
wasteful | +0.537 |
Neg logit contributions | |
mine | -0.495 |
berry | -0.482 |
wherever | -0.473 |
superstar | -0.473 |
Will | -0.470 |
Token | she |
Token ID | 673 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
site | +0.027 |
her | +0.027 |
office | +0.026 |
ia | +0.024 |
wasteful | +0.024 |
Neg logit contributions | |
mine | -0.017 |
berry | -0.017 |
wherever | -0.017 |
Benny | -0.016 |
superstar | -0.016 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Will | +0.056 |
Benny | +0.055 |
mine | +0.055 |
berry | +0.054 |
wherever | +0.053 |
Neg logit contributions | |
site | -0.087 |
her | -0.084 |
office | -0.080 |
wasteful | -0.076 |
ia | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
site | +0.174 |
her | +0.163 |
office | +0.156 |
ia | +0.149 |
wasteful | +0.149 |
Neg logit contributions | |
Benny | -0.130 |
Will | -0.126 |
mine | -0.123 |
Grac | -0.123 |
wherever | -0.123 |
Token | card |
Token ID | 2657 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
site | +0.061 |
her | +0.060 |
office | +0.055 |
ia | +0.053 |
wasteful | +0.052 |
Neg logit contributions | |
berry | -0.060 |
Benny | -0.059 |
Will | -0.059 |
mine | -0.059 |
wherever | -0.059 |
Token | you |
Token ID | 345 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
site | +0.313 |
her | +0.303 |
office | +0.295 |
ia | +0.278 |
wasteful | +0.274 |
Neg logit contributions | |
mine | -0.229 |
berry | -0.223 |
superstar | -0.218 |
wherever | -0.218 |
mattered | -0.215 |
Token | â |
Token ID | 22940 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
her | +0.003 |
site | +0.003 |
ia | +0.002 |
office | +0.002 |
wasteful | +0.002 |
Neg logit contributions | |
Nice | -0.002 |
mattered | -0.002 |
superstar | -0.002 |
wherever | -0.002 |
berry | -0.002 |
Token | € |
Token ID | 26391 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
site | +0.083 |
her | +0.077 |
office | +0.075 |
ia | +0.075 |
wasteful | +0.072 |
Neg logit contributions | |
mine | -0.078 |
Benny | -0.069 |
berry | -0.069 |
Will | -0.068 |
ease | -0.068 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
site | +0.210 |
her | +0.207 |
office | +0.194 |
wasteful | +0.188 |
ia | +0.186 |
Neg logit contributions | |
mine | -0.151 |
berry | -0.149 |
wherever | -0.148 |
Will | -0.148 |
Benny | -0.147 |
Token | re |
Token ID | 260 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Benny | +0.012 |
superstar | +0.012 |
wherever | +0.012 |
stuffed | +0.012 |
Will | +0.012 |
Neg logit contributions | |
her | -0.020 |
site | -0.020 |
office | -0.018 |
ia | -0.018 |
wasteful | -0.017 |
Token | old |
Token ID | 1468 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
mine | +0.120 |
wherever | +0.117 |
Will | +0.116 |
Benny | +0.116 |
berry | +0.116 |
Neg logit contributions | |
site | -0.139 |
her | -0.134 |
office | -0.126 |
wasteful | -0.121 |
ia | -0.120 |
Token | enough |
Token ID | 1576 |
Feature activation | +7.35e+00 |
Pos logit contributions | |
site | +0.541 |
her | +0.528 |
office | +0.514 |
ia | +0.478 |
wasteful | +0.471 |
Neg logit contributions | |
mine | -0.470 |
berry | -0.454 |
wherever | -0.452 |
Will | -0.452 |
ease | -0.449 |
Token | , |
Token ID | 11 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
site | +0.586 |
her | +0.578 |
office | +0.546 |
ia | +0.521 |
wasteful | +0.516 |
Neg logit contributions | |
mine | -0.462 |
berry | -0.451 |
wherever | -0.450 |
Benny | -0.450 |
Will | -0.449 |
Token | I |
Token ID | 314 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
site | +0.029 |
her | +0.029 |
office | +0.027 |
ia | +0.026 |
wasteful | +0.026 |
Neg logit contributions | |
mine | -0.024 |
berry | -0.023 |
superstar | -0.023 |
wherever | -0.023 |
Will | -0.023 |
Token | â |
Token ID | 22940 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
wherever | +0.117 |
Benny | +0.117 |
mine | +0.115 |
mattered | +0.112 |
berry | +0.112 |
Neg logit contributions | |
her | -0.179 |
site | -0.173 |
office | -0.170 |
ia | -0.161 |
wasteful | -0.157 |
Token | € |
Token ID | 26391 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
site | +0.087 |
her | +0.084 |
office | +0.079 |
ia | +0.077 |
wasteful | +0.076 |
Neg logit contributions | |
mine | -0.086 |
berry | -0.082 |
Benny | -0.081 |
Will | -0.081 |
wherever | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
mine | +0.071 |
Benny | +0.071 |
wherever | +0.070 |
Will | +0.070 |
berry | +0.070 |
Neg logit contributions | |
site | -0.073 |
her | -0.072 |
office | -0.068 |
ia | -0.065 |
wasteful | -0.064 |
Token | swing |
Token ID | 9628 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
her | +0.018 |
site | +0.018 |
ia | +0.016 |
wasteful | +0.016 |
office | +0.016 |
Neg logit contributions | |
wherever | -0.018 |
Benny | -0.018 |
stuffed | -0.017 |
berry | -0.017 |
Will | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
mattered | +0.067 |
Benny | +0.067 |
Will | +0.066 |
mine | +0.066 |
Grac | +0.066 |
Neg logit contributions | |
site | -0.086 |
her | -0.086 |
office | -0.081 |
ia | -0.076 |
wasteful | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
superstar | +0.038 |
berry | +0.038 |
mine | +0.037 |
mattered | +0.037 |
Grac | +0.036 |
Neg logit contributions | |
site | -0.041 |
her | -0.041 |
office | -0.040 |
wasteful | -0.037 |
ia | -0.036 |
Token | sees |
Token ID | 7224 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
site | +0.020 |
her | +0.020 |
office | +0.018 |
ia | +0.017 |
wasteful | +0.017 |
Neg logit contributions | |
mine | -0.018 |
wherever | -0.017 |
berry | -0.017 |
Benny | -0.017 |
Will | -0.017 |
Token | aw |
Token ID | 707 |
Feature activation | +7.72e+00 |
Pos logit contributions | |
site | +0.301 |
her | +0.297 |
office | +0.278 |
ia | +0.264 |
wasteful | +0.261 |
Neg logit contributions | |
mine | -0.296 |
berry | -0.290 |
wherever | -0.289 |
Benny | -0.289 |
Will | -0.289 |
Token | too |
Token ID | 1165 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
site | +0.652 |
her | +0.637 |
office | +0.613 |
wasteful | +0.590 |
ia | +0.577 |
Neg logit contributions | |
mine | -0.452 |
wherever | -0.443 |
berry | -0.442 |
Will | -0.433 |
superstar | -0.422 |
Token | ." |
Token ID | 526 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
wherever | +0.062 |
mine | +0.058 |
mattered | +0.058 |
Benny | +0.057 |
berry | +0.057 |
Neg logit contributions | |
site | -0.097 |
office | -0.094 |
her | -0.092 |
wasteful | -0.089 |
ia | -0.085 |
Token |
|
Token ID | 198 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
mine | +0.210 |
mattered | +0.207 |
superstar | +0.207 |
ease | +0.204 |
wherever | +0.203 |
Neg logit contributions | |
site | -0.219 |
her | -0.216 |
office | -0.209 |
ia | -0.202 |
wasteful | -0.192 |
Token |
|
Token ID | 198 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
Benny | +0.019 |
Will | +0.019 |
mine | +0.019 |
wherever | +0.018 |
berry | +0.018 |
Neg logit contributions | |
site | -0.034 |
her | -0.033 |
office | -0.032 |
wasteful | -0.031 |
ia | -0.030 |
Token | " |
Token ID | 1 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
mine | +0.028 |
Benny | +0.028 |
berry | +0.028 |
Will | +0.027 |
wherever | +0.027 |
Neg logit contributions | |
site | -0.025 |
her | -0.025 |
office | -0.023 |
ia | -0.022 |
wasteful | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -9.43e-02 |
Pos logit contributions | |
site | +0.068 |
her | +0.067 |
office | +0.064 |
ia | +0.061 |
wasteful | +0.060 |
Neg logit contributions | |
mine | -0.049 |
berry | -0.047 |
wherever | -0.047 |
Benny | -0.047 |
Will | -0.047 |
Token | She |
Token ID | 1375 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
superstar | +0.007 |
mine | +0.007 |
ease | +0.007 |
mattered | +0.007 |
wherever | +0.007 |
Neg logit contributions | |
her | -0.006 |
office | -0.006 |
site | -0.005 |
ia | -0.005 |
wasteful | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
her | +0.106 |
site | +0.104 |
office | +0.099 |
ia | +0.096 |
wasteful | +0.093 |
Neg logit contributions | |
berry | -0.061 |
mine | -0.061 |
wherever | -0.059 |
ease | -0.059 |
Benny | -0.058 |
Token | three |
Token ID | 1115 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
site | +0.056 |
her | +0.055 |
office | +0.052 |
ia | +0.049 |
wasteful | +0.049 |
Neg logit contributions | |
mine | -0.053 |
berry | -0.052 |
wherever | -0.052 |
Benny | -0.052 |
Will | -0.052 |
Token | years |
Token ID | 812 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
site | +0.000 |
her | +0.000 |
office | +0.000 |
ia | +0.000 |
wasteful | +0.000 |
Neg logit contributions | |
mine | -0.000 |
berry | -0.000 |
wherever | -0.000 |
Benny | -0.000 |
Will | -0.000 |
Token | old |
Token ID | 1468 |
Feature activation | +7.07e+00 |
Pos logit contributions | |
site | +0.121 |
her | +0.116 |
wasteful | +0.103 |
yourselves | +0.094 |
office | +0.093 |
Neg logit contributions | |
Benny | -0.279 |
berry | -0.278 |
Grac | -0.273 |
Will | -0.272 |
stuffed | -0.268 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
site | +0.505 |
her | +0.501 |
office | +0.483 |
ia | +0.446 |
wasteful | +0.438 |
Neg logit contributions | |
mine | -0.498 |
ease | -0.488 |
mattered | -0.482 |
wherever | -0.481 |
Benny | -0.480 |
Token | She |
Token ID | 1375 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
superstar | +0.008 |
mine | +0.008 |
mattered | +0.008 |
stuffed | +0.008 |
wherever | +0.008 |
Neg logit contributions | |
her | -0.007 |
site | -0.007 |
office | -0.007 |
ia | -0.007 |
yourselves | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
her | +0.111 |
site | +0.110 |
office | +0.104 |
ia | +0.101 |
wasteful | +0.099 |
Neg logit contributions | |
mine | -0.058 |
berry | -0.057 |
wherever | -0.057 |
ease | -0.055 |
Benny | -0.055 |
Token | a |
Token ID | 257 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
mine | +0.055 |
berry | +0.054 |
wherever | +0.053 |
Benny | +0.053 |
Will | +0.052 |
Neg logit contributions | |
her | -0.048 |
site | -0.047 |
office | -0.045 |
ia | -0.041 |
wasteful | -0.041 |
Token | big |
Token ID | 1263 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
office | +0.055 |
her | +0.055 |
site | +0.055 |
ia | +0.048 |
wasteful | +0.048 |
Neg logit contributions | |
mine | -0.068 |
ease | -0.064 |
wherever | -0.063 |
Will | -0.062 |
berry | -0.062 |
Token | down |
Token ID | 866 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
site | +0.197 |
her | +0.194 |
office | +0.186 |
ia | +0.179 |
wasteful | +0.178 |
Neg logit contributions | |
mine | -0.124 |
wherever | -0.124 |
Benny | -0.123 |
Will | -0.122 |
berry | -0.120 |
Token | the |
Token ID | 262 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
mine | +0.024 |
wherever | +0.024 |
Benny | +0.024 |
Will | +0.024 |
berry | +0.023 |
Neg logit contributions | |
site | -0.033 |
her | -0.033 |
office | -0.031 |
ia | -0.030 |
wasteful | -0.030 |
Token | road |
Token ID | 2975 |
Feature activation | +6.38e+00 |
Pos logit contributions | |
ia | +0.014 |
her | +0.014 |
wasteful | +0.014 |
site | +0.014 |
office | +0.014 |
Neg logit contributions | |
wherever | -0.019 |
mine | -0.017 |
Benny | -0.017 |
Hop | -0.017 |
Will | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
her | +0.543 |
site | +0.541 |
wasteful | +0.517 |
ia | +0.512 |
office | +0.512 |
Neg logit contributions | |
wherever | -0.353 |
mine | -0.345 |
Benny | -0.332 |
berry | -0.327 |
Will | -0.323 |
Token | sn |
Token ID | 3013 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
berry | +0.039 |
mine | +0.039 |
superstar | +0.037 |
mattered | +0.037 |
ease | +0.036 |
Neg logit contributions | |
site | -0.046 |
her | -0.045 |
office | -0.042 |
wasteful | -0.039 |
ia | -0.038 |
Token | uck |
Token ID | 1347 |
Feature activation | +7.40e+00 |
Pos logit contributions | |
site | +0.099 |
her | +0.095 |
office | +0.092 |
ia | +0.089 |
wasteful | +0.089 |
Neg logit contributions | |
wherever | -0.073 |
mine | -0.073 |
berry | -0.072 |
Benny | -0.070 |
ease | -0.067 |
Token | into |
Token ID | 656 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
site | +0.592 |
her | +0.581 |
office | +0.542 |
ia | +0.517 |
wasteful | +0.504 |
Neg logit contributions | |
mine | -0.470 |
superstar | -0.467 |
berry | -0.463 |
mattered | -0.454 |
Will | -0.450 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
site | +0.156 |
her | +0.153 |
office | +0.145 |
ia | +0.137 |
wasteful | +0.136 |
Neg logit contributions | |
mine | -0.130 |
berry | -0.126 |
wherever | -0.126 |
mattered | -0.125 |
Benny | -0.124 |
Token | country |
Token ID | 1499 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
her | +0.014 |
site | +0.014 |
ia | +0.014 |
office | +0.012 |
wasteful | +0.012 |
Neg logit contributions | |
wherever | -0.017 |
stuffed | -0.017 |
berry | -0.017 |
Benny | -0.017 |
Will | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
mine | +0.039 |
wherever | +0.038 |
berry | +0.038 |
Benny | +0.038 |
Will | +0.038 |
Neg logit contributions | |
site | -0.046 |
her | -0.045 |
office | -0.043 |
ia | -0.041 |
wasteful | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
mine | +0.004 |
berry | +0.004 |
wherever | +0.004 |
mattered | +0.004 |
superstar | +0.004 |
Neg logit contributions | |
site | -0.005 |
her | -0.005 |
office | -0.005 |
ia | -0.005 |
wasteful | -0.005 |
Token | dangerous |
Token ID | 4923 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
site | +0.145 |
office | +0.130 |
her | +0.119 |
ups | +0.118 |
irens | +0.114 |
Neg logit contributions | |
Benny | -0.160 |
mattered | -0.149 |
Will | -0.146 |
wherever | -0.143 |
mineral | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
site | +0.369 |
her | +0.366 |
office | +0.344 |
ia | +0.324 |
wasteful | +0.323 |
Neg logit contributions | |
mine | -0.330 |
berry | -0.322 |
ease | -0.318 |
mattered | -0.315 |
Grac | -0.315 |
Token | You |
Token ID | 921 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
mine | +0.006 |
wherever | +0.006 |
berry | +0.006 |
ease | +0.006 |
mattered | +0.006 |
Neg logit contributions | |
her | -0.007 |
site | -0.007 |
office | -0.007 |
ia | -0.007 |
wasteful | -0.007 |
Token | could |
Token ID | 714 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
berry | +0.121 |
Nice | +0.118 |
superstar | +0.117 |
mine | +0.113 |
Grac | +0.112 |
Neg logit contributions | |
her | -0.142 |
wasteful | -0.132 |
office | -0.129 |
site | -0.129 |
ia | -0.120 |
Token | have |
Token ID | 423 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
mine | +0.114 |
berry | +0.113 |
superstar | +0.111 |
mattered | +0.110 |
wherever | +0.109 |
Neg logit contributions | |
her | -0.200 |
site | -0.196 |
office | -0.188 |
ia | -0.179 |
wasteful | -0.179 |
Token | been |
Token ID | 587 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
berry | +0.210 |
mine | +0.209 |
superstar | +0.202 |
Nice | +0.197 |
wherever | +0.196 |
Neg logit contributions | |
her | -0.142 |
site | -0.137 |
wasteful | -0.123 |
office | -0.122 |
yourselves | -0.118 |
Token | dead |
Token ID | 2636 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
site | +0.105 |
her | +0.101 |
office | +0.095 |
ia | +0.091 |
wasteful | +0.086 |
Neg logit contributions | |
Benny | -0.122 |
mine | -0.122 |
Will | -0.122 |
wherever | -0.121 |
mattered | -0.121 |
Token | ." |
Token ID | 526 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
site | +0.074 |
her | +0.073 |
office | +0.071 |
wasteful | +0.066 |
yourselves | +0.064 |
Neg logit contributions | |
mine | -0.078 |
ease | -0.075 |
Grac | -0.074 |
berry | -0.073 |
mattered | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
mine | +0.191 |
berry | +0.185 |
wherever | +0.184 |
superstar | +0.182 |
mattered | +0.182 |
Neg logit contributions | |
site | -0.261 |
her | -0.257 |
office | -0.244 |
ia | -0.235 |
wasteful | -0.230 |
Token |
|
Token ID | 198 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
Benny | +0.021 |
wherever | +0.019 |
Will | +0.018 |
berry | +0.018 |
ease | +0.018 |
Neg logit contributions | |
site | -0.045 |
her | -0.043 |
office | -0.043 |
wasteful | -0.042 |
men | -0.039 |
Token | Tim |
Token ID | 14967 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Benny | +0.026 |
berry | +0.022 |
wherever | +0.022 |
Will | +0.021 |
mine | +0.021 |
Neg logit contributions | |
site | -0.042 |
office | -0.040 |
her | -0.040 |
wasteful | -0.036 |
ews | -0.036 |
Token | sters |
Token ID | 5937 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
site | +0.128 |
her | +0.126 |
office | +0.121 |
ia | +0.112 |
ups | +0.107 |
Neg logit contributions | |
mine | -0.198 |
ease | -0.195 |
mattered | -0.194 |
Benny | -0.194 |
superstar | -0.192 |
Token | . |
Token ID | 13 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
her | +0.155 |
site | +0.152 |
office | +0.144 |
ia | +0.132 |
ups | +0.129 |
Neg logit contributions | |
superstar | -0.165 |
Will | -0.164 |
mine | -0.164 |
Benny | -0.162 |
mattered | -0.160 |
Token | She |
Token ID | 1375 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
mine | +0.005 |
berry | +0.005 |
wherever | +0.005 |
Will | +0.005 |
mattered | +0.005 |
Neg logit contributions | |
site | -0.007 |
her | -0.007 |
office | -0.006 |
ia | -0.006 |
wasteful | -0.006 |
Token | took |
Token ID | 1718 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
site | +0.099 |
her | +0.098 |
office | +0.093 |
ia | +0.088 |
wasteful | +0.087 |
Neg logit contributions | |
mine | -0.071 |
wherever | -0.070 |
berry | -0.069 |
Benny | -0.069 |
Will | -0.068 |
Token | the |
Token ID | 262 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
her | +0.036 |
site | +0.034 |
office | +0.032 |
ia | +0.030 |
men | +0.030 |
Neg logit contributions | |
superstar | -0.033 |
mine | -0.032 |
mattered | -0.032 |
Nice | -0.032 |
berry | -0.032 |
Token | oy |
Token ID | 35104 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
site | +0.015 |
her | +0.015 |
office | +0.014 |
ia | +0.013 |
wasteful | +0.013 |
Neg logit contributions | |
mine | -0.014 |
Benny | -0.014 |
wherever | -0.014 |
Will | -0.014 |
berry | -0.013 |
Token | sters |
Token ID | 5937 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
site | +0.132 |
her | +0.129 |
office | +0.123 |
ia | +0.113 |
ups | +0.108 |
Neg logit contributions | |
mine | -0.194 |
Benny | -0.193 |
mattered | -0.192 |
ease | -0.191 |
Will | -0.191 |
Token | back |
Token ID | 736 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
her | +0.168 |
site | +0.166 |
office | +0.158 |
ia | +0.141 |
ups | +0.140 |
Neg logit contributions | |
superstar | -0.153 |
Will | -0.153 |
mattered | -0.150 |
mine | -0.148 |
Benny | -0.148 |
Token | to |
Token ID | 284 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
mine | +0.072 |
wherever | +0.071 |
berry | +0.071 |
Benny | +0.070 |
Will | +0.070 |
Neg logit contributions | |
site | -0.112 |
her | -0.110 |
office | -0.104 |
ia | -0.100 |
wasteful | -0.100 |
Token | her |
Token ID | 607 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
mine | +0.008 |
berry | +0.008 |
mattered | +0.008 |
wherever | +0.008 |
Benny | +0.008 |
Neg logit contributions | |
site | -0.011 |
her | -0.011 |
office | -0.010 |
ia | -0.009 |
wasteful | -0.009 |
Token | kitchen |
Token ID | 9592 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
mine | +0.182 |
berry | +0.177 |
wherever | +0.177 |
Will | +0.177 |
Benny | +0.177 |
Neg logit contributions | |
site | -0.142 |
her | -0.140 |
office | -0.130 |
ia | -0.122 |
wasteful | -0.120 |
Token | , |
Token ID | 11 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
site | +0.140 |
her | +0.132 |
ia | +0.131 |
office | +0.125 |
men | +0.111 |
Neg logit contributions | |
mine | -0.175 |
superstar | -0.174 |
ease | -0.170 |
berry | -0.168 |
hello | -0.164 |
Token | there |
Token ID | 612 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
her | +0.025 |
site | +0.025 |
office | +0.022 |
ia | +0.022 |
wasteful | +0.021 |
Neg logit contributions | |
mine | -0.027 |
berry | -0.026 |
superstar | -0.026 |
ease | -0.026 |
wherever | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
site | +0.012 |
her | +0.011 |
ia | +0.011 |
office | +0.011 |
wasteful | +0.009 |
Neg logit contributions | |
mine | -0.012 |
superstar | -0.012 |
wherever | -0.012 |
Grac | -0.012 |
berry | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
her | +0.050 |
site | +0.046 |
office | +0.043 |
ia | +0.041 |
wasteful | +0.038 |
Neg logit contributions | |
mine | -0.070 |
superstar | -0.067 |
mattered | -0.067 |
berry | -0.067 |
wherever | -0.067 |
Token | charming |
Token ID | 23332 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
site | +0.063 |
her | +0.062 |
office | +0.058 |
ia | +0.055 |
wasteful | +0.054 |
Neg logit contributions | |
mine | -0.067 |
berry | -0.066 |
wherever | -0.065 |
Benny | -0.065 |
Will | -0.065 |
Token | boy |
Token ID | 2933 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
mine | +0.123 |
ease | +0.121 |
mattered | +0.119 |
wherever | +0.119 |
Will | +0.115 |
Neg logit contributions | |
site | -0.116 |
her | -0.112 |
office | -0.109 |
ia | -0.102 |
wasteful | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
her | +0.253 |
site | +0.250 |
office | +0.246 |
ia | +0.223 |
wasteful | +0.213 |
Neg logit contributions | |
ease | -0.255 |
mine | -0.250 |
superstar | -0.243 |
wherever | -0.241 |
Grac | -0.239 |
Token | He |
Token ID | 679 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
mine | +0.003 |
wherever | +0.003 |
mattered | +0.003 |
superstar | +0.003 |
ease | +0.003 |
Neg logit contributions | |
site | -0.002 |
her | -0.002 |
office | -0.002 |
ia | -0.002 |
men | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
her | +0.122 |
site | +0.120 |
office | +0.113 |
ia | +0.111 |
wasteful | +0.106 |
Neg logit contributions | |
mine | -0.073 |
berry | -0.072 |
ease | -0.070 |
wherever | -0.069 |
Grac | -0.068 |
Token | three |
Token ID | 1115 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
site | +0.063 |
her | +0.061 |
office | +0.058 |
ia | +0.055 |
wasteful | +0.054 |
Neg logit contributions | |
mine | -0.057 |
wherever | -0.056 |
Benny | -0.056 |
berry | -0.056 |
Will | -0.056 |
Token | years |
Token ID | 812 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
site | +0.003 |
her | +0.003 |
office | +0.003 |
ia | +0.003 |
wasteful | +0.003 |
Neg logit contributions | |
mine | -0.005 |
wherever | -0.004 |
Benny | -0.004 |
berry | -0.004 |
Will | -0.004 |
Token | led |
Token ID | 992 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
mine | +0.228 |
berry | +0.223 |
wherever | +0.223 |
Benny | +0.222 |
Will | +0.222 |
Neg logit contributions | |
site | -0.282 |
her | -0.279 |
office | -0.262 |
ia | -0.251 |
wasteful | -0.248 |
Token | in |
Token ID | 287 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
her | +0.058 |
site | +0.057 |
office | +0.052 |
ia | +0.050 |
wasteful | +0.049 |
Neg logit contributions | |
mine | -0.052 |
berry | -0.052 |
mattered | -0.050 |
superstar | -0.050 |
Grac | -0.050 |
Token | his |
Token ID | 465 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
mattered | +0.024 |
berry | +0.024 |
mine | +0.024 |
superstar | +0.024 |
Grac | +0.023 |
Neg logit contributions | |
site | -0.030 |
her | -0.029 |
office | -0.027 |
ia | -0.026 |
wasteful | -0.025 |
Token | ears |
Token ID | 11368 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
mine | +0.175 |
wherever | +0.173 |
berry | +0.172 |
Benny | +0.172 |
Will | +0.171 |
Neg logit contributions | |
site | -0.188 |
her | -0.186 |
office | -0.173 |
ia | -0.165 |
wasteful | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
mine | +0.021 |
Benny | +0.021 |
mattered | +0.021 |
Grac | +0.021 |
berry | +0.021 |
Neg logit contributions | |
her | -0.021 |
site | -0.020 |
office | -0.019 |
ia | -0.018 |
ups | -0.017 |
Token | He |
Token ID | 679 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
mine | +0.002 |
berry | +0.002 |
wherever | +0.002 |
mattered | +0.002 |
Benny | +0.002 |
Neg logit contributions | |
site | -0.003 |
her | -0.003 |
office | -0.002 |
ia | -0.002 |
wasteful | -0.002 |
Token | raced |
Token ID | 32897 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
site | +0.108 |
her | +0.107 |
office | +0.099 |
ia | +0.096 |
wasteful | +0.093 |
Neg logit contributions | |
mine | -0.087 |
berry | -0.087 |
wherever | -0.084 |
Benny | -0.084 |
Grac | -0.082 |
Token | back |
Token ID | 736 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
site | +0.037 |
her | +0.037 |
office | +0.034 |
ia | +0.033 |
men | +0.032 |
Neg logit contributions | |
berry | -0.029 |
mattered | -0.029 |
mine | -0.029 |
superstar | -0.028 |
Grac | -0.027 |
Token | home |
Token ID | 1363 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
mine | +0.074 |
berry | +0.072 |
Benny | +0.071 |
Will | +0.071 |
mattered | +0.070 |
Neg logit contributions | |
site | -0.103 |
her | -0.101 |
office | -0.096 |
ia | -0.091 |
wasteful | -0.090 |
Token | and |
Token ID | 290 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
site | +0.024 |
her | +0.024 |
office | +0.022 |
ia | +0.021 |
wasteful | +0.021 |
Neg logit contributions | |
mine | -0.018 |
wherever | -0.018 |
berry | -0.018 |
Benny | -0.018 |
Will | -0.018 |
Token | he |
Token ID | 339 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
berry | +0.037 |
mine | +0.037 |
superstar | +0.034 |
wherever | +0.034 |
Benny | +0.034 |
Neg logit contributions | |
site | -0.046 |
her | -0.045 |
office | -0.043 |
ia | -0.040 |
wasteful | -0.040 |
Token | " |
Token ID | 366 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
her | +0.019 |
site | +0.019 |
office | +0.017 |
ia | +0.016 |
wasteful | +0.015 |
Neg logit contributions | |
ease | -0.026 |
mine | -0.026 |
berry | -0.025 |
mattered | -0.025 |
wherever | -0.025 |
Token | I |
Token ID | 40 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
her | +0.021 |
site | +0.020 |
office | +0.019 |
ia | +0.018 |
ups | +0.018 |
Neg logit contributions | |
wherever | -0.017 |
ease | -0.017 |
berry | -0.016 |
mine | -0.016 |
Benny | -0.016 |
Token | 'm |
Token ID | 1101 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
mine | +0.092 |
berry | +0.091 |
wherever | +0.091 |
ease | +0.088 |
Benny | +0.086 |
Neg logit contributions | |
her | -0.136 |
site | -0.130 |
office | -0.127 |
ia | -0.122 |
wasteful | -0.122 |
Token | trying |
Token ID | 2111 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Benny | +0.211 |
Will | +0.211 |
mine | +0.207 |
wherever | +0.207 |
Grac | +0.204 |
Neg logit contributions | |
site | -0.272 |
her | -0.267 |
office | -0.249 |
ia | -0.247 |
wasteful | -0.239 |
Token | to |
Token ID | 284 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
site | +0.193 |
her | +0.192 |
office | +0.182 |
ia | +0.172 |
wasteful | +0.171 |
Neg logit contributions | |
mine | -0.146 |
berry | -0.139 |
superstar | -0.135 |
Will | -0.134 |
mattered | -0.133 |
Token | get |
Token ID | 651 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
mine | +0.008 |
berry | +0.007 |
wherever | +0.007 |
Will | +0.007 |
Benny | +0.007 |
Neg logit contributions | |
site | -0.012 |
her | -0.012 |
office | -0.011 |
ia | -0.010 |
wasteful | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
her | +0.183 |
site | +0.177 |
office | +0.168 |
wasteful | +0.162 |
ups | +0.152 |
Neg logit contributions | |
mine | -0.193 |
berry | -0.189 |
superstar | -0.185 |
mattered | -0.181 |
wherever | -0.179 |
Token | cr |
Token ID | 1067 |
Feature activation | -7.03e+00 |
Pos logit contributions | |
office | +0.014 |
site | +0.014 |
her | +0.013 |
men | +0.013 |
gate | +0.012 |
Neg logit contributions | |
mine | -0.015 |
berry | -0.015 |
mattered | -0.015 |
Will | -0.014 |
superstar | -0.014 |
Token | ay |
Token ID | 323 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
mine | +0.334 |
berry | +0.324 |
wherever | +0.315 |
Will | +0.314 |
Benny | +0.312 |
Neg logit contributions | |
site | -0.674 |
her | -0.657 |
office | -0.633 |
wasteful | -0.616 |
ia | -0.605 |
Token | ons |
Token ID | 684 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Benny | +0.102 |
superstar | +0.099 |
wherever | +0.099 |
Will | +0.099 |
ease | +0.098 |
Neg logit contributions | |
her | -0.144 |
site | -0.142 |
office | -0.138 |
ia | -0.132 |
ups | -0.125 |
Token | from |
Token ID | 422 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Will | +0.121 |
mine | +0.119 |
berry | +0.119 |
mattered | +0.118 |
superstar | +0.118 |
Neg logit contributions | |
her | -0.129 |
site | -0.126 |
office | -0.120 |
ia | -0.111 |
wasteful | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
Will | +0.019 |
mine | +0.019 |
Benny | +0.019 |
wherever | +0.018 |
berry | +0.018 |
Neg logit contributions | |
site | -0.035 |
her | -0.034 |
office | -0.033 |
wasteful | -0.032 |
ia | -0.031 |
Token | The |
Token ID | 464 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
mine | +0.027 |
Will | +0.026 |
wherever | +0.026 |
Benny | +0.026 |
berry | +0.026 |
Neg logit contributions | |
site | -0.027 |
her | -0.025 |
office | -0.025 |
wasteful | -0.024 |
ia | -0.023 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
site | +0.092 |
her | +0.090 |
office | +0.080 |
wasteful | +0.079 |
ia | +0.079 |
Neg logit contributions | |
Will | -0.112 |
berry | -0.111 |
wherever | -0.111 |
Benny | -0.111 |
mine | -0.110 |
Token | was |
Token ID | 373 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
mine | +0.098 |
berry | +0.096 |
Will | +0.095 |
wherever | +0.095 |
Benny | +0.094 |
Neg logit contributions | |
site | -0.160 |
her | -0.158 |
office | -0.151 |
wasteful | -0.145 |
ia | -0.144 |
Token | shining |
Token ID | 22751 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
site | +0.086 |
her | +0.084 |
office | +0.081 |
ia | +0.079 |
wasteful | +0.078 |
Neg logit contributions | |
mine | -0.034 |
wherever | -0.033 |
Benny | -0.033 |
berry | -0.033 |
Will | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
mine | +0.269 |
berry | +0.261 |
Will | +0.261 |
wherever | +0.260 |
Benny | +0.260 |
Neg logit contributions | |
site | -0.356 |
her | -0.354 |
office | -0.330 |
ia | -0.317 |
wasteful | -0.311 |
Token | the |
Token ID | 262 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
her | +0.027 |
site | +0.027 |
office | +0.025 |
ia | +0.024 |
wasteful | +0.023 |
Neg logit contributions | |
mine | -0.025 |
mattered | -0.024 |
berry | -0.024 |
Will | -0.024 |
superstar | -0.024 |
Token | birds |
Token ID | 10087 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
site | +0.018 |
her | +0.018 |
office | +0.017 |
ia | +0.016 |
wasteful | +0.016 |
Neg logit contributions | |
mine | -0.018 |
berry | -0.017 |
wherever | -0.017 |
Benny | -0.017 |
Will | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
Benny | +0.069 |
mineral | +0.067 |
Nice | +0.066 |
mattered | +0.065 |
Grac | +0.065 |
Neg logit contributions | |
her | -0.092 |
site | -0.086 |
ia | -0.079 |
office | -0.078 |
men | -0.075 |
Token | singing |
Token ID | 13777 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
mine | +0.217 |
wherever | +0.213 |
berry | +0.212 |
Will | +0.210 |
Benny | +0.210 |
Neg logit contributions | |
site | -0.400 |
her | -0.393 |
office | -0.376 |
ia | -0.362 |
wasteful | -0.361 |
Token | , |
Token ID | 11 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
mine | +0.340 |
mattered | +0.330 |
berry | +0.327 |
ease | +0.322 |
Benny | +0.321 |
Neg logit contributions | |
her | -0.297 |
site | -0.289 |
office | -0.263 |
ia | -0.258 |
men | -0.243 |
Token | , |
Token ID | 11 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
mine | +0.591 |
superstar | +0.582 |
Will | +0.578 |
berry | +0.576 |
ease | +0.574 |
Neg logit contributions | |
her | -0.554 |
site | -0.542 |
office | -0.523 |
ia | -0.511 |
wasteful | -0.485 |
Token | we |
Token ID | 356 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
office | +0.017 |
ia | +0.016 |
her | +0.016 |
wasteful | +0.015 |
site | +0.015 |
Neg logit contributions | |
mine | -0.027 |
ease | -0.026 |
berry | -0.026 |
hello | -0.026 |
superstar | -0.025 |
Token | can |
Token ID | 460 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
berry | +0.063 |
Nice | +0.062 |
mine | +0.061 |
superstar | +0.061 |
Grac | +0.060 |
Neg logit contributions | |
her | -0.076 |
wasteful | -0.073 |
office | -0.069 |
site | -0.064 |
ia | -0.063 |
Token | make |
Token ID | 787 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
superstar | +0.226 |
mattered | +0.224 |
mine | +0.223 |
Nice | +0.222 |
wherever | +0.221 |
Neg logit contributions | |
her | -0.319 |
site | -0.304 |
office | -0.292 |
ia | -0.278 |
wasteful | -0.270 |
Token | another |
Token ID | 1194 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
site | +0.052 |
her | +0.050 |
office | +0.047 |
ia | +0.046 |
wasteful | +0.045 |
Neg logit contributions | |
Benny | -0.045 |
Will | -0.045 |
berry | -0.044 |
mine | -0.044 |
wherever | -0.044 |
Token | cake |
Token ID | 12187 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
site | +0.034 |
her | +0.033 |
office | +0.032 |
ia | +0.030 |
wasteful | +0.029 |
Neg logit contributions | |
mine | -0.034 |
Benny | -0.033 |
Will | -0.033 |
wherever | -0.033 |
berry | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
mine | +0.045 |
wherever | +0.044 |
berry | +0.044 |
Will | +0.044 |
Benny | +0.044 |
Neg logit contributions | |
site | -0.064 |
her | -0.063 |
office | -0.059 |
wasteful | -0.057 |
ia | -0.057 |
Token | But |
Token ID | 887 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
mine | +0.006 |
berry | +0.006 |
ease | +0.006 |
mattered | +0.006 |
wherever | +0.006 |
Neg logit contributions | |
her | -0.007 |
site | -0.006 |
office | -0.006 |
ia | -0.006 |
wasteful | -0.006 |
Token | this |
Token ID | 428 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
mine | +0.064 |
berry | +0.062 |
wherever | +0.062 |
Benny | +0.062 |
Will | +0.061 |
Neg logit contributions | |
site | -0.059 |
her | -0.058 |
office | -0.054 |
ia | -0.051 |
wasteful | -0.051 |
Token | time |
Token ID | 640 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
site | +0.024 |
her | +0.023 |
office | +0.022 |
ia | +0.021 |
wasteful | +0.021 |
Neg logit contributions | |
mine | -0.024 |
berry | -0.023 |
wherever | -0.023 |
mattered | -0.023 |
Will | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
site | +0.145 |
her | +0.141 |
office | +0.139 |
ia | +0.134 |
wasteful | +0.131 |
Neg logit contributions | |
mine | -0.162 |
berry | -0.154 |
superstar | -0.153 |
ease | -0.152 |
Benny | -0.149 |
Token | After |
Token ID | 3260 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
mine | +0.038 |
berry | +0.038 |
Will | +0.038 |
wherever | +0.037 |
Benny | +0.037 |
Neg logit contributions | |
her | -0.027 |
site | -0.026 |
office | -0.023 |
ia | -0.023 |
wasteful | -0.022 |
Token | that |
Token ID | 326 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
site | +0.347 |
her | +0.335 |
office | +0.324 |
ia | +0.301 |
men | +0.283 |
Neg logit contributions | |
mine | -0.384 |
berry | -0.366 |
mattered | -0.358 |
superstar | -0.355 |
wherever | -0.350 |
Token | , |
Token ID | 11 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
site | +0.295 |
her | +0.281 |
office | +0.278 |
ia | +0.258 |
wasteful | +0.248 |
Neg logit contributions | |
mine | -0.263 |
berry | -0.257 |
ease | -0.255 |
Will | -0.254 |
Benny | -0.249 |
Token | Daisy |
Token ID | 40355 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
site | +0.025 |
her | +0.025 |
ia | +0.024 |
wasteful | +0.023 |
office | +0.023 |
Neg logit contributions | |
mine | -0.017 |
berry | -0.016 |
superstar | -0.015 |
hello | -0.015 |
tie | -0.015 |
Token | decided |
Token ID | 3066 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
mine | +0.399 |
wherever | +0.389 |
Benny | +0.386 |
berry | +0.385 |
mattered | +0.384 |
Neg logit contributions | |
her | -0.537 |
site | -0.536 |
office | -0.507 |
ia | -0.487 |
wasteful | -0.468 |
Token | it |
Token ID | 340 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
mine | +0.026 |
berry | +0.025 |
Benny | +0.025 |
wherever | +0.025 |
Will | +0.025 |
Neg logit contributions | |
site | -0.040 |
her | -0.040 |
office | -0.038 |
ia | -0.036 |
wasteful | -0.036 |
Token | was |
Token ID | 373 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
mine | +0.064 |
berry | +0.063 |
Benny | +0.061 |
Will | +0.061 |
superstar | +0.060 |
Neg logit contributions | |
her | -0.077 |
site | -0.074 |
office | -0.071 |
ia | -0.069 |
ups | -0.066 |
Token | time |
Token ID | 640 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
her | +0.047 |
site | +0.046 |
office | +0.043 |
ia | +0.041 |
wasteful | +0.040 |
Neg logit contributions | |
mine | -0.063 |
berry | -0.062 |
Will | -0.061 |
superstar | -0.060 |
Benny | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
site | +0.180 |
her | +0.178 |
office | +0.168 |
ia | +0.161 |
wasteful | +0.160 |
Neg logit contributions | |
mine | -0.128 |
berry | -0.125 |
Benny | -0.125 |
wherever | -0.125 |
Will | -0.124 |
Token | go |
Token ID | 467 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
mine | +0.009 |
berry | +0.009 |
mattered | +0.009 |
Will | +0.009 |
Benny | +0.009 |
Neg logit contributions | |
site | -0.010 |
her | -0.010 |
office | -0.010 |
ia | -0.009 |
wasteful | -0.009 |
Token | home |
Token ID | 1363 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
site | +0.327 |
her | +0.322 |
office | +0.313 |
ia | +0.290 |
wasteful | +0.280 |
Neg logit contributions | |
mine | -0.246 |
mattered | -0.239 |
Will | -0.239 |
berry | -0.237 |
Benny | -0.235 |
Token | started |
Token ID | 2067 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
mine | +0.042 |
berry | +0.041 |
superstar | +0.039 |
wherever | +0.039 |
mattered | +0.038 |
Neg logit contributions | |
site | -0.049 |
her | -0.049 |
office | -0.046 |
wasteful | -0.043 |
ia | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
site | +0.093 |
her | +0.090 |
office | +0.088 |
ia | +0.079 |
ups | +0.078 |
Neg logit contributions | |
mine | -0.080 |
superstar | -0.076 |
berry | -0.075 |
mattered | -0.075 |
Benny | -0.073 |
Token | play |
Token ID | 711 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
superstar | +0.009 |
mine | +0.009 |
mattered | +0.009 |
berry | +0.009 |
Nice | +0.009 |
Neg logit contributions | |
site | -0.010 |
her | -0.010 |
office | -0.009 |
mistake | -0.008 |
ia | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
mine | +0.303 |
mattered | +0.294 |
berry | +0.291 |
Will | +0.290 |
're | +0.289 |
Neg logit contributions | |
site | -0.328 |
her | -0.306 |
office | -0.293 |
ia | -0.264 |
men | -0.252 |
Token | it |
Token ID | 340 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
superstar | +0.097 |
mine | +0.096 |
berry | +0.093 |
mattered | +0.091 |
Nice | +0.090 |
Neg logit contributions | |
site | -0.116 |
her | -0.112 |
office | -0.104 |
ia | -0.099 |
men | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
mine | +0.077 |
berry | +0.073 |
superstar | +0.073 |
Will | +0.073 |
Grac | +0.072 |
Neg logit contributions | |
her | -0.063 |
site | -0.062 |
office | -0.057 |
ia | -0.055 |
wasteful | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
Benny | +0.004 |
Will | +0.004 |
wherever | +0.004 |
mine | +0.004 |
ease | +0.004 |
Neg logit contributions | |
site | -0.010 |
her | -0.009 |
office | -0.009 |
wasteful | -0.009 |
ia | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
Will | +0.020 |
Benny | +0.019 |
wherever | +0.019 |
mine | +0.019 |
ease | +0.018 |
Neg logit contributions | |
site | -0.045 |
wasteful | -0.044 |
office | -0.043 |
her | -0.043 |
ia | -0.040 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +7.81e+00 |
Pos logit contributions | |
mine | +0.030 |
wherever | +0.030 |
Benny | +0.029 |
Will | +0.029 |
whenever | +0.029 |
Neg logit contributions | |
site | -0.032 |
office | -0.030 |
wasteful | -0.029 |
ia | -0.028 |
her | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
site | +0.650 |
her | +0.646 |
office | +0.607 |
ia | +0.582 |
wasteful | +0.580 |
Neg logit contributions | |
mine | -0.461 |
Benny | -0.459 |
Will | -0.456 |
wherever | -0.454 |
berry | -0.452 |
Token | he |
Token ID | 339 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
site | +0.025 |
her | +0.025 |
office | +0.023 |
ia | +0.022 |
wasteful | +0.022 |
Neg logit contributions | |
mine | -0.019 |
berry | -0.018 |
wherever | -0.018 |
Benny | -0.018 |
Will | -0.018 |
Token | supply |
Token ID | 5127 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
mattered | +0.006 |
berry | +0.006 |
superstar | +0.006 |
wherever | +0.006 |
mine | +0.006 |
Neg logit contributions | |
site | -0.012 |
her | -0.012 |
office | -0.012 |
ia | -0.011 |
wasteful | -0.010 |
Token | food |
Token ID | 2057 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
Benny | +0.009 |
wherever | +0.009 |
Will | +0.009 |
berry | +0.009 |
mine | +0.009 |
Neg logit contributions | |
site | -0.014 |
her | -0.014 |
office | -0.013 |
wasteful | -0.013 |
ia | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
site | +0.044 |
her | +0.043 |
office | +0.041 |
ia | +0.039 |
wasteful | +0.039 |
Neg logit contributions | |
mine | -0.032 |
berry | -0.032 |
Will | -0.031 |
Benny | -0.031 |
wherever | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
mine | +0.008 |
berry | +0.008 |
wherever | +0.008 |
Benny | +0.008 |
Will | +0.008 |
Neg logit contributions | |
site | -0.012 |
her | -0.012 |
office | -0.011 |
ia | -0.010 |
wasteful | -0.010 |
Token | animals |
Token ID | 4695 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
site | +0.014 |
her | +0.014 |
office | +0.013 |
ia | +0.012 |
wasteful | +0.012 |
Neg logit contributions | |
wherever | -0.013 |
berry | -0.013 |
mine | -0.013 |
Will | -0.013 |
Benny | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
her | +0.074 |
site | +0.073 |
office | +0.070 |
wasteful | +0.061 |
ups | +0.060 |
Neg logit contributions | |
superstar | -0.087 |
mine | -0.085 |
ease | -0.084 |
Will | -0.082 |
Grac | -0.082 |
Token | the |
Token ID | 262 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
mine | +0.028 |
berry | +0.028 |
Benny | +0.027 |
wherever | +0.027 |
Will | +0.027 |
Neg logit contributions | |
site | -0.035 |
her | -0.034 |
office | -0.033 |
ia | -0.031 |
wasteful | -0.031 |
Token | forest |
Token ID | 8222 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
site | +0.014 |
her | +0.013 |
ia | +0.013 |
wasteful | +0.012 |
office | +0.012 |
Neg logit contributions | |
Benny | -0.013 |
berry | -0.013 |
wherever | -0.013 |
Will | -0.013 |
mine | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
site | +0.086 |
her | +0.086 |
office | +0.079 |
wasteful | +0.079 |
ia | +0.079 |
Neg logit contributions | |
wherever | -0.058 |
mine | -0.056 |
berry | -0.055 |
mattered | -0.055 |
Will | -0.053 |
Token | Every |
Token ID | 3887 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
mine | +0.005 |
Will | +0.005 |
berry | +0.005 |
wherever | +0.005 |
Benny | +0.005 |
Neg logit contributions | |
site | -0.008 |
her | -0.008 |
office | -0.008 |
wasteful | -0.007 |
ia | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
wherever | +0.071 |
Benny | +0.070 |
Will | +0.070 |
berry | +0.070 |
mine | +0.069 |
Neg logit contributions | |
site | -0.168 |
her | -0.168 |
office | -0.158 |
wasteful | -0.157 |
ia | -0.152 |
Token | right |
Token ID | 826 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
mine | +0.306 |
berry | +0.300 |
wherever | +0.299 |
Benny | +0.298 |
Will | +0.298 |
Neg logit contributions | |
site | -0.331 |
her | -0.327 |
office | -0.307 |
ia | -0.291 |
wasteful | -0.289 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
site | +0.011 |
her | +0.011 |
office | +0.011 |
wasteful | +0.010 |
ia | +0.010 |
Neg logit contributions | |
wherever | -0.008 |
mine | -0.008 |
Will | -0.008 |
mattered | -0.008 |
Benny | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
stuffed | +0.019 |
superstar | +0.019 |
mattered | +0.019 |
mine | +0.018 |
wherever | +0.018 |
Neg logit contributions | |
site | -0.023 |
her | -0.022 |
ia | -0.022 |
office | -0.021 |
men | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
mine | +0.026 |
Benny | +0.025 |
berry | +0.025 |
wherever | +0.025 |
Will | +0.025 |
Neg logit contributions | |
site | -0.034 |
her | -0.034 |
office | -0.032 |
wasteful | -0.030 |
ia | -0.030 |
Token | Joe |
Token ID | 19585 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
mine | +0.026 |
berry | +0.026 |
wherever | +0.026 |
Benny | +0.026 |
Will | +0.026 |
Neg logit contributions | |
site | -0.033 |
her | -0.032 |
office | -0.030 |
ia | -0.029 |
wasteful | -0.029 |
Token | smiled |
Token ID | 13541 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
wherever | +0.019 |
Benny | +0.019 |
Grac | +0.019 |
mine | +0.019 |
berry | +0.019 |
Neg logit contributions | |
her | -0.030 |
site | -0.030 |
ia | -0.028 |
office | -0.028 |
ups | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
mine | +0.452 |
berry | +0.432 |
mattered | +0.431 |
ease | +0.430 |
Will | +0.424 |
Neg logit contributions | |
her | -0.419 |
site | -0.407 |
office | -0.388 |
ia | -0.372 |
wasteful | -0.347 |
Token | said |
Token ID | 531 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
berry | +0.041 |
mine | +0.040 |
wherever | +0.038 |
ease | +0.038 |
Will | +0.037 |
Neg logit contributions | |
her | -0.044 |
site | -0.043 |
office | -0.041 |
ia | -0.040 |
wasteful | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
site | +0.167 |
her | +0.158 |
ia | +0.155 |
office | +0.155 |
men | +0.140 |
Neg logit contributions | |
mine | -0.193 |
berry | -0.193 |
ease | -0.186 |
superstar | -0.182 |
berries | -0.181 |
Token | " |
Token ID | 366 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
her | +0.020 |
site | +0.020 |
office | +0.018 |
ia | +0.017 |
wasteful | +0.015 |
Neg logit contributions | |
mattered | -0.029 |
ease | -0.029 |
mine | -0.029 |
berry | -0.029 |
Benny | -0.028 |
Token | Thank |
Token ID | 10449 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
her | +0.021 |
site | +0.017 |
ups | +0.017 |
Meanwhile | +0.017 |
Soon | +0.017 |
Neg logit contributions | |
stuffed | -0.022 |
berry | -0.021 |
Benny | -0.020 |
berries | -0.020 |
mine | -0.020 |
Token | When |
Token ID | 2215 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
mine | +0.028 |
Will | +0.028 |
Benny | +0.028 |
wherever | +0.027 |
berry | +0.027 |
Neg logit contributions | |
site | -0.027 |
her | -0.025 |
office | -0.024 |
wasteful | -0.023 |
ia | -0.023 |
Token | she |
Token ID | 673 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
site | +0.373 |
her | +0.363 |
office | +0.349 |
ia | +0.333 |
wasteful | +0.325 |
Neg logit contributions | |
mine | -0.286 |
berry | -0.278 |
wherever | -0.273 |
mattered | -0.272 |
superstar | -0.269 |
Token | got |
Token ID | 1392 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
mine | +0.056 |
wherever | +0.055 |
Benny | +0.054 |
berry | +0.054 |
mattered | +0.054 |
Neg logit contributions | |
site | -0.076 |
her | -0.076 |
office | -0.071 |
ia | -0.069 |
wasteful | -0.066 |
Token | to |
Token ID | 284 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
site | +0.158 |
her | +0.156 |
office | +0.148 |
ia | +0.141 |
wasteful | +0.140 |
Neg logit contributions | |
mine | -0.115 |
berry | -0.112 |
wherever | -0.112 |
Benny | -0.112 |
Will | -0.112 |
Token | the |
Token ID | 262 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
mine | +0.005 |
berry | +0.005 |
mattered | +0.004 |
wherever | +0.004 |
Will | +0.004 |
Neg logit contributions | |
site | -0.006 |
her | -0.006 |
office | -0.005 |
ia | -0.005 |
wasteful | -0.005 |
Token | television |
Token ID | 5581 |
Feature activation | -7.36e+00 |
Pos logit contributions | |
site | +0.018 |
her | +0.018 |
ia | +0.017 |
wasteful | +0.016 |
ups | +0.016 |
Neg logit contributions | |
berry | -0.018 |
wherever | -0.018 |
Benny | -0.018 |
Will | -0.018 |
stuffed | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
mine | +0.467 |
Benny | +0.456 |
wherever | +0.456 |
berry | +0.456 |
Will | +0.455 |
Neg logit contributions | |
site | -0.582 |
her | -0.571 |
office | -0.543 |
ia | -0.512 |
wasteful | -0.502 |
Token | she |
Token ID | 673 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
site | +0.030 |
her | +0.029 |
office | +0.029 |
ia | +0.027 |
wasteful | +0.026 |
Neg logit contributions | |
mine | -0.024 |
berry | -0.024 |
superstar | -0.023 |
ease | -0.023 |
mattered | -0.022 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
mine | +0.055 |
Will | +0.054 |
berry | +0.054 |
Benny | +0.054 |
wherever | +0.053 |
Neg logit contributions | |
site | -0.076 |
her | -0.074 |
office | -0.070 |
ia | -0.068 |
wasteful | -0.067 |
Token | a |
Token ID | 257 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
site | +0.152 |
her | +0.150 |
office | +0.140 |
ia | +0.132 |
wasteful | +0.131 |
Neg logit contributions | |
mine | -0.155 |
berry | -0.152 |
wherever | -0.152 |
Benny | -0.151 |
Will | -0.151 |
Token | scary |
Token ID | 14343 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
site | +0.060 |
her | +0.058 |
office | +0.055 |
wasteful | +0.049 |
ia | +0.049 |
Neg logit contributions | |
mine | -0.075 |
wherever | -0.071 |
ease | -0.071 |
mattered | -0.071 |
berry | -0.071 |
Token | nods |
Token ID | 34833 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
site | +0.334 |
her | +0.331 |
office | +0.311 |
ia | +0.298 |
wasteful | +0.291 |
Neg logit contributions | |
mine | -0.307 |
wherever | -0.302 |
berry | -0.300 |
Benny | -0.300 |
Will | -0.299 |
Token | and |
Token ID | 290 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
mine | +0.216 |
berry | +0.212 |
mattered | +0.211 |
Benny | +0.211 |
wherever | +0.210 |
Neg logit contributions | |
site | -0.234 |
her | -0.233 |
office | -0.220 |
ia | -0.213 |
wasteful | -0.203 |
Token | says |
Token ID | 1139 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
mine | +0.056 |
Benny | +0.055 |
Will | +0.055 |
berry | +0.055 |
wherever | +0.055 |
Neg logit contributions | |
site | -0.035 |
her | -0.034 |
office | -0.031 |
ia | -0.029 |
wasteful | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
ia | +0.314 |
site | +0.307 |
her | +0.293 |
office | +0.283 |
men | +0.264 |
Neg logit contributions | |
mine | -0.441 |
ease | -0.432 |
berry | -0.431 |
superstar | -0.420 |
| | -0.415 |
Token | " |
Token ID | 366 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
site | +0.016 |
her | +0.016 |
office | +0.015 |
ia | +0.014 |
wasteful | +0.013 |
Neg logit contributions | |
mine | -0.026 |
ease | -0.026 |
mattered | -0.026 |
berry | -0.025 |
Benny | -0.024 |
Token | Yes |
Token ID | 5297 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
her | +0.023 |
site | +0.021 |
ia | +0.020 |
ups | +0.020 |
wasteful | +0.020 |
Neg logit contributions | |
ease | -0.014 |
berry | -0.013 |
mine | -0.013 |
stuffed | -0.013 |
Benny | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
mine | +0.382 |
berry | +0.373 |
wherever | +0.372 |
Benny | +0.371 |
Will | +0.371 |
Neg logit contributions | |
site | -0.485 |
her | -0.478 |
office | -0.452 |
ia | -0.434 |
wasteful | -0.427 |
Token | please |
Token ID | 3387 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
site | +0.021 |
her | +0.021 |
office | +0.021 |
ia | +0.020 |
wasteful | +0.019 |
Neg logit contributions | |
mine | -0.022 |
ease | -0.022 |
wherever | -0.022 |
mattered | -0.021 |
berry | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
site | +0.130 |
her | +0.128 |
office | +0.120 |
wasteful | +0.116 |
ia | +0.113 |
Neg logit contributions | |
wherever | -0.090 |
Will | -0.089 |
mine | -0.089 |
Benny | -0.088 |
berry | -0.088 |
Token | I |
Token ID | 314 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
mine | +0.007 |
ease | +0.007 |
mattered | +0.007 |
superstar | +0.006 |
berry | +0.006 |
Neg logit contributions | |
office | -0.006 |
site | -0.006 |
her | -0.006 |
ia | -0.006 |
yourselves | -0.005 |
Token | like |
Token ID | 588 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
mine | +0.131 |
berry | +0.128 |
Benny | +0.127 |
Grac | +0.124 |
Will | +0.122 |
Neg logit contributions | |
her | -0.181 |
site | -0.175 |
office | -0.170 |
ia | -0.163 |
wasteful | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
site | +0.274 |
her | +0.267 |
office | +0.250 |
ia | +0.235 |
wasteful | +0.226 |
Neg logit contributions | |
mine | -0.301 |
Benny | -0.290 |
Will | -0.290 |
Grac | -0.286 |
superstar | -0.286 |
Token | It |
Token ID | 632 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Benny | +0.004 |
Will | +0.004 |
berry | +0.004 |
Grac | +0.004 |
mine | +0.004 |
Neg logit contributions | |
site | -0.007 |
her | -0.007 |
office | -0.007 |
wasteful | -0.006 |
ia | -0.006 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
mine | +0.073 |
wherever | +0.071 |
berry | +0.070 |
ease | +0.070 |
superstar | +0.068 |
Neg logit contributions | |
her | -0.081 |
site | -0.080 |
ia | -0.073 |
office | -0.071 |
wasteful | -0.066 |
Token | like |
Token ID | 588 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
mine | +0.009 |
berry | +0.009 |
Will | +0.009 |
superstar | +0.009 |
mattered | +0.008 |
Neg logit contributions | |
her | -0.011 |
site | -0.011 |
wasteful | -0.010 |
office | -0.010 |
ia | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
mine | +0.256 |
berry | +0.242 |
superstar | +0.231 |
mattered | +0.229 |
wherever | +0.227 |
Neg logit contributions | |
site | -0.194 |
her | -0.191 |
office | -0.178 |
ia | -0.169 |
men | -0.163 |
Token | ruby |
Token ID | 43506 |
Feature activation | -7.99e+00 |
Pos logit contributions | |
site | +0.065 |
her | +0.063 |
office | +0.060 |
ia | +0.058 |
wasteful | +0.055 |
Neg logit contributions | |
mine | -0.062 |
ease | -0.056 |
berry | -0.055 |
mattered | -0.054 |
wherever | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
mine | +0.571 |
Will | +0.558 |
Benny | +0.554 |
ease | +0.553 |
Grac | +0.546 |
Neg logit contributions | |
site | -0.570 |
her | -0.564 |
office | -0.533 |
ia | -0.514 |
wasteful | -0.466 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
Benny | +0.004 |
Will | +0.004 |
Grac | +0.004 |
berry | +0.004 |
mine | +0.004 |
Neg logit contributions | |
site | -0.008 |
her | -0.007 |
office | -0.007 |
wasteful | -0.007 |
ia | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
mine | +0.019 |
wherever | +0.018 |
berry | +0.018 |
ease | +0.018 |
superstar | +0.018 |
Neg logit contributions | |
her | -0.024 |
site | -0.024 |
office | -0.023 |
ia | -0.022 |
wasteful | -0.021 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
mine | +0.049 |
berry | +0.049 |
wherever | +0.049 |
Benny | +0.048 |
Will | +0.048 |
Neg logit contributions | |
site | -0.040 |
her | -0.039 |
office | -0.037 |
ia | -0.035 |
wasteful | -0.034 |
Token | were |
Token ID | 547 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
her | +0.162 |
site | +0.147 |
ia | +0.140 |
wasteful | +0.135 |
men | +0.133 |
Neg logit contributions | |
berry | -0.144 |
superstar | -0.143 |
wherever | -0.141 |
Nice | -0.140 |
Benny | -0.134 |
Token | funny |
Token ID | 8258 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
her | +0.052 |
site | +0.052 |
office | +0.047 |
ia | +0.046 |
wasteful | +0.046 |
Neg logit contributions | |
mine | -0.062 |
berry | -0.060 |
wherever | -0.058 |
Will | -0.058 |
superstar | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
mine | +0.069 |
ease | +0.065 |
berry | +0.064 |
Grac | +0.064 |
wherever | +0.063 |
Neg logit contributions | |
site | -0.055 |
her | -0.053 |
office | -0.051 |
ia | -0.050 |
ups | -0.046 |
Token | He |
Token ID | 679 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
mine | +0.004 |
Benny | +0.004 |
Will | +0.004 |
berry | +0.004 |
wherever | +0.004 |
Neg logit contributions | |
site | -0.007 |
her | -0.007 |
office | -0.006 |
wasteful | -0.006 |
ia | -0.006 |
Token | laughed |
Token ID | 13818 |
Feature activation | -6.13e+00 |
Pos logit contributions | |
her | +0.105 |
site | +0.102 |
ia | +0.096 |
office | +0.095 |
wasteful | +0.091 |
Neg logit contributions | |
wherever | -0.082 |
mine | -0.082 |
berry | -0.080 |
ease | -0.079 |
Grac | -0.078 |
Token | and |
Token ID | 290 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
mine | +0.484 |
berry | +0.475 |
ease | +0.469 |
mattered | +0.469 |
Grac | +0.463 |
Neg logit contributions | |
her | -0.400 |
site | -0.383 |
office | -0.348 |
ia | -0.342 |
wasteful | -0.323 |
Token | laughed |
Token ID | 13818 |
Feature activation | -6.13e+00 |
Pos logit contributions | |
berry | +0.044 |
mine | +0.043 |
wherever | +0.041 |
ease | +0.040 |
berries | +0.040 |
Neg logit contributions | |
her | -0.044 |
site | -0.044 |
ia | -0.040 |
wasteful | -0.040 |
office | -0.039 |
Token | as |
Token ID | 355 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
mine | +0.491 |
berry | +0.484 |
mattered | +0.473 |
ease | +0.472 |
Grac | +0.465 |
Neg logit contributions | |
her | -0.390 |
site | -0.376 |
ia | -0.332 |
office | -0.332 |
men | -0.309 |
Token | he |
Token ID | 339 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
site | +0.133 |
her | +0.131 |
ia | +0.124 |
office | +0.123 |
wasteful | +0.118 |
Neg logit contributions | |
mine | -0.097 |
berry | -0.095 |
wherever | -0.090 |
Grac | -0.089 |
mattered | -0.088 |
Token | continued |
Token ID | 3767 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
mine | +0.078 |
wherever | +0.077 |
Benny | +0.075 |
Grac | +0.075 |
berry | +0.075 |
Neg logit contributions | |
her | -0.108 |
site | -0.108 |
office | -0.100 |
ia | -0.100 |
wasteful | -0.094 |
Token | to |
Token ID | 284 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
mine | +0.027 |
superstar | +0.026 |
berry | +0.026 |
mattered | +0.026 |
Benny | +0.026 |
Neg logit contributions | |
site | -0.033 |
office | -0.031 |
her | -0.031 |
ia | -0.028 |
men | -0.027 |
Token | repeat |
Token ID | 9585 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Grac | +0.006 |
superstar | +0.006 |
mattered | +0.006 |
Nice | +0.006 |
Benny | +0.006 |
Neg logit contributions | |
site | -0.011 |
office | -0.011 |
her | -0.010 |
ia | -0.010 |
mistake | -0.009 |