Token | a |
Token ID | 257 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
Penny | +0.027 |
Bruce | +0.027 |
Cindy | +0.027 |
Lilly | +0.025 |
Emmy | +0.025 |
Neg logit contributions | |
we | -0.035 |
bel | -0.029 |
ep | -0.029 |
men | -0.029 |
anas | -0.028 |
Token | big |
Token ID | 1263 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
Bruce | +0.030 |
Penny | +0.030 |
Cindy | +0.029 |
Lilly | +0.029 |
Emmy | +0.029 |
Neg logit contributions | |
we | -0.017 |
ep | -0.016 |
bel | -0.014 |
ilot | -0.014 |
men | -0.014 |
Token | bottle |
Token ID | 9294 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
Bruce | +0.001 |
Penny | +0.001 |
Cindy | +0.001 |
Sophie | +0.001 |
Emmy | +0.001 |
Neg logit contributions | |
ep | -0.001 |
song | -0.000 |
ilot | -0.000 |
ney | -0.000 |
songs | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Bruce | +0.163 |
Penny | +0.162 |
Cindy | +0.157 |
Emmy | +0.153 |
Lilly | +0.152 |
Neg logit contributions | |
we | -0.142 |
ep | -0.128 |
bel | -0.118 |
men | -0.114 |
ilot | -0.113 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
songs | +0.039 |
we | +0.037 |
ep | +0.037 |
song | +0.035 |
ity | +0.033 |
Neg logit contributions | |
Bruce | -0.051 |
Harriet | -0.049 |
Penny | -0.047 |
Sophie | -0.047 |
Emmy | -0.047 |
Token | ion |
Token ID | 295 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
Bruce | +0.053 |
Cindy | +0.051 |
Penny | +0.051 |
Emmy | +0.050 |
Harriet | +0.050 |
Neg logit contributions | |
we | -0.049 |
ep | -0.044 |
as | -0.043 |
men | -0.042 |
ney | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
Bruce | +0.296 |
Penny | +0.296 |
Cindy | +0.288 |
Emmy | +0.284 |
Lilly | +0.282 |
Neg logit contributions | |
we | -0.228 |
ep | -0.186 |
men | -0.178 |
bel | -0.173 |
angels | -0.165 |
Token | The |
Token ID | 383 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
Penny | +0.020 |
Bruce | +0.020 |
Cindy | +0.019 |
Lilly | +0.019 |
Emmy | +0.019 |
Neg logit contributions | |
we | -0.022 |
ep | -0.020 |
bel | -0.019 |
men | -0.018 |
ilot | -0.018 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Bruce | +0.016 |
Penny | +0.016 |
Cindy | +0.016 |
Emmy | +0.015 |
Lilly | +0.015 |
Neg logit contributions | |
we | -0.015 |
ep | -0.013 |
bel | -0.012 |
men | -0.012 |
ilot | -0.012 |
Token | ion |
Token ID | 295 |
Feature activation | +5.90e+00 |
Pos logit contributions | |
Bruce | +0.041 |
Penny | +0.039 |
Cindy | +0.038 |
Emmy | +0.037 |
Harriet | +0.036 |
Neg logit contributions | |
we | -0.057 |
ep | -0.053 |
men | -0.049 |
bel | -0.048 |
ilot | -0.047 |
Token | was |
Token ID | 373 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
Bruce | +0.297 |
Penny | +0.292 |
Cindy | +0.288 |
Emmy | +0.282 |
Lilly | +0.278 |
Neg logit contributions | |
we | -0.220 |
ep | -0.184 |
men | -0.170 |
bel | -0.164 |
ney | -0.158 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
songs | +0.039 |
we | +0.037 |
ep | +0.037 |
song | +0.035 |
ity | +0.033 |
Neg logit contributions | |
Bruce | -0.051 |
Harriet | -0.049 |
Penny | -0.047 |
Sophie | -0.047 |
Emmy | -0.047 |
Token | ion |
Token ID | 295 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
Bruce | +0.053 |
Cindy | +0.051 |
Penny | +0.051 |
Emmy | +0.050 |
Harriet | +0.050 |
Neg logit contributions | |
we | -0.049 |
ep | -0.044 |
as | -0.043 |
men | -0.042 |
ney | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
Bruce | +0.296 |
Penny | +0.296 |
Cindy | +0.288 |
Emmy | +0.284 |
Lilly | +0.282 |
Neg logit contributions | |
we | -0.228 |
ep | -0.186 |
men | -0.178 |
bel | -0.173 |
angels | -0.165 |
Token | The |
Token ID | 383 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
Penny | +0.020 |
Bruce | +0.020 |
Cindy | +0.019 |
Lilly | +0.019 |
Emmy | +0.019 |
Neg logit contributions | |
we | -0.022 |
ep | -0.020 |
bel | -0.019 |
men | -0.018 |
ilot | -0.018 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Bruce | +0.016 |
Penny | +0.016 |
Cindy | +0.016 |
Emmy | +0.015 |
Lilly | +0.015 |
Neg logit contributions | |
we | -0.015 |
ep | -0.013 |
bel | -0.012 |
men | -0.012 |
ilot | -0.012 |
Token | ion |
Token ID | 295 |
Feature activation | +5.90e+00 |
Pos logit contributions | |
Bruce | +0.041 |
Penny | +0.039 |
Cindy | +0.038 |
Emmy | +0.037 |
Harriet | +0.036 |
Neg logit contributions | |
we | -0.057 |
ep | -0.053 |
men | -0.049 |
bel | -0.048 |
ilot | -0.047 |
Token | was |
Token ID | 373 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
Bruce | +0.297 |
Penny | +0.292 |
Cindy | +0.288 |
Emmy | +0.282 |
Lilly | +0.278 |
Neg logit contributions | |
we | -0.220 |
ep | -0.184 |
men | -0.170 |
bel | -0.164 |
ney | -0.158 |
Token | for |
Token ID | 329 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Bruce | +0.041 |
Penny | +0.040 |
Cindy | +0.039 |
Emmy | +0.038 |
Lilly | +0.038 |
Neg logit contributions | |
we | -0.029 |
ep | -0.026 |
bel | -0.024 |
men | -0.023 |
ilot | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
Penny | +0.024 |
Bruce | +0.024 |
Cindy | +0.023 |
Lilly | +0.022 |
Emmy | +0.022 |
Neg logit contributions | |
we | -0.026 |
ep | -0.023 |
bel | -0.022 |
ilot | -0.021 |
men | -0.021 |
Token | bear |
Token ID | 6842 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Bruce | +0.043 |
Penny | +0.042 |
Cindy | +0.041 |
Emmy | +0.041 |
Lilly | +0.040 |
Neg logit contributions | |
we | -0.031 |
ep | -0.027 |
men | -0.025 |
bel | -0.024 |
songs | -0.024 |
Token | 's |
Token ID | 338 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
we | +0.007 |
ep | +0.006 |
bel | +0.005 |
men | +0.005 |
anas | +0.005 |
Neg logit contributions | |
Bruce | -0.008 |
Penny | -0.008 |
Cindy | -0.008 |
Emmy | -0.008 |
Lilly | -0.008 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Bruce | +0.001 |
Penny | +0.001 |
Cindy | +0.001 |
Lilly | +0.001 |
Emmy | +0.001 |
Neg logit contributions | |
we | -0.001 |
ep | -0.001 |
bel | -0.000 |
men | -0.000 |
ilot | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Bruce | +0.007 |
Penny | +0.007 |
Cindy | +0.007 |
Emmy | +0.006 |
Lilly | +0.006 |
Neg logit contributions | |
we | -0.007 |
ep | -0.006 |
bel | -0.006 |
men | -0.006 |
ilot | -0.006 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Bruce | +0.017 |
Penny | +0.016 |
Cindy | +0.016 |
Lilly | +0.015 |
Emmy | +0.015 |
Neg logit contributions | |
we | -0.018 |
ep | -0.017 |
bel | -0.016 |
men | -0.015 |
anas | -0.015 |
Token | for |
Token ID | 329 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
Bruce | +0.085 |
Penny | +0.083 |
Cindy | +0.080 |
Emmy | +0.076 |
Lilly | +0.076 |
Neg logit contributions | |
we | -0.116 |
ep | -0.105 |
bel | -0.100 |
men | -0.098 |
ilot | -0.095 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Bruce | +0.029 |
Penny | +0.029 |
Cindy | +0.028 |
Emmy | +0.027 |
Lilly | +0.027 |
Neg logit contributions | |
we | -0.026 |
ep | -0.023 |
bel | -0.021 |
men | -0.021 |
angels | -0.020 |
Token | ion |
Token ID | 295 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
Bruce | +0.053 |
Penny | +0.049 |
Cindy | +0.048 |
Emmy | +0.048 |
Harriet | +0.046 |
Neg logit contributions | |
we | -0.050 |
ep | -0.043 |
angels | -0.042 |
men | -0.041 |
Some | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
Bruce | +0.309 |
Penny | +0.298 |
Cindy | +0.294 |
Emmy | +0.291 |
Lilly | +0.282 |
Neg logit contributions | |
we | -0.208 |
men | -0.169 |
ep | -0.161 |
angels | -0.152 |
bel | -0.150 |
Token | Her |
Token ID | 2332 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
Penny | +0.019 |
Bruce | +0.019 |
Cindy | +0.018 |
Lilly | +0.018 |
Emmy | +0.018 |
Neg logit contributions | |
we | -0.025 |
ep | -0.023 |
bel | -0.021 |
ity | -0.021 |
ilot | -0.021 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Penny | +0.035 |
Cindy | +0.035 |
Emmy | +0.034 |
Lilly | +0.034 |
Hannah | +0.033 |
Neg logit contributions | |
we | -0.027 |
ep | -0.023 |
bel | -0.021 |
ilot | -0.020 |
ney | -0.020 |
Token | said |
Token ID | 531 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
we | +0.006 |
ep | +0.006 |
bel | +0.005 |
ilot | +0.005 |
men | +0.005 |
Neg logit contributions | |
Penny | -0.004 |
Bruce | -0.004 |
Cindy | -0.004 |
Emmy | -0.003 |
Lilly | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
Penny | +0.075 |
Bruce | +0.075 |
Cindy | +0.071 |
Lilly | +0.069 |
Emmy | +0.069 |
Neg logit contributions | |
we | -0.115 |
ep | -0.107 |
bel | -0.101 |
men | -0.097 |
ilot | -0.097 |
Token | forgot |
Token ID | 16453 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
we | +0.005 |
ep | +0.005 |
bel | +0.004 |
men | +0.004 |
ity | +0.004 |
Neg logit contributions | |
Bruce | -0.006 |
Penny | -0.006 |
Cindy | -0.006 |
Emmy | -0.006 |
Lilly | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
Bruce | +0.081 |
Penny | +0.079 |
Cindy | +0.077 |
Emmy | +0.075 |
Lilly | +0.075 |
Neg logit contributions | |
we | -0.067 |
ep | -0.061 |
songs | -0.057 |
angels | -0.056 |
men | -0.056 |
Token | put |
Token ID | 1234 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Bruce | +0.002 |
Penny | +0.002 |
Cindy | +0.002 |
Emmy | +0.002 |
Lilly | +0.002 |
Neg logit contributions | |
we | -0.002 |
ep | -0.002 |
bel | -0.002 |
songs | -0.002 |
ity | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
Bruce | +0.054 |
Penny | +0.053 |
Cindy | +0.051 |
Emmy | +0.050 |
Lilly | +0.050 |
Neg logit contributions | |
we | -0.047 |
ep | -0.043 |
bel | -0.039 |
men | -0.037 |
ilot | -0.037 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
we | +0.017 |
ep | +0.016 |
bel | +0.014 |
men | +0.014 |
angels | +0.014 |
Neg logit contributions | |
Bruce | -0.013 |
Penny | -0.013 |
Cindy | -0.012 |
Emmy | -0.012 |
Lilly | -0.012 |
Token | ion |
Token ID | 295 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
Bruce | +0.037 |
Penny | +0.036 |
Cindy | +0.034 |
Emmy | +0.034 |
Lilly | +0.032 |
Neg logit contributions | |
we | -0.064 |
ep | -0.059 |
bel | -0.054 |
as | -0.054 |
men | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Bruce | +0.283 |
Penny | +0.278 |
Cindy | +0.269 |
Emmy | +0.269 |
Lilly | +0.265 |
Neg logit contributions | |
we | -0.225 |
ep | -0.187 |
men | -0.181 |
bel | -0.180 |
angels | -0.167 |
Token | which |
Token ID | 543 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Penny | +0.050 |
Bruce | +0.049 |
Cindy | +0.048 |
Lilly | +0.047 |
Emmy | +0.047 |
Neg logit contributions | |
we | -0.057 |
ep | -0.053 |
ilot | -0.049 |
bel | -0.049 |
men | -0.049 |
Token | made |
Token ID | 925 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Bruce | +0.094 |
Penny | +0.091 |
Cindy | +0.088 |
Emmy | +0.086 |
Lilly | +0.085 |
Neg logit contributions | |
we | -0.089 |
ep | -0.080 |
bel | -0.074 |
men | -0.073 |
angels | -0.070 |
Token | her |
Token ID | 607 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
we | +0.068 |
ep | +0.063 |
bel | +0.060 |
ilot | +0.058 |
men | +0.058 |
Neg logit contributions | |
Penny | -0.039 |
Bruce | -0.038 |
Cindy | -0.037 |
Lilly | -0.036 |
Emmy | -0.036 |
Token | skin |
Token ID | 4168 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
we | +0.008 |
ep | +0.007 |
men | +0.007 |
ilot | +0.007 |
anas | +0.006 |
Neg logit contributions | |
Penny | -0.006 |
Cindy | -0.005 |
Lilly | -0.005 |
Bruce | -0.005 |
Emmy | -0.005 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Bruce | +0.037 |
Penny | +0.036 |
Cindy | +0.034 |
Emmy | +0.033 |
Lilly | +0.032 |
Neg logit contributions | |
we | -0.059 |
ep | -0.054 |
bel | -0.052 |
men | -0.050 |
ilot | -0.050 |
Token | 's |
Token ID | 338 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
Bruce | +0.072 |
Penny | +0.070 |
Cindy | +0.069 |
Emmy | +0.066 |
Lilly | +0.065 |
Neg logit contributions | |
we | -0.066 |
ep | -0.062 |
bel | -0.055 |
ney | -0.054 |
men | -0.053 |
Token | mom |
Token ID | 1995 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
Penny | +0.003 |
Cindy | +0.003 |
Bruce | +0.003 |
Lilly | +0.003 |
Emmy | +0.003 |
Neg logit contributions | |
we | -0.003 |
ep | -0.002 |
anas | -0.002 |
v | -0.002 |
ity | -0.002 |
Token | put |
Token ID | 1234 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Bruce | +0.003 |
Penny | +0.003 |
Cindy | +0.003 |
Emmy | +0.003 |
Holly | +0.003 |
Neg logit contributions | |
we | -0.004 |
ep | -0.003 |
men | -0.003 |
bel | -0.003 |
ney | -0.003 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Penny | +0.051 |
Bruce | +0.050 |
Cindy | +0.049 |
Lilly | +0.048 |
Emmy | +0.047 |
Neg logit contributions | |
we | -0.050 |
ep | -0.045 |
bel | -0.043 |
ilot | -0.041 |
men | -0.041 |
Token | ion |
Token ID | 295 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
Bruce | +0.038 |
Penny | +0.037 |
Emmy | +0.035 |
Cindy | +0.035 |
Harriet | +0.034 |
Neg logit contributions | |
we | -0.057 |
ep | -0.055 |
bel | -0.049 |
men | -0.049 |
as | -0.048 |
Token | on |
Token ID | 319 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
Bruce | +0.294 |
Penny | +0.294 |
Cindy | +0.282 |
Emmy | +0.279 |
Lilly | +0.276 |
Neg logit contributions | |
we | -0.217 |
ep | -0.186 |
bel | -0.174 |
men | -0.169 |
angels | -0.160 |
Token | her |
Token ID | 607 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
we | +0.020 |
ep | +0.018 |
bel | +0.017 |
men | +0.017 |
ilot | +0.016 |
Neg logit contributions | |
Bruce | -0.014 |
Penny | -0.014 |
Cindy | -0.014 |
Emmy | -0.013 |
Lilly | -0.013 |
Token | arms |
Token ID | 5101 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
we | +0.007 |
ep | +0.006 |
men | +0.006 |
bel | +0.006 |
ilot | +0.006 |
Neg logit contributions | |
Penny | -0.008 |
Cindy | -0.007 |
Bruce | -0.007 |
Emmy | -0.007 |
Lilly | -0.007 |
Token | because |
Token ID | 780 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
Bruce | +0.008 |
Penny | +0.008 |
Cindy | +0.007 |
Emmy | +0.007 |
Lilly | +0.007 |
Neg logit contributions | |
we | -0.005 |
ep | -0.005 |
bel | -0.004 |
ilot | -0.004 |
men | -0.004 |
Token | they |
Token ID | 484 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
Penny | +0.015 |
Bruce | +0.015 |
Cindy | +0.014 |
Lilly | +0.014 |
Emmy | +0.014 |
Neg logit contributions | |
we | -0.022 |
ep | -0.020 |
bel | -0.019 |
ilot | -0.018 |
men | -0.018 |
Token | found |
Token ID | 1043 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
we | +0.009 |
ep | +0.009 |
men | +0.008 |
bel | +0.008 |
ney | +0.008 |
Neg logit contributions | |
Bruce | -0.011 |
Cindy | -0.011 |
Penny | -0.011 |
Emmy | -0.011 |
Harriet | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
we | +0.023 |
ep | +0.020 |
bel | +0.019 |
ilot | +0.019 |
anas | +0.018 |
Neg logit contributions | |
Penny | -0.025 |
Bruce | -0.025 |
Cindy | -0.024 |
Lilly | -0.023 |
Emmy | -0.023 |
Token | bottle |
Token ID | 9294 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
Bruce | +0.030 |
Penny | +0.030 |
Cindy | +0.029 |
Lilly | +0.028 |
Emmy | +0.028 |
Neg logit contributions | |
we | -0.016 |
ep | -0.015 |
bel | -0.013 |
men | -0.013 |
song | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Bruce | +0.180 |
Cindy | +0.178 |
Penny | +0.177 |
Emmy | +0.172 |
Lilly | +0.168 |
Neg logit contributions | |
we | -0.116 |
ep | -0.103 |
bel | -0.092 |
men | -0.088 |
ney | -0.088 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
we | +0.044 |
ep | +0.043 |
songs | +0.043 |
song | +0.042 |
ity | +0.038 |
Neg logit contributions | |
Bruce | -0.056 |
Harriet | -0.052 |
Penny | -0.051 |
Cindy | -0.051 |
Cody | -0.050 |
Token | ion |
Token ID | 295 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
Bruce | +0.053 |
Cindy | +0.050 |
Harriet | +0.049 |
Emmy | +0.048 |
Penny | +0.047 |
Neg logit contributions | |
we | -0.040 |
as | -0.035 |
ep | -0.034 |
ney | -0.032 |
men | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
Bruce | +0.331 |
Cindy | +0.326 |
Penny | +0.323 |
Emmy | +0.322 |
Lilly | +0.315 |
Neg logit contributions | |
we | -0.185 |
ep | -0.134 |
men | -0.132 |
angels | -0.118 |
bel | -0.113 |
Token | The |
Token ID | 383 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Penny | +0.011 |
Bruce | +0.011 |
Cindy | +0.010 |
Lilly | +0.010 |
Sophie | +0.010 |
Neg logit contributions | |
we | -0.016 |
ep | -0.015 |
bel | -0.013 |
ity | -0.013 |
men | -0.013 |
Token | cat |
Token ID | 3797 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Penny | +0.013 |
Cindy | +0.013 |
Bruce | +0.012 |
Lilly | +0.012 |
Hannah | +0.012 |
Neg logit contributions | |
we | -0.009 |
ep | -0.008 |
bel | -0.008 |
ilot | -0.007 |
anas | -0.007 |
Token | did |
Token ID | 750 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
we | +0.012 |
ep | +0.011 |
bel | +0.010 |
ilot | +0.010 |
men | +0.010 |
Neg logit contributions | |
Penny | -0.013 |
Bruce | -0.013 |
Cindy | -0.013 |
Lilly | -0.012 |
Emmy | -0.012 |
Token | not |
Token ID | 407 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
we | +0.068 |
ep | +0.059 |
bel | +0.053 |
ilot | +0.053 |
men | +0.052 |
Neg logit contributions | |
Penny | -0.110 |
Bruce | -0.109 |
Cindy | -0.106 |
Lilly | -0.104 |
Emmy | -0.103 |
Token | mom |
Token ID | 1995 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
we | +0.004 |
ep | +0.004 |
anas | +0.003 |
bel | +0.003 |
ilot | +0.003 |
Neg logit contributions | |
Penny | -0.007 |
Bruce | -0.007 |
Cindy | -0.007 |
Emmy | -0.007 |
Lilly | -0.007 |
Token | my |
Token ID | 1820 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Bruce | +0.002 |
Penny | +0.002 |
Cindy | +0.002 |
Emmy | +0.002 |
Lilly | +0.002 |
Neg logit contributions | |
we | -0.003 |
ep | -0.003 |
bel | -0.003 |
men | -0.003 |
ilot | -0.003 |
Token | using |
Token ID | 1262 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
we | +0.068 |
ep | +0.061 |
bel | +0.056 |
men | +0.054 |
ilot | +0.053 |
Neg logit contributions | |
Bruce | -0.071 |
Penny | -0.070 |
Cindy | -0.068 |
Lilly | -0.066 |
Emmy | -0.065 |
Token | a |
Token ID | 257 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
Bruce | +0.080 |
Penny | +0.076 |
Cindy | +0.074 |
Harriet | +0.072 |
Emmy | +0.071 |
Neg logit contributions | |
ep | -0.050 |
we | -0.050 |
bel | -0.043 |
songs | -0.041 |
angels | -0.040 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Bruce | +0.022 |
Penny | +0.021 |
Cindy | +0.021 |
Lilly | +0.020 |
Sophie | +0.020 |
Neg logit contributions | |
we | -0.014 |
ep | -0.013 |
bel | -0.012 |
ilot | -0.011 |
men | -0.011 |
Token | ion |
Token ID | 295 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
Bruce | +0.058 |
Penny | +0.057 |
Cindy | +0.056 |
Emmy | +0.054 |
Harriet | +0.053 |
Neg logit contributions | |
we | -0.031 |
ep | -0.028 |
bel | -0.025 |
men | -0.023 |
ilot | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Bruce | +0.313 |
Penny | +0.304 |
Cindy | +0.296 |
Emmy | +0.290 |
Lilly | +0.286 |
Neg logit contributions | |
we | -0.204 |
ep | -0.159 |
men | -0.156 |
bel | -0.155 |
angels | -0.143 |
Token | smelled |
Token ID | 37609 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Bruce | +0.045 |
Penny | +0.043 |
Cindy | +0.042 |
Emmy | +0.040 |
Lilly | +0.040 |
Neg logit contributions | |
we | -0.051 |
ep | -0.046 |
bel | -0.043 |
men | -0.042 |
angels | -0.040 |
Token | so |
Token ID | 523 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
Bruce | +0.061 |
Penny | +0.059 |
Cindy | +0.057 |
Harriet | +0.056 |
Emmy | +0.056 |
Neg logit contributions | |
we | -0.045 |
ep | -0.041 |
bel | -0.037 |
songs | -0.037 |
ity | -0.036 |
Token | good |
Token ID | 922 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Bruce | +0.030 |
Penny | +0.030 |
Cindy | +0.029 |
Emmy | +0.028 |
Lilly | +0.028 |
Neg logit contributions | |
we | -0.023 |
ep | -0.020 |
bel | -0.019 |
men | -0.018 |
ilot | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
Bruce | +0.087 |
Penny | +0.083 |
Cindy | +0.081 |
Harriet | +0.079 |
Emmy | +0.079 |
Neg logit contributions | |
we | -0.053 |
songs | -0.041 |
ep | -0.040 |
men | -0.039 |
angels | -0.038 |
Token | soon |
Token ID | 2582 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
Penny | +0.006 |
Bruce | +0.006 |
Cindy | +0.006 |
Emmy | +0.006 |
Lilly | +0.006 |
Neg logit contributions | |
we | -0.005 |
ep | -0.005 |
bel | -0.005 |
ilot | -0.004 |
men | -0.004 |
Token | found |
Token ID | 1043 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
we | +0.129 |
ep | +0.126 |
bel | +0.117 |
men | +0.114 |
ilot | +0.109 |
Neg logit contributions | |
Cindy | -0.126 |
Bruce | -0.124 |
Penny | -0.121 |
Emmy | -0.120 |
Lilly | -0.117 |
Token | a |
Token ID | 257 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
we | +0.033 |
ep | +0.030 |
bel | +0.027 |
men | +0.027 |
angels | +0.026 |
Neg logit contributions | |
Penny | -0.043 |
Bruce | -0.043 |
Cindy | -0.043 |
Emmy | -0.042 |
Lilly | -0.041 |
Token | new |
Token ID | 649 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Bruce | +0.014 |
Penny | +0.014 |
Cindy | +0.014 |
Lilly | +0.014 |
Emmy | +0.014 |
Neg logit contributions | |
we | -0.009 |
ep | -0.008 |
bel | -0.007 |
men | -0.007 |
song | -0.007 |
Token | lot |
Token ID | 1256 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
Penny | +0.066 |
Bruce | +0.065 |
Cindy | +0.064 |
Emmy | +0.062 |
Lilly | +0.062 |
Neg logit contributions | |
we | -0.044 |
ep | -0.041 |
song | -0.038 |
songs | -0.037 |
bel | -0.036 |
Token | ion |
Token ID | 295 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
Cindy | +0.053 |
Bruce | +0.053 |
Penny | +0.052 |
Harriet | +0.052 |
Emmy | +0.052 |
Neg logit contributions | |
we | -0.022 |
ep | -0.018 |
as | -0.017 |
men | -0.015 |
ney | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
Penny | +0.295 |
Bruce | +0.289 |
Cindy | +0.288 |
Emmy | +0.283 |
Lilly | +0.280 |
Neg logit contributions | |
we | -0.214 |
men | -0.164 |
ep | -0.160 |
bel | -0.148 |
angels | -0.146 |
Token | which |
Token ID | 543 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Bruce | +0.032 |
Penny | +0.032 |
Cindy | +0.031 |
Emmy | +0.030 |
Lilly | +0.030 |
Neg logit contributions | |
we | -0.027 |
ep | -0.024 |
bel | -0.022 |
men | -0.021 |
anas | -0.020 |
Token | wasn |
Token ID | 2492 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
Bruce | +0.081 |
Penny | +0.080 |
Cindy | +0.078 |
Emmy | +0.076 |
Harriet | +0.075 |
Neg logit contributions | |
we | -0.062 |
ep | -0.056 |
men | -0.052 |
bel | -0.049 |
ney | -0.047 |
Token | 't |
Token ID | 470 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Penny | +0.028 |
Bruce | +0.028 |
Cindy | +0.027 |
Lilly | +0.027 |
Harriet | +0.027 |
Neg logit contributions | |
we | -0.019 |
ep | -0.018 |
ilot | -0.016 |
z | -0.016 |
bel | -0.015 |
Token | so |
Token ID | 523 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
we | +0.016 |
ep | +0.016 |
bel | +0.013 |
angels | +0.013 |
ity | +0.013 |
Neg logit contributions | |
Bruce | -0.019 |
Penny | -0.018 |
Cindy | -0.018 |
Harriet | -0.017 |
Emmy | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Cindy | +0.001 |
Bruce | +0.001 |
Penny | +0.001 |
Emmy | +0.001 |
Hannah | +0.001 |
Neg logit contributions | |
we | -0.000 |
ep | -0.000 |
men | -0.000 |
bel | -0.000 |
ney | -0.000 |
Token | she |
Token ID | 673 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Bruce | +0.015 |
Cindy | +0.014 |
Penny | +0.014 |
Emmy | +0.013 |
Hannah | +0.013 |
Neg logit contributions | |
we | -0.015 |
bel | -0.014 |
ep | -0.013 |
men | -0.012 |
songs | -0.012 |
Token | shouted |
Token ID | 17293 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Bruce | +0.048 |
Penny | +0.047 |
Cindy | +0.046 |
Emmy | +0.044 |
Harriet | +0.043 |
Neg logit contributions | |
we | -0.046 |
ep | -0.045 |
bel | -0.040 |
men | -0.038 |
anas | -0.037 |
Token | ' |
Token ID | 705 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
Bruce | +0.077 |
Cindy | +0.075 |
Penny | +0.075 |
Emmy | +0.072 |
Lilly | +0.071 |
Neg logit contributions | |
we | -0.070 |
bel | -0.058 |
ep | -0.057 |
songs | -0.056 |
men | -0.055 |
Token | On |
Token ID | 2202 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Bruce | +0.022 |
Cindy | +0.021 |
Penny | +0.021 |
Lilly | +0.021 |
Emmy | +0.021 |
Neg logit contributions | |
we | -0.021 |
ep | -0.020 |
men | -0.020 |
ilot | -0.020 |
angels | -0.019 |
Token | ion |
Token ID | 295 |
Feature activation | +5.77e+00 |
Pos logit contributions | |
Bruce | +0.049 |
Cindy | +0.048 |
Penny | +0.046 |
Emmy | +0.045 |
Cody | +0.044 |
Neg logit contributions | |
ep | -0.040 |
we | -0.037 |
songs | -0.033 |
ilot | -0.033 |
angels | -0.032 |
Token | !' |
Token ID | 13679 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Bruce | +0.214 |
Penny | +0.210 |
Cindy | +0.204 |
Emmy | +0.200 |
Lilly | +0.198 |
Neg logit contributions | |
we | -0.278 |
ep | -0.232 |
men | -0.230 |
bel | -0.226 |
z | -0.219 |
Token | as |
Token ID | 355 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
Bruce | +0.017 |
Penny | +0.016 |
Cindy | +0.016 |
Emmy | +0.015 |
Lilly | +0.015 |
Neg logit contributions | |
we | -0.020 |
ep | -0.018 |
bel | -0.017 |
ilot | -0.016 |
men | -0.016 |
Token | loud |
Token ID | 7812 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
Bruce | +0.002 |
Penny | +0.002 |
Cindy | +0.002 |
Lilly | +0.002 |
Emmy | +0.002 |
Neg logit contributions | |
we | -0.004 |
ep | -0.003 |
bel | -0.003 |
men | -0.003 |
angels | -0.003 |
Token | as |
Token ID | 355 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
we | +0.122 |
ep | +0.108 |
songs | +0.107 |
angels | +0.103 |
bel | +0.102 |
Neg logit contributions | |
Bruce | -0.111 |
Penny | -0.110 |
Emmy | -0.102 |
Cindy | -0.101 |
Harriet | -0.101 |
Token | she |
Token ID | 673 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
Bruce | +0.001 |
Penny | +0.001 |
Cindy | +0.001 |
Emmy | +0.001 |
Lilly | +0.001 |
Neg logit contributions | |
we | -0.001 |
angels | -0.001 |
ep | -0.001 |
men | -0.001 |
bel | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Penny | +0.017 |
Bruce | +0.017 |
Cindy | +0.016 |
Lilly | +0.016 |
Emmy | +0.016 |
Neg logit contributions | |
we | -0.016 |
ep | -0.014 |
bel | -0.013 |
ilot | -0.013 |
men | -0.013 |
Token | big |
Token ID | 1263 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Bruce | +0.024 |
Penny | +0.024 |
Cindy | +0.023 |
Emmy | +0.023 |
Lilly | +0.023 |
Neg logit contributions | |
we | -0.015 |
ep | -0.013 |
bel | -0.012 |
men | -0.011 |
ilot | -0.011 |
Token | bottle |
Token ID | 9294 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
ep | +0.009 |
we | +0.008 |
ilot | +0.008 |
men | +0.008 |
songs | +0.007 |
Neg logit contributions | |
Bruce | -0.012 |
Penny | -0.011 |
Cindy | -0.011 |
Emmy | -0.011 |
Lilly | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Penny | +0.170 |
Bruce | +0.169 |
Cindy | +0.163 |
Lilly | +0.160 |
Emmy | +0.159 |
Neg logit contributions | |
we | -0.133 |
ep | -0.118 |
bel | -0.109 |
men | -0.104 |
ilot | -0.104 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
songs | +0.050 |
we | +0.050 |
ep | +0.047 |
song | +0.047 |
ity | +0.044 |
Neg logit contributions | |
Bruce | -0.062 |
Harriet | -0.058 |
Cindy | -0.056 |
Emmy | -0.055 |
Penny | -0.055 |
Token | ion |
Token ID | 295 |
Feature activation | +5.77e+00 |
Pos logit contributions | |
Bruce | +0.039 |
Cindy | +0.038 |
Penny | +0.037 |
Emmy | +0.036 |
Harriet | +0.036 |
Neg logit contributions | |
we | -0.050 |
ep | -0.045 |
as | -0.043 |
men | -0.043 |
bel | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Penny | +0.285 |
Bruce | +0.285 |
Cindy | +0.281 |
Emmy | +0.275 |
Lilly | +0.272 |
Neg logit contributions | |
we | -0.215 |
ep | -0.179 |
men | -0.171 |
bel | -0.167 |
angels | -0.159 |
Token | he |
Token ID | 339 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Penny | +0.006 |
Bruce | +0.006 |
Cindy | +0.006 |
Lilly | +0.006 |
Emmy | +0.006 |
Neg logit contributions | |
we | -0.007 |
ep | -0.006 |
bel | -0.006 |
ilot | -0.006 |
men | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
we | +0.011 |
ep | +0.010 |
bel | +0.009 |
men | +0.009 |
ilot | +0.009 |
Neg logit contributions | |
Bruce | -0.015 |
Penny | -0.015 |
Cindy | -0.015 |
Emmy | -0.014 |
Lilly | -0.014 |
Token | very |
Token ID | 845 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
Bruce | +0.025 |
Penny | +0.025 |
Cindy | +0.024 |
Emmy | +0.024 |
Lilly | +0.024 |
Neg logit contributions | |
we | -0.021 |
ep | -0.020 |
bel | -0.018 |
men | -0.018 |
ilot | -0.017 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Bruce | +0.033 |
Penny | +0.033 |
Cindy | +0.032 |
Emmy | +0.031 |
Lilly | +0.031 |
Neg logit contributions | |
we | -0.022 |
ep | -0.020 |
bel | -0.018 |
men | -0.017 |
ilot | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
we | +0.062 |
ep | +0.056 |
bel | +0.052 |
men | +0.050 |
ilot | +0.050 |
Neg logit contributions | |
Bruce | -0.068 |
Penny | -0.068 |
Cindy | -0.065 |
Emmy | -0.064 |
Lilly | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Penny | +0.005 |
Bruce | +0.005 |
Cindy | +0.005 |
Emmy | +0.005 |
Lilly | +0.005 |
Neg logit contributions | |
we | -0.005 |
ep | -0.004 |
bel | -0.004 |
ilot | -0.004 |
men | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Penny | +0.011 |
Bruce | +0.011 |
Cindy | +0.011 |
Lilly | +0.011 |
Emmy | +0.011 |
Neg logit contributions | |
we | -0.011 |
ep | -0.010 |
bel | -0.009 |
men | -0.009 |
ity | -0.009 |
Token | The |
Token ID | 464 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
Penny | +0.015 |
Bruce | +0.015 |
Cindy | +0.014 |
Emmy | +0.014 |
Lilly | +0.014 |
Neg logit contributions | |
we | -0.009 |
ep | -0.007 |
bel | -0.007 |
men | -0.007 |
angels | -0.007 |
Token | scorp |
Token ID | 47394 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
we | +0.022 |
ep | +0.020 |
bel | +0.018 |
men | +0.018 |
ilot | +0.018 |
Neg logit contributions | |
Bruce | -0.029 |
Penny | -0.029 |
Cindy | -0.028 |
Emmy | -0.027 |
Lilly | -0.027 |
Token | ion |
Token ID | 295 |
Feature activation | +5.77e+00 |
Pos logit contributions | |
Bruce | +0.026 |
Cindy | +0.026 |
Penny | +0.026 |
Emmy | +0.024 |
Harriet | +0.024 |
Neg logit contributions | |
we | -0.032 |
ep | -0.029 |
ilot | -0.026 |
as | -0.026 |
men | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Penny | +0.253 |
Bruce | +0.253 |
Cindy | +0.246 |
Emmy | +0.239 |
Lilly | +0.238 |
Neg logit contributions | |
we | -0.246 |
ep | -0.221 |
bel | -0.204 |
men | -0.203 |
ilot | -0.197 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
Bruce | +0.011 |
Penny | +0.011 |
Cindy | +0.011 |
Emmy | +0.011 |
Lilly | +0.011 |
Neg logit contributions | |
we | -0.010 |
ep | -0.010 |
bel | -0.009 |
men | -0.009 |
ilot | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
we | +0.100 |
ep | +0.088 |
bel | +0.082 |
men | +0.080 |
ilot | +0.078 |
Neg logit contributions | |
Bruce | -0.112 |
Penny | -0.111 |
Cindy | -0.108 |
Emmy | -0.105 |
Lilly | -0.105 |
Token | ready |
Token ID | 3492 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Bruce | +0.007 |
Penny | +0.007 |
Cindy | +0.006 |
Emmy | +0.006 |
Lilly | +0.006 |
Neg logit contributions | |
we | -0.007 |
ep | -0.007 |
bel | -0.006 |
men | -0.006 |
songs | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
we | +0.041 |
ep | +0.037 |
bel | +0.034 |
men | +0.034 |
ilot | +0.033 |
Neg logit contributions | |
Bruce | -0.049 |
Penny | -0.049 |
Cindy | -0.048 |
Emmy | -0.046 |
Lilly | -0.046 |
Token | has |
Token ID | 468 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
Bruce | +0.049 |
Penny | +0.047 |
Cindy | +0.045 |
Emmy | +0.045 |
Lilly | +0.045 |
Neg logit contributions | |
we | -0.033 |
ep | -0.031 |
men | -0.027 |
ilot | -0.026 |
angels | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
Bruce | +0.048 |
Penny | +0.046 |
Cindy | +0.045 |
Emmy | +0.044 |
Lilly | +0.044 |
Neg logit contributions | |
we | -0.034 |
ep | -0.031 |
bel | -0.027 |
songs | -0.027 |
angels | -0.026 |
Token | lot |
Token ID | 1256 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
Bruce | +0.014 |
Penny | +0.014 |
Cindy | +0.013 |
Lilly | +0.013 |
Emmy | +0.013 |
Neg logit contributions | |
we | -0.008 |
ep | -0.008 |
ilot | -0.007 |
song | -0.007 |
bel | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Bruce | +0.061 |
Penny | +0.058 |
Cindy | +0.057 |
Emmy | +0.057 |
Harriet | +0.056 |
Neg logit contributions | |
we | -0.022 |
ep | -0.018 |
as | -0.017 |
bel | -0.016 |
songs | -0.014 |
Token | lot |
Token ID | 1256 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
we | +0.042 |
ep | +0.042 |
songs | +0.042 |
song | +0.037 |
angels | +0.037 |
Neg logit contributions | |
Bruce | -0.079 |
Penny | -0.075 |
Harriet | -0.071 |
Emmy | -0.070 |
Jackie | -0.070 |
Token | ion |
Token ID | 295 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
Bruce | +0.044 |
Penny | +0.040 |
Emmy | +0.039 |
Harriet | +0.039 |
Cindy | +0.038 |
Neg logit contributions | |
we | -0.037 |
as | -0.032 |
ep | -0.032 |
songs | -0.030 |
angels | -0.030 |
Token | on |
Token ID | 319 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
Bruce | +0.288 |
Penny | +0.281 |
Emmy | +0.274 |
Cindy | +0.273 |
Lilly | +0.269 |
Neg logit contributions | |
we | -0.219 |
ep | -0.179 |
men | -0.178 |
bel | -0.170 |
angels | -0.167 |
Token | her |
Token ID | 607 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
we | +0.027 |
ep | +0.025 |
bel | +0.023 |
men | +0.023 |
ilot | +0.023 |
Neg logit contributions | |
Bruce | -0.020 |
Penny | -0.020 |
Cindy | -0.019 |
Emmy | -0.018 |
Lilly | -0.018 |
Token | skin |
Token ID | 4168 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
we | +0.010 |
ep | +0.009 |
bel | +0.009 |
men | +0.008 |
anas | +0.008 |
Neg logit contributions | |
Penny | -0.013 |
Cindy | -0.012 |
Bruce | -0.012 |
Emmy | -0.012 |
Lilly | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -7.66e-04 |
Pos logit contributions | |
Penny | +0.069 |
Bruce | +0.068 |
Cindy | +0.066 |
Lilly | +0.064 |
Emmy | +0.064 |
Neg logit contributions | |
we | -0.068 |
ep | -0.061 |
bel | -0.057 |
ilot | -0.055 |
men | -0.055 |
Token | She |
Token ID | 1375 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
we | +0.000 |
ep | +0.000 |
bel | +0.000 |
ity | +0.000 |
men | +0.000 |
Neg logit contributions | |
Penny | -0.000 |
Bruce | -0.000 |
Cindy | -0.000 |
Lilly | -0.000 |
Emmy | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
Bruce | +0.017 |
Penny | +0.017 |
Cindy | +0.016 |
Emmy | +0.016 |
Lilly | +0.016 |
Neg logit contributions | |
we | -0.012 |
ep | -0.011 |
bel | -0.010 |
men | -0.009 |
ity | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Bruce | +0.027 |
Penny | +0.027 |
Cindy | +0.026 |
Emmy | +0.026 |
Harriet | +0.025 |
Neg logit contributions | |
we | -0.017 |
ep | -0.017 |
men | -0.014 |
bel | -0.014 |
songs | -0.014 |
Token | very |
Token ID | 845 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
Bruce | +0.018 |
Penny | +0.018 |
Cindy | +0.018 |
Emmy | +0.017 |
Lilly | +0.017 |
Neg logit contributions | |
we | -0.013 |
ep | -0.012 |
bel | -0.011 |
men | -0.011 |
ilot | -0.010 |
Token | sweet |
Token ID | 6029 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Penny | +0.032 |
Bruce | +0.032 |
Cindy | +0.032 |
Emmy | +0.031 |
Lilly | +0.030 |
Neg logit contributions | |
we | -0.023 |
ep | -0.021 |
bel | -0.020 |
men | -0.019 |
ity | -0.018 |
Token | stall |
Token ID | 22549 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
Penny | +0.072 |
Bruce | +0.071 |
Cindy | +0.069 |
Emmy | +0.068 |
Lilly | +0.066 |
Neg logit contributions | |
we | -0.056 |
ep | -0.049 |
ity | -0.048 |
song | -0.048 |
songs | -0.047 |
Token | ion |
Token ID | 295 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
Penny | +0.027 |
Bruce | +0.027 |
Cindy | +0.027 |
Emmy | +0.026 |
Lilly | +0.026 |
Neg logit contributions | |
we | -0.019 |
ep | -0.017 |
men | -0.016 |
ney | -0.016 |
bel | -0.015 |
Token | ! |
Token ID | 0 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
Penny | +0.283 |
Bruce | +0.280 |
Cindy | +0.278 |
Emmy | +0.273 |
Lilly | +0.270 |
Neg logit contributions | |
we | -0.215 |
ep | -0.168 |
men | -0.167 |
anas | -0.154 |
angels | -0.151 |
Token | John |
Token ID | 1757 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
we | +0.025 |
ep | +0.023 |
bel | +0.022 |
men | +0.021 |
ilot | +0.021 |
Neg logit contributions | |
Bruce | -0.018 |
Penny | -0.018 |
Cindy | -0.017 |
Emmy | -0.017 |
Lilly | -0.017 |
Token | just |
Token ID | 655 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
we | +0.044 |
ep | +0.039 |
bel | +0.038 |
men | +0.036 |
ilot | +0.036 |
Neg logit contributions | |
Penny | -0.044 |
Bruce | -0.044 |
Cindy | -0.043 |
Emmy | -0.042 |
Lilly | -0.042 |
Token | had |
Token ID | 550 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
we | +0.002 |
ep | +0.002 |
ity | +0.002 |
bel | +0.002 |
anas | +0.002 |
Neg logit contributions | |
Bruce | -0.002 |
Penny | -0.002 |
Cindy | -0.002 |
Emmy | -0.002 |
Harriet | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Bruce | +0.014 |
Penny | +0.014 |
Cindy | +0.013 |
Emmy | +0.013 |
Lilly | +0.013 |
Neg logit contributions | |
we | -0.011 |
ep | -0.010 |
bel | -0.009 |
men | -0.008 |
ilot | -0.008 |
Token | house |
Token ID | 2156 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Penny | +0.026 |
Bruce | +0.026 |
Cindy | +0.026 |
Emmy | +0.025 |
Lilly | +0.024 |
Neg logit contributions | |
we | -0.032 |
ep | -0.029 |
bel | -0.027 |
ilot | -0.027 |
men | -0.026 |
Token | looking |
Token ID | 2045 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
we | +0.020 |
ep | +0.019 |
bel | +0.017 |
ilot | +0.017 |
ity | +0.017 |
Neg logit contributions | |
Penny | -0.017 |
Bruce | -0.017 |
Cindy | -0.016 |
Lilly | -0.016 |
Emmy | -0.016 |
Token | for |
Token ID | 329 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
we | +0.072 |
ep | +0.065 |
bel | +0.065 |
songs | +0.061 |
angels | +0.060 |
Neg logit contributions | |
Bruce | -0.081 |
Penny | -0.079 |
Cindy | -0.077 |
Emmy | -0.075 |
Harriet | -0.074 |
Token | her |
Token ID | 607 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Bruce | +0.022 |
Penny | +0.022 |
Emmy | +0.020 |
Cindy | +0.020 |
Jackie | +0.020 |
Neg logit contributions | |
we | -0.022 |
ep | -0.020 |
angels | -0.018 |
bel | -0.018 |
songs | -0.018 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
we | +0.006 |
ep | +0.006 |
bel | +0.005 |
men | +0.005 |
angels | +0.005 |
Neg logit contributions | |
Bruce | -0.010 |
Penny | -0.010 |
Cindy | -0.009 |
Emmy | -0.009 |
Lilly | -0.009 |
Token | ion |
Token ID | 295 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
Bruce | +0.040 |
Penny | +0.037 |
Emmy | +0.035 |
Harriet | +0.034 |
Cindy | +0.033 |
Neg logit contributions | |
we | -0.055 |
ep | -0.048 |
as | -0.047 |
men | -0.045 |
angels | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +8.01e-02 |
Pos logit contributions | |
Bruce | +0.307 |
Penny | +0.298 |
Cindy | +0.295 |
Emmy | +0.290 |
Lilly | +0.287 |
Neg logit contributions | |
we | -0.195 |
men | -0.149 |
ep | -0.146 |
angels | -0.141 |
bel | -0.136 |
Token | She |
Token ID | 1375 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Bruce | +0.003 |
Penny | +0.003 |
Cindy | +0.003 |
Emmy | +0.003 |
Lilly | +0.003 |
Neg logit contributions | |
we | -0.004 |
ep | -0.004 |
bel | -0.004 |
men | -0.004 |
ilot | -0.004 |
Token | tried |
Token ID | 3088 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
Bruce | +0.055 |
Penny | +0.054 |
Cindy | +0.052 |
Emmy | +0.050 |
Lilly | +0.050 |
Neg logit contributions | |
we | -0.073 |
ep | -0.068 |
bel | -0.063 |
men | -0.061 |
ilot | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
Bruce | +0.025 |
Penny | +0.025 |
Cindy | +0.024 |
Emmy | +0.024 |
Lilly | +0.024 |
Neg logit contributions | |
we | -0.022 |
ep | -0.020 |
bel | -0.018 |
men | -0.018 |
ilot | -0.017 |
Token | look |
Token ID | 804 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
we | +0.002 |
ep | +0.002 |
bel | +0.002 |
ilot | +0.001 |
ity | +0.001 |
Neg logit contributions | |
Bruce | -0.002 |
Penny | -0.002 |
Cindy | -0.001 |
Emmy | -0.001 |
Lilly | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
Penny | +0.087 |
Bruce | +0.083 |
Cindy | +0.082 |
Lilly | +0.080 |
Emmy | +0.079 |
Neg logit contributions | |
we | -0.096 |
ep | -0.086 |
ilot | -0.079 |
bel | -0.078 |
anas | -0.078 |
Token | put |
Token ID | 1234 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Bruce | +0.009 |
Penny | +0.009 |
Cindy | +0.009 |
Emmy | +0.009 |
Lilly | +0.009 |
Neg logit contributions | |
we | -0.010 |
ep | -0.009 |
bel | -0.009 |
men | -0.008 |
ilot | -0.008 |
Token | on |
Token ID | 319 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
Bruce | +0.054 |
Penny | +0.053 |
Cindy | +0.051 |
Emmy | +0.050 |
Lilly | +0.049 |
Neg logit contributions | |
we | -0.053 |
ep | -0.049 |
bel | -0.044 |
men | -0.043 |
ilot | -0.043 |
Token | cooling |
Token ID | 15134 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
we | +0.022 |
ep | +0.021 |
bel | +0.019 |
songs | +0.018 |
men | +0.018 |
Neg logit contributions | |
Bruce | -0.016 |
Penny | -0.016 |
Cindy | -0.015 |
Emmy | -0.015 |
Lilly | -0.014 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
we | +0.045 |
ep | +0.041 |
bel | +0.039 |
men | +0.037 |
ilot | +0.037 |
Neg logit contributions | |
Penny | -0.034 |
Bruce | -0.033 |
Cindy | -0.032 |
Lilly | -0.031 |
Emmy | -0.031 |
Token | ion |
Token ID | 295 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
Bruce | +0.035 |
Penny | +0.033 |
Cindy | +0.032 |
Emmy | +0.031 |
Harriet | +0.030 |
Neg logit contributions | |
we | -0.055 |
ep | -0.050 |
bel | -0.047 |
as | -0.046 |
men | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
Bruce | +0.267 |
Penny | +0.262 |
Cindy | +0.255 |
Emmy | +0.250 |
Lilly | +0.249 |
Neg logit contributions | |
we | -0.242 |
ep | -0.208 |
bel | -0.199 |
men | -0.196 |
angels | -0.188 |
Token | make |
Token ID | 787 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
we | +0.005 |
ep | +0.004 |
bel | +0.004 |
men | +0.004 |
ilot | +0.004 |
Neg logit contributions | |
Penny | -0.004 |
Bruce | -0.003 |
Cindy | -0.003 |
Lilly | -0.003 |
Emmy | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
we | +0.072 |
ep | +0.066 |
bel | +0.063 |
ilot | +0.062 |
ney | +0.062 |
Neg logit contributions | |
Penny | -0.047 |
Bruce | -0.045 |
Cindy | -0.045 |
Lilly | -0.043 |
Emmy | -0.043 |
Token | feel |
Token ID | 1254 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
we | +0.014 |
ep | +0.013 |
men | +0.012 |
anas | +0.012 |
Mark | +0.012 |
Neg logit contributions | |
Penny | -0.012 |
Cindy | -0.012 |
Lilly | -0.011 |
Bruce | -0.011 |
Emmy | -0.011 |
Token | better |
Token ID | 1365 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Bruce | +0.016 |
Cindy | +0.015 |
Penny | +0.015 |
Harriet | +0.015 |
Emmy | +0.015 |
Neg logit contributions | |
we | -0.012 |
ep | -0.012 |
songs | -0.011 |
bel | -0.011 |
song | -0.011 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Bruce | +0.011 |
Penny | +0.011 |
Cindy | +0.011 |
Emmy | +0.010 |
Harriet | +0.010 |
Neg logit contributions | |
we | -0.008 |
ep | -0.008 |
bel | -0.007 |
men | -0.006 |
Some | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
we | +0.086 |
ep | +0.077 |
bel | +0.071 |
men | +0.068 |
ilot | +0.067 |
Neg logit contributions | |
Bruce | -0.108 |
Penny | -0.108 |
Cindy | -0.105 |
Emmy | -0.102 |
Lilly | -0.102 |
Token | bottle |
Token ID | 9294 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
Bruce | +0.022 |
Penny | +0.021 |
Cindy | +0.020 |
Lilly | +0.020 |
Emmy | +0.020 |
Neg logit contributions | |
we | -0.011 |
ep | -0.010 |
bel | -0.009 |
men | -0.009 |
song | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Bruce | +0.185 |
Cindy | +0.182 |
Penny | +0.182 |
Emmy | +0.176 |
Lilly | +0.173 |
Neg logit contributions | |
we | -0.101 |
ep | -0.088 |
men | -0.075 |
bel | -0.074 |
ney | -0.072 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
we | +0.053 |
ep | +0.049 |
songs | +0.048 |
song | +0.045 |
ity | +0.044 |
Neg logit contributions | |
Bruce | -0.062 |
Harriet | -0.057 |
Penny | -0.057 |
Sophie | -0.055 |
Cody | -0.054 |
Token | ion |
Token ID | 295 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
Bruce | +0.045 |
Penny | +0.041 |
Harriet | +0.041 |
Cindy | +0.041 |
Emmy | +0.040 |
Neg logit contributions | |
we | -0.044 |
as | -0.039 |
ep | -0.039 |
men | -0.036 |
ves | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
Bruce | +0.324 |
Penny | +0.319 |
Emmy | +0.311 |
Cindy | +0.311 |
Lilly | +0.308 |
Neg logit contributions | |
we | -0.187 |
men | -0.136 |
ep | -0.131 |
angels | -0.117 |
ower | -0.115 |
Token | Anna |
Token ID | 11735 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
Bruce | +0.010 |
Penny | +0.010 |
Cindy | +0.009 |
Emmy | +0.009 |
Lilly | +0.009 |
Neg logit contributions | |
we | -0.008 |
ep | -0.008 |
bel | -0.007 |
men | -0.007 |
ilot | -0.007 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
we | +0.002 |
ep | +0.002 |
bel | +0.002 |
ilot | +0.002 |
men | +0.002 |
Neg logit contributions | |
Penny | -0.002 |
Bruce | -0.002 |
Cindy | -0.002 |
Emmy | -0.002 |
Lilly | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Bruce | +0.071 |
Penny | +0.069 |
Cindy | +0.066 |
Emmy | +0.063 |
Lilly | +0.063 |
Neg logit contributions | |
we | -0.099 |
ep | -0.092 |
bel | -0.086 |
men | -0.085 |
ilot | -0.084 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
we | +0.004 |
ep | +0.003 |
men | +0.003 |
bel | +0.003 |
ilot | +0.003 |
Neg logit contributions | |
Bruce | -0.013 |
Penny | -0.013 |
Cindy | -0.013 |
Emmy | -0.013 |
Lilly | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Penny | +0.017 |
Bruce | +0.017 |
Cindy | +0.017 |
Emmy | +0.016 |
Lilly | +0.016 |
Neg logit contributions | |
we | -0.013 |
ep | -0.012 |
men | -0.010 |
bel | -0.010 |
ilot | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Bruce | +0.010 |
Penny | +0.009 |
Sophie | +0.009 |
Cindy | +0.009 |
Lilly | +0.009 |
Neg logit contributions | |
we | -0.014 |
ep | -0.013 |
ity | -0.012 |
bel | -0.012 |
z | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
Penny | +0.014 |
Bruce | +0.013 |
Sophie | +0.013 |
Lilly | +0.013 |
Cindy | +0.013 |
Neg logit contributions | |
we | -0.026 |
ep | -0.024 |
ity | -0.023 |
bel | -0.023 |
men | -0.022 |
Token | " |
Token ID | 1 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
Bruce | +0.017 |
Penny | +0.016 |
Stella | +0.016 |
Sophie | +0.016 |
Cindy | +0.016 |
Neg logit contributions | |
we | -0.023 |
ilot | -0.017 |
angels | -0.017 |
ity | -0.017 |
bel | -0.017 |
Token | L |
Token ID | 43 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
we | +0.012 |
ep | +0.011 |
bel | +0.011 |
ilot | +0.011 |
as | +0.011 |
Neg logit contributions | |
Bruce | -0.009 |
Penny | -0.009 |
Cindy | -0.008 |
Sophie | -0.008 |
Lilly | -0.008 |
Token | ion |
Token ID | 295 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
we | +0.040 |
bel | +0.037 |
ep | +0.034 |
men | +0.034 |
songs | +0.033 |
Neg logit contributions | |
Penny | -0.031 |
Bruce | -0.031 |
Lilly | -0.030 |
Sophie | -0.030 |
Cindy | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
Penny | +0.285 |
Cindy | +0.281 |
Bruce | +0.280 |
Emmy | +0.277 |
Lilly | +0.272 |
Neg logit contributions | |
we | -0.201 |
ep | -0.182 |
men | -0.173 |
ney | -0.161 |
angels | -0.157 |
Token | can |
Token ID | 460 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
Penny | +0.035 |
Bruce | +0.035 |
Cindy | +0.033 |
Lilly | +0.032 |
Emmy | +0.032 |
Neg logit contributions | |
we | -0.048 |
ep | -0.044 |
bel | -0.042 |
ilot | -0.040 |
men | -0.040 |
Token | I |
Token ID | 314 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Penny | +0.030 |
Bruce | +0.029 |
Cindy | +0.028 |
Emmy | +0.027 |
Lilly | +0.026 |
Neg logit contributions | |
we | -0.050 |
ep | -0.048 |
bel | -0.046 |
ney | -0.046 |
ilot | -0.045 |
Token | have |
Token ID | 423 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
Penny | +0.117 |
Bruce | +0.115 |
Cindy | +0.111 |
Sophie | +0.108 |
Harriet | +0.107 |
Neg logit contributions | |
we | -0.117 |
ep | -0.115 |
bel | -0.111 |
ilot | -0.105 |
ney | -0.102 |
Token | your |
Token ID | 534 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ep | +0.019 |
we | +0.018 |
songs | +0.015 |
Some | +0.015 |
angels | +0.014 |
Neg logit contributions | |
Penny | -0.028 |
Bruce | -0.028 |
Jackie | -0.027 |
Lilly | -0.027 |
Emmy | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Penny | +0.083 |
Bruce | +0.083 |
Cindy | +0.080 |
Lilly | +0.078 |
Emmy | +0.078 |
Neg logit contributions | |
we | -0.072 |
ep | -0.065 |
bel | -0.060 |
ilot | -0.058 |
men | -0.058 |
Token | so |
Token ID | 523 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Penny | +0.047 |
Bruce | +0.046 |
Cindy | +0.045 |
Lilly | +0.044 |
Emmy | +0.044 |
Neg logit contributions | |
we | -0.049 |
ep | -0.045 |
bel | -0.042 |
ilot | -0.041 |
men | -0.041 |
Token | she |
Token ID | 673 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Penny | +0.014 |
Bruce | +0.014 |
Cindy | +0.013 |
Lilly | +0.013 |
Emmy | +0.013 |
Neg logit contributions | |
we | -0.025 |
ep | -0.023 |
bel | -0.022 |
men | -0.022 |
ilot | -0.022 |
Token | put |
Token ID | 1234 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Bruce | +0.051 |
Penny | +0.049 |
Cindy | +0.048 |
Emmy | +0.047 |
Lilly | +0.046 |
Neg logit contributions | |
we | -0.060 |
ep | -0.058 |
men | -0.052 |
bel | -0.051 |
anas | -0.049 |
Token | lot |
Token ID | 1256 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
Bruce | +0.049 |
Penny | +0.047 |
Cindy | +0.046 |
Emmy | +0.045 |
Harriet | +0.044 |
Neg logit contributions | |
we | -0.048 |
ep | -0.043 |
bel | -0.039 |
men | -0.037 |
angels | -0.037 |
Token | ion |
Token ID | 295 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
Bruce | +0.029 |
Penny | +0.028 |
Cindy | +0.027 |
Emmy | +0.026 |
Lilly | +0.025 |
Neg logit contributions | |
we | -0.053 |
ep | -0.050 |
bel | -0.046 |
men | -0.045 |
ilot | -0.045 |
Token | on |
Token ID | 319 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
Bruce | +0.295 |
Penny | +0.289 |
Cindy | +0.281 |
Emmy | +0.279 |
Lilly | +0.274 |
Neg logit contributions | |
we | -0.218 |
ep | -0.178 |
bel | -0.169 |
men | -0.166 |
z | -0.157 |
Token | it |
Token ID | 340 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
we | +0.025 |
ep | +0.023 |
bel | +0.021 |
men | +0.021 |
ilot | +0.020 |
Neg logit contributions | |
Bruce | -0.019 |
Penny | -0.019 |
Cindy | -0.018 |
Emmy | -0.018 |
Lilly | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Bruce | +0.029 |
Penny | +0.028 |
Cindy | +0.028 |
Emmy | +0.027 |
Lilly | +0.027 |
Neg logit contributions | |
we | -0.018 |
ep | -0.016 |
bel | -0.015 |
men | -0.014 |
ney | -0.014 |
Token | Mitt |
Token ID | 16627 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Bruce | +0.011 |
Cody | +0.010 |
Harriet | +0.010 |
Emmy | +0.010 |
Penny | +0.010 |
Neg logit contributions | |
we | -0.008 |
Blood | -0.007 |
Some | -0.007 |
men | -0.007 |
ep | -0.006 |
Token | ens |
Token ID | 641 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Penny | +0.062 |
Bruce | +0.059 |
Cindy | +0.056 |
Lilly | +0.055 |
Emmy | +0.054 |
Neg logit contributions | |
we | -0.147 |
ep | -0.139 |
bel | -0.134 |
ilot | -0.130 |
men | -0.129 |
Token | didn |
Token ID | 1422 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Bruce | +0.067 |
Penny | +0.067 |
Cindy | +0.065 |
Emmy | +0.063 |
Lilly | +0.063 |
Neg logit contributions | |
we | -0.060 |
ep | -0.054 |
bel | -0.050 |
men | -0.048 |
ilot | -0.047 |
Token | 't |
Token ID | 470 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
Bruce | +0.019 |
Penny | +0.019 |
Cindy | +0.018 |
Lilly | +0.018 |
Emmy | +0.018 |
Neg logit contributions | |
we | -0.019 |
ep | -0.017 |
bel | -0.016 |
men | -0.015 |
ilot | -0.015 |
Token | like |
Token ID | 588 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
Bruce | +0.009 |
Penny | +0.009 |
Cindy | +0.009 |
Emmy | +0.008 |
Lilly | +0.008 |
Neg logit contributions | |
we | -0.013 |
ep | -0.012 |
bel | -0.012 |
men | -0.011 |
ilot | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
Bruce | +0.021 |
Penny | +0.021 |
Cindy | +0.020 |
Emmy | +0.020 |
Lilly | +0.020 |
Neg logit contributions | |
we | -0.027 |
ep | -0.024 |
bel | -0.023 |
men | -0.022 |
ilot | -0.022 |
Token | lot |
Token ID | 1256 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
Bruce | +0.036 |
Penny | +0.035 |
Emmy | +0.034 |
Lilly | +0.033 |
Cindy | +0.033 |
Neg logit contributions | |
we | -0.026 |
ep | -0.023 |
bel | -0.021 |
men | -0.020 |
angels | -0.020 |
Token | ion |
Token ID | 295 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
Bruce | +0.033 |
Penny | +0.031 |
Emmy | +0.028 |
Cindy | +0.028 |
Harriet | +0.027 |
Neg logit contributions | |
we | -0.056 |
ep | -0.051 |
men | -0.048 |
bel | -0.047 |
angels | -0.047 |
Token | because |
Token ID | 780 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Bruce | +0.264 |
Penny | +0.259 |
Cindy | +0.251 |
Emmy | +0.246 |
Lilly | +0.243 |
Neg logit contributions | |
we | -0.234 |
ep | -0.198 |
men | -0.188 |
bel | -0.183 |
angels | -0.178 |
Token | it |
Token ID | 340 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
Penny | +0.011 |
Bruce | +0.011 |
Cindy | +0.011 |
Lilly | +0.010 |
Emmy | +0.010 |
Neg logit contributions | |
we | -0.017 |
ep | -0.016 |
bel | -0.015 |
ilot | -0.015 |
men | -0.015 |
Token | felt |
Token ID | 2936 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
Penny | +0.019 |
Bruce | +0.019 |
Cindy | +0.019 |
Lilly | +0.018 |
Emmy | +0.018 |
Neg logit contributions | |
we | -0.018 |
ep | -0.017 |
bel | -0.016 |
ilot | -0.015 |
men | -0.015 |
Token | bad |
Token ID | 2089 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
we | +0.011 |
ep | +0.010 |
songs | +0.009 |
bel | +0.009 |
song | +0.008 |
Neg logit contributions | |
Bruce | -0.017 |
Penny | -0.016 |
Harriet | -0.016 |
Emmy | -0.016 |
Cindy | -0.016 |
Token | on |
Token ID | 319 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
Bruce | +0.066 |
Penny | +0.065 |
Cindy | +0.064 |
Emmy | +0.061 |
Lilly | +0.061 |
Neg logit contributions | |
we | -0.061 |
ep | -0.053 |
bel | -0.050 |
men | -0.049 |
songs | -0.047 |
Token | out |
Token ID | 503 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
we | +0.017 |
ep | +0.016 |
bel | +0.015 |
songs | +0.014 |
angels | +0.014 |
Neg logit contributions | |
Bruce | -0.017 |
Penny | -0.016 |
Cindy | -0.015 |
Emmy | -0.015 |
Lilly | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
we | +0.003 |
ep | +0.003 |
bel | +0.002 |
men | +0.002 |
ilot | +0.002 |
Neg logit contributions | |
Bruce | -0.003 |
Penny | -0.003 |
Cindy | -0.003 |
Emmy | -0.003 |
Lilly | -0.003 |
Token | bottle |
Token ID | 9294 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
Bruce | +0.016 |
Penny | +0.015 |
Cindy | +0.015 |
Lilly | +0.015 |
Emmy | +0.015 |
Neg logit contributions | |
we | -0.010 |
ep | -0.010 |
bel | -0.009 |
ilot | -0.008 |
men | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Bruce | +0.177 |
Penny | +0.173 |
Cindy | +0.171 |
Emmy | +0.166 |
Lilly | +0.163 |
Neg logit contributions | |
we | -0.105 |
ep | -0.091 |
bel | -0.084 |
men | -0.080 |
ney | -0.078 |
Token | lot |
Token ID | 1256 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
we | +0.053 |
ep | +0.050 |
songs | +0.044 |
bel | +0.043 |
song | +0.042 |
Neg logit contributions | |
Bruce | -0.062 |
Penny | -0.060 |
Harriet | -0.057 |
Cindy | -0.057 |
Emmy | -0.056 |
Token | ion |
Token ID | 295 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
Bruce | +0.037 |
Penny | +0.035 |
Cindy | +0.034 |
Emmy | +0.033 |
Harriet | +0.032 |
Neg logit contributions | |
we | -0.050 |
ep | -0.047 |
as | -0.042 |
men | -0.042 |
Some | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Bruce | +0.306 |
Penny | +0.300 |
Emmy | +0.290 |
Cindy | +0.287 |
Jackie | +0.286 |
Neg logit contributions | |
we | -0.200 |
men | -0.151 |
ep | -0.149 |
bel | -0.141 |
z | -0.137 |
Token | put |
Token ID | 1234 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Bruce | +0.005 |
Penny | +0.005 |
Cindy | +0.004 |
Harriet | +0.004 |
Emmy | +0.004 |
Neg logit contributions | |
we | -0.005 |
ep | -0.005 |
bel | -0.004 |
men | -0.004 |
songs | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
Bruce | +0.048 |
Penny | +0.047 |
Cindy | +0.044 |
Emmy | +0.044 |
Lilly | +0.043 |
Neg logit contributions | |
we | -0.051 |
ep | -0.046 |
bel | -0.042 |
men | -0.040 |
z | -0.040 |
Token | on |
Token ID | 319 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
Penny | +0.025 |
Bruce | +0.025 |
Cindy | +0.024 |
Lilly | +0.023 |
Emmy | +0.023 |
Neg logit contributions | |
we | -0.023 |
ep | -0.020 |
bel | -0.019 |
men | -0.018 |
ilot | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
we | +0.024 |
ep | +0.022 |
songs | +0.020 |
men | +0.019 |
bel | +0.019 |
Neg logit contributions | |
Bruce | -0.023 |
Penny | -0.022 |
Cindy | -0.021 |
Emmy | -0.021 |
Lilly | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
we | +0.040 |
ep | +0.036 |
bel | +0.034 |
songs | +0.033 |
z | +0.032 |
Neg logit contributions | |
Bruce | -0.039 |
Penny | -0.038 |
Emmy | -0.037 |
Cindy | -0.037 |
Harriet | -0.037 |
Token | ball |
Token ID | 2613 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
we | +0.007 |
ep | +0.007 |
bel | +0.006 |
men | +0.006 |
ilot | +0.006 |
Neg logit contributions | |
Bruce | -0.010 |
Penny | -0.010 |
Cindy | -0.009 |
Emmy | -0.009 |
Lilly | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
Bruce | +0.002 |
Penny | +0.002 |
Cindy | +0.002 |
Emmy | +0.002 |
Lilly | +0.002 |
Neg logit contributions | |
we | -0.002 |
ep | -0.002 |
bel | -0.002 |
men | -0.002 |
ilot | -0.002 |
Token | z |
Token ID | 1976 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
we | +0.016 |
ep | +0.013 |
men | +0.012 |
bel | +0.012 |
z | +0.012 |
Neg logit contributions | |
Bruce | -0.016 |
Penny | -0.015 |
Harriet | -0.015 |
Cindy | -0.015 |
Emmy | -0.015 |
Token | ig |
Token ID | 328 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
we | +0.167 |
ep | +0.152 |
ney | +0.149 |
men | +0.146 |
bel | +0.146 |
Neg logit contributions | |
Penny | -0.146 |
Bruce | -0.145 |
Cindy | -0.145 |
Lilly | -0.142 |
Sophie | -0.139 |
Token | z |
Token ID | 89 |
Feature activation | -8.27e+00 |
Pos logit contributions | |
we | +0.095 |
ep | +0.081 |
anas | +0.079 |
ney | +0.074 |
Some | +0.071 |
Neg logit contributions | |
Penny | -0.270 |
Cindy | -0.264 |
Lilly | -0.261 |
Bruce | -0.260 |
Emmy | -0.256 |
Token | agging |
Token ID | 16406 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
we | +0.341 |
bel | +0.301 |
ney | +0.295 |
ep | +0.294 |
anas | +0.284 |
Neg logit contributions | |
Penny | -0.365 |
Bruce | -0.359 |
Cindy | -0.357 |
Lilly | -0.351 |
Sophie | -0.347 |
Token | around |
Token ID | 1088 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
we | +0.121 |
ep | +0.102 |
bel | +0.097 |
anas | +0.097 |
Some | +0.096 |
Neg logit contributions | |
Penny | -0.105 |
Bruce | -0.104 |
Cindy | -0.101 |
Lilly | -0.098 |
Emmy | -0.096 |
Token | the |
Token ID | 262 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
Penny | +0.013 |
Bruce | +0.013 |
Cindy | +0.013 |
Lilly | +0.012 |
Emmy | +0.012 |
Neg logit contributions | |
we | -0.016 |
ep | -0.015 |
bel | -0.014 |
ilot | -0.013 |
men | -0.013 |
Token | room |
Token ID | 2119 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Bruce | +0.005 |
Penny | +0.005 |
Cindy | +0.004 |
Emmy | +0.004 |
Lilly | +0.004 |
Neg logit contributions | |
we | -0.003 |
ep | -0.003 |
bel | -0.003 |
men | -0.003 |
ilot | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
Penny | +0.009 |
Bruce | +0.009 |
Cindy | +0.009 |
Lilly | +0.009 |
Emmy | +0.009 |
Neg logit contributions | |
we | -0.010 |
ep | -0.009 |
bel | -0.008 |
ilot | -0.008 |
men | -0.008 |
Token | fast |
Token ID | 3049 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
Bruce | +0.014 |
Penny | +0.014 |
Cindy | +0.014 |
Emmy | +0.013 |
Lilly | +0.013 |
Neg logit contributions | |
we | -0.008 |
ep | -0.007 |
bel | -0.007 |
men | -0.006 |
songs | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
we | +0.026 |
ep | +0.024 |
bel | +0.022 |
men | +0.021 |
songs | +0.020 |
Neg logit contributions | |
Bruce | -0.035 |
Penny | -0.035 |
Cindy | -0.034 |
Emmy | -0.033 |
Lilly | -0.033 |
Token | he |
Token ID | 339 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Bruce | +0.014 |
Penny | +0.014 |
Cindy | +0.014 |
Sophie | +0.013 |
Harriet | +0.013 |
Neg logit contributions | |
we | -0.014 |
ep | -0.013 |
bel | -0.012 |
men | -0.011 |
songs | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
we | +0.013 |
ep | +0.012 |
bel | +0.011 |
men | +0.011 |
ilot | +0.011 |
Neg logit contributions | |
Bruce | -0.013 |
Penny | -0.013 |
Cindy | -0.012 |
Emmy | -0.012 |
Lilly | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
Penny | +0.059 |
Bruce | +0.059 |
Cindy | +0.057 |
Lilly | +0.055 |
Emmy | +0.054 |
Neg logit contributions | |
we | -0.083 |
ep | -0.076 |
bel | -0.071 |
ney | -0.069 |
men | -0.069 |
Token | z |
Token ID | 89 |
Feature activation | -8.14e+00 |
Pos logit contributions | |
we | +0.015 |
men | +0.014 |
ilot | +0.014 |
anas | +0.014 |
angels | +0.014 |
Neg logit contributions | |
Emmy | -0.017 |
Cindy | -0.017 |
Penny | -0.017 |
Lilly | -0.017 |
Bruce | -0.017 |
Token | oom |
Token ID | 4207 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
we | +0.291 |
bel | +0.241 |
ep | +0.229 |
ney | +0.227 |
anas | +0.223 |
Neg logit contributions | |
Bruce | -0.410 |
Penny | -0.408 |
Cindy | -0.393 |
Lilly | -0.390 |
Sophie | -0.385 |
Token | !" |
Token ID | 2474 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
we | +0.197 |
ep | +0.174 |
bel | +0.171 |
ney | +0.160 |
anas | +0.159 |
Neg logit contributions | |
Penny | -0.172 |
Bruce | -0.170 |
Cindy | -0.165 |
Emmy | -0.160 |
Lilly | -0.160 |
Token | as |
Token ID | 355 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Penny | +0.030 |
Bruce | +0.030 |
Cindy | +0.029 |
Lilly | +0.028 |
Emmy | +0.028 |
Neg logit contributions | |
we | -0.036 |
ep | -0.033 |
bel | -0.031 |
ity | -0.030 |
men | -0.030 |
Token | he |
Token ID | 339 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
we | +0.005 |
ep | +0.005 |
bel | +0.004 |
men | +0.004 |
ilot | +0.004 |
Neg logit contributions | |
Bruce | -0.005 |
Penny | -0.005 |
Cindy | -0.004 |
Emmy | -0.004 |
Lilly | -0.004 |
Token | made |
Token ID | 925 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
we | +0.020 |
bel | +0.017 |
ilot | +0.017 |
angels | +0.017 |
ep | +0.017 |
Neg logit contributions | |
Penny | -0.015 |
Cindy | -0.014 |
Bruce | -0.014 |
Lilly | -0.014 |
Emmy | -0.014 |
Token | make |
Token ID | 787 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
we | +0.022 |
ep | +0.020 |
bel | +0.019 |
ilot | +0.018 |
men | +0.018 |
Neg logit contributions | |
Penny | -0.024 |
Bruce | -0.024 |
Cindy | -0.023 |
Lilly | -0.023 |
Emmy | -0.023 |
Token | sure |
Token ID | 1654 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
we | +0.078 |
ep | +0.071 |
bel | +0.065 |
men | +0.063 |
ilot | +0.062 |
Neg logit contributions | |
Bruce | -0.081 |
Penny | -0.081 |
Cindy | -0.078 |
Emmy | -0.076 |
Lilly | -0.076 |
Token | his |
Token ID | 465 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
we | +0.178 |
ep | +0.158 |
bel | +0.153 |
men | +0.149 |
angels | +0.143 |
Neg logit contributions | |
Penny | -0.200 |
Bruce | -0.199 |
Cindy | -0.193 |
Emmy | -0.188 |
Lilly | -0.188 |
Token | z |
Token ID | 1976 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
we | +0.071 |
ep | +0.062 |
bel | +0.057 |
men | +0.055 |
ilot | +0.055 |
Neg logit contributions | |
Penny | -0.092 |
Bruce | -0.091 |
Cindy | -0.087 |
Emmy | -0.086 |
Lilly | -0.086 |
Token | ig |
Token ID | 328 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
we | +0.165 |
ep | +0.148 |
men | +0.147 |
Mark | +0.145 |
bel | +0.144 |
Neg logit contributions | |
Penny | -0.137 |
Bruce | -0.132 |
Lilly | -0.127 |
Cindy | -0.125 |
Emmy | -0.120 |
Token | z |
Token ID | 89 |
Feature activation | -8.12e+00 |
Pos logit contributions | |
we | +0.171 |
ep | +0.156 |
anas | +0.146 |
Some | +0.143 |
songs | +0.137 |
Neg logit contributions | |
Penny | -0.183 |
Bruce | -0.177 |
Cindy | -0.172 |
Emmy | -0.171 |
Lilly | -0.171 |
Token | ags |
Token ID | 3775 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
we | +0.339 |
ep | +0.301 |
bel | +0.293 |
anas | +0.283 |
ney | +0.280 |
Neg logit contributions | |
Penny | -0.358 |
Bruce | -0.358 |
Cindy | -0.343 |
Lilly | -0.338 |
Emmy | -0.335 |
Token | were |
Token ID | 547 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
we | +0.033 |
ep | +0.029 |
bel | +0.027 |
ilot | +0.027 |
men | +0.027 |
Neg logit contributions | |
Bruce | -0.030 |
Penny | -0.030 |
Cindy | -0.029 |
Lilly | -0.028 |
Emmy | -0.028 |
Token | neat |
Token ID | 15049 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
we | +0.025 |
ep | +0.024 |
bel | +0.021 |
men | +0.021 |
songs | +0.020 |
Neg logit contributions | |
Bruce | -0.025 |
Penny | -0.025 |
Cindy | -0.024 |
Emmy | -0.023 |
Lilly | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Bruce | +0.020 |
Penny | +0.020 |
Cindy | +0.019 |
Lilly | +0.019 |
Emmy | +0.019 |
Neg logit contributions | |
we | -0.014 |
ep | -0.012 |
bel | -0.011 |
men | -0.011 |
ity | -0.011 |
Token | tidy |
Token ID | 43044 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
we | +0.007 |
ep | +0.007 |
bel | +0.006 |
men | +0.006 |
ity | +0.006 |
Neg logit contributions | |
Bruce | -0.007 |
Penny | -0.007 |
Cindy | -0.007 |
Lilly | -0.007 |
Emmy | -0.007 |
Token | on |
Token ID | 319 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Bruce | +0.116 |
Cindy | +0.112 |
Penny | +0.111 |
Emmy | +0.106 |
Lilly | +0.104 |
Neg logit contributions | |
we | -0.119 |
ep | -0.111 |
bel | -0.106 |
ilot | -0.099 |
men | -0.098 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
we | +0.006 |
ep | +0.005 |
bel | +0.005 |
men | +0.005 |
ilot | +0.005 |
Neg logit contributions | |
Penny | -0.004 |
Bruce | -0.004 |
Cindy | -0.004 |
Emmy | -0.004 |
Lilly | -0.004 |
Token | whenever |
Token ID | 8797 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Bruce | +0.049 |
Penny | +0.048 |
Cindy | +0.046 |
Lilly | +0.045 |
Emmy | +0.045 |
Neg logit contributions | |
we | -0.055 |
ep | -0.051 |
bel | -0.048 |
men | -0.046 |
ilot | -0.046 |
Token | she |
Token ID | 673 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
we | +0.085 |
ep | +0.076 |
men | +0.072 |
bel | +0.071 |
angels | +0.071 |
Neg logit contributions | |
Bruce | -0.077 |
Penny | -0.077 |
Cindy | -0.073 |
Lilly | -0.071 |
Emmy | -0.070 |
Token | un |
Token ID | 555 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
Bruce | +0.042 |
Penny | +0.041 |
Cindy | +0.041 |
Emmy | +0.040 |
Lilly | +0.039 |
Neg logit contributions | |
we | -0.036 |
ep | -0.033 |
bel | -0.030 |
men | -0.029 |
ney | -0.029 |
Token | z |
Token ID | 89 |
Feature activation | -8.06e+00 |
Pos logit contributions | |
Bruce | +0.020 |
Cindy | +0.020 |
Emmy | +0.020 |
Penny | +0.020 |
Lilly | +0.019 |
Neg logit contributions | |
we | -0.019 |
ep | -0.016 |
songs | -0.016 |
anas | -0.016 |
ity | -0.016 |
Token | ipped |
Token ID | 3949 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
we | +0.334 |
ep | +0.286 |
anas | +0.286 |
bel | +0.281 |
ney | +0.280 |
Neg logit contributions | |
Penny | -0.357 |
Bruce | -0.351 |
Cindy | -0.344 |
Lilly | -0.341 |
Emmy | -0.338 |
Token | her |
Token ID | 607 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
we | +0.066 |
ep | +0.061 |
bel | +0.058 |
men | +0.054 |
angels | +0.053 |
Neg logit contributions | |
Bruce | -0.066 |
Penny | -0.063 |
Cindy | -0.060 |
Harriet | -0.058 |
Emmy | -0.058 |
Token | cup |
Token ID | 6508 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
we | +0.021 |
ep | +0.019 |
bel | +0.017 |
men | +0.017 |
ilot | +0.017 |
Neg logit contributions | |
Bruce | -0.026 |
Penny | -0.026 |
Cindy | -0.025 |
Lilly | -0.025 |
Emmy | -0.025 |
Token | it |
Token ID | 340 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
we | +0.015 |
ep | +0.014 |
bel | +0.013 |
men | +0.013 |
ilot | +0.012 |
Neg logit contributions | |
Bruce | -0.016 |
Penny | -0.016 |
Cindy | -0.016 |
Emmy | -0.015 |
Lilly | -0.015 |
Token | would |
Token ID | 561 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
Bruce | +0.025 |
Penny | +0.025 |
Cindy | +0.024 |
Emmy | +0.023 |
Lilly | +0.023 |
Neg logit contributions | |
we | -0.024 |
ep | -0.021 |
bel | -0.020 |
men | -0.019 |
ilot | -0.019 |
Token | played |
Token ID | 2826 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
Penny | +0.012 |
Bruce | +0.012 |
Cindy | +0.012 |
Emmy | +0.011 |
Lilly | +0.011 |
Neg logit contributions | |
we | -0.010 |
ep | -0.010 |
ilot | -0.009 |
bel | -0.009 |
men | -0.009 |
Token | with |
Token ID | 351 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
Bruce | +0.002 |
Penny | +0.002 |
Cindy | +0.002 |
Lilly | +0.002 |
Holly | +0.002 |
Neg logit contributions | |
we | -0.003 |
ep | -0.002 |
ney | -0.002 |
bel | -0.002 |
ity | -0.002 |
Token | their |
Token ID | 511 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Bruce | +0.031 |
Penny | +0.030 |
Cindy | +0.030 |
Lilly | +0.028 |
Emmy | +0.028 |
Neg logit contributions | |
we | -0.044 |
ep | -0.040 |
bel | -0.038 |
ney | -0.036 |
ity | -0.036 |
Token | z |
Token ID | 1976 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
we | +0.045 |
bel | +0.038 |
ep | +0.038 |
anas | +0.038 |
ilot | +0.036 |
Neg logit contributions | |
Penny | -0.046 |
Cindy | -0.046 |
Bruce | -0.045 |
Emmy | -0.043 |
Lilly | -0.043 |
Token | ig |
Token ID | 328 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
we | +0.166 |
anas | +0.161 |
men | +0.158 |
Some | +0.157 |
bel | +0.155 |
Neg logit contributions | |
Cindy | -0.080 |
Penny | -0.079 |
Holly | -0.074 |
Lilly | -0.074 |
Ag | -0.073 |
Token | z |
Token ID | 89 |
Feature activation | -7.96e+00 |
Pos logit contributions | |
we | +0.135 |
Some | +0.123 |
anas | +0.119 |
Thunder | +0.114 |
Quick | +0.113 |
Neg logit contributions | |
Penny | -0.200 |
Emmy | -0.192 |
Cindy | -0.191 |
Lilly | -0.189 |
Bruce | -0.189 |
Token | ags |
Token ID | 3775 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
we | +0.341 |
bel | +0.299 |
anas | +0.290 |
ney | +0.287 |
men | +0.276 |
Neg logit contributions | |
Bruce | -0.342 |
Penny | -0.340 |
Cindy | -0.330 |
Lilly | -0.322 |
Emmy | -0.319 |
Token | every |
Token ID | 790 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
we | +0.028 |
anas | +0.024 |
ep | +0.024 |
bel | +0.023 |
ity | +0.023 |
Neg logit contributions | |
Bruce | -0.022 |
Penny | -0.021 |
Cindy | -0.021 |
Lilly | -0.020 |
Emmy | -0.020 |
Token | day |
Token ID | 1110 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
we | +0.118 |
bel | +0.102 |
anas | +0.102 |
ep | +0.100 |
men | +0.098 |
Neg logit contributions | |
Bruce | -0.075 |
Penny | -0.075 |
Cindy | -0.073 |
Lilly | -0.070 |
Emmy | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
we | +0.037 |
ep | +0.033 |
bel | +0.031 |
men | +0.030 |
ilot | +0.029 |
Neg logit contributions | |
Bruce | -0.038 |
Penny | -0.038 |
Cindy | -0.036 |
Lilly | -0.035 |
Emmy | -0.035 |
Token | They |
Token ID | 1119 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
we | +0.015 |
ep | +0.014 |
bel | +0.013 |
men | +0.012 |
ilot | +0.012 |
Neg logit contributions | |
Penny | -0.018 |
Bruce | -0.018 |
Cindy | -0.017 |
Emmy | -0.017 |
Lilly | -0.017 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
Bruce | +0.075 |
Penny | +0.074 |
Cindy | +0.072 |
Emmy | +0.070 |
Lilly | +0.070 |
Neg logit contributions | |
we | -0.042 |
ep | -0.036 |
bel | -0.033 |
men | -0.032 |
ilot | -0.031 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Bruce | +0.029 |
Cindy | +0.028 |
Penny | +0.027 |
Emmy | +0.026 |
Stella | +0.026 |
Neg logit contributions | |
we | -0.027 |
ep | -0.024 |
songs | -0.023 |
ity | -0.022 |
song | -0.022 |
Token | ." |
Token ID | 526 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
Bruce | +0.056 |
Penny | +0.055 |
Cindy | +0.054 |
Lilly | +0.052 |
Emmy | +0.052 |
Neg logit contributions | |
we | -0.050 |
ep | -0.045 |
bel | -0.040 |
men | -0.040 |
ilot | -0.040 |
Token | She |
Token ID | 1375 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
we | +0.001 |
ep | +0.001 |
bel | +0.001 |
ilot | +0.001 |
men | +0.001 |
Neg logit contributions | |
Bruce | -0.001 |
Penny | -0.001 |
Cindy | -0.001 |
Emmy | -0.001 |
Harriet | -0.001 |
Token | un |
Token ID | 555 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
Bruce | +0.065 |
Penny | +0.061 |
Cindy | +0.061 |
Emmy | +0.061 |
Lilly | +0.058 |
Neg logit contributions | |
we | -0.058 |
ep | -0.058 |
bel | -0.051 |
men | -0.049 |
ilot | -0.047 |
Token | z |
Token ID | 89 |
Feature activation | -7.92e+00 |
Pos logit contributions | |
Penny | +0.030 |
Emmy | +0.030 |
Cindy | +0.030 |
Bruce | +0.029 |
Lilly | +0.029 |
Neg logit contributions | |
we | -0.025 |
ilot | -0.022 |
ep | -0.022 |
songs | -0.021 |
angels | -0.021 |
Token | ipped |
Token ID | 3949 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
we | +0.341 |
ep | +0.298 |
bel | +0.296 |
ney | +0.287 |
anas | +0.282 |
Neg logit contributions | |
Penny | -0.352 |
Bruce | -0.345 |
Cindy | -0.333 |
Lilly | -0.329 |
Sophie | -0.327 |
Token | the |
Token ID | 262 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
we | +0.058 |
ep | +0.054 |
bel | +0.051 |
z | +0.049 |
songs | +0.048 |
Neg logit contributions | |
Bruce | -0.062 |
Penny | -0.057 |
Cindy | -0.055 |
Emmy | -0.055 |
Harriet | -0.054 |
Token | coat |
Token ID | 13209 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
Bruce | +0.016 |
Cindy | +0.015 |
Penny | +0.015 |
Sophie | +0.014 |
Emmy | +0.014 |
Neg logit contributions | |
we | -0.015 |
ep | -0.013 |
bel | -0.012 |
songs | -0.012 |
song | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
Penny | +0.003 |
Bruce | +0.003 |
Cindy | +0.003 |
Emmy | +0.003 |
Lilly | +0.003 |
Neg logit contributions | |
we | -0.003 |
ep | -0.003 |
bel | -0.003 |
anas | -0.003 |
ilot | -0.003 |
Token | gently |
Token ID | 15165 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
we | +0.003 |
ep | +0.003 |
bel | +0.003 |
men | +0.003 |
songs | +0.002 |
Neg logit contributions | |
Bruce | -0.003 |
Penny | -0.003 |
Cindy | -0.003 |
Emmy | -0.003 |
Lilly | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
Bruce | +0.028 |
Penny | +0.028 |
Cindy | +0.027 |
Emmy | +0.026 |
Lilly | +0.026 |
Neg logit contributions | |
we | -0.025 |
ep | -0.022 |
bel | -0.021 |
men | -0.020 |
angels | -0.019 |
Token | around |
Token ID | 1088 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
we | +0.002 |
ep | +0.001 |
z | +0.001 |
bel | +0.001 |
men | +0.001 |
Neg logit contributions | |
Bruce | -0.002 |
Penny | -0.002 |
Harriet | -0.002 |
Emmy | -0.002 |
Cindy | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
Bruce | +0.023 |
Penny | +0.023 |
Cindy | +0.022 |
Emmy | +0.021 |
Lilly | +0.021 |
Neg logit contributions | |
we | -0.029 |
ep | -0.027 |
bel | -0.025 |
men | -0.024 |
ilot | -0.024 |
Token | z |
Token ID | 1976 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
Penny | +0.017 |
Bruce | +0.017 |
Cindy | +0.016 |
Lilly | +0.015 |
Emmy | +0.015 |
Neg logit contributions | |
we | -0.022 |
ep | -0.020 |
bel | -0.019 |
ilot | -0.018 |
men | -0.018 |
Token | ig |
Token ID | 328 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
we | +0.135 |
ep | +0.117 |
bel | +0.112 |
men | +0.111 |
songs | +0.106 |
Neg logit contributions | |
Penny | -0.154 |
Bruce | -0.153 |
Cindy | -0.148 |
Lilly | -0.145 |
Sophie | -0.144 |
Token | z |
Token ID | 89 |
Feature activation | -7.92e+00 |
Pos logit contributions | |
we | +0.166 |
songs | +0.159 |
song | +0.152 |
ep | +0.149 |
anas | +0.146 |
Neg logit contributions | |
Penny | -0.185 |
Cindy | -0.181 |
Lilly | -0.178 |
Bruce | -0.177 |
Emmy | -0.173 |
Token | ags |
Token ID | 3775 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
we | +0.321 |
bel | +0.272 |
ep | +0.265 |
men | +0.260 |
ney | +0.258 |
Neg logit contributions | |
Penny | -0.377 |
Bruce | -0.373 |
Cindy | -0.364 |
Lilly | -0.361 |
Sophie | -0.356 |
Token | . |
Token ID | 13 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
we | +0.028 |
ep | +0.025 |
bel | +0.024 |
anas | +0.024 |
ilot | +0.024 |
Neg logit contributions | |
Bruce | -0.022 |
Penny | -0.022 |
Cindy | -0.021 |
Lilly | -0.021 |
Sophie | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
we | +0.027 |
ep | +0.025 |
bel | +0.023 |
ity | +0.022 |
men | +0.022 |
Neg logit contributions | |
Bruce | -0.025 |
Cindy | -0.025 |
Penny | -0.025 |
Lilly | -0.024 |
Emmy | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
we | +0.021 |
ep | +0.018 |
ity | +0.018 |
bel | +0.018 |
men | +0.018 |
Neg logit contributions | |
Cindy | -0.016 |
Bruce | -0.015 |
Penny | -0.015 |
Lilly | -0.014 |
Emmy | -0.014 |
Token | When |
Token ID | 2215 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
we | +0.013 |
ity | +0.011 |
ep | +0.011 |
anas | +0.010 |
bel | +0.010 |
Neg logit contributions | |
Cindy | -0.016 |
Bruce | -0.015 |
Holly | -0.015 |
Penny | -0.014 |
Stella | -0.014 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
we | +0.074 |
ep | +0.070 |
bel | +0.062 |
songs | +0.061 |
ilot | +0.061 |
Neg logit contributions | |
Penny | -0.085 |
Bruce | -0.085 |
Cindy | -0.081 |
Emmy | -0.079 |
Lilly | -0.079 |
Token | with |
Token ID | 351 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
Bruce | +0.042 |
Penny | +0.041 |
Cindy | +0.041 |
Emmy | +0.040 |
Lilly | +0.039 |
Neg logit contributions | |
we | -0.056 |
ep | -0.054 |
ney | -0.052 |
ilot | -0.052 |
bel | -0.052 |
Token | their |
Token ID | 511 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Bruce | +0.031 |
Penny | +0.031 |
Cindy | +0.030 |
Lilly | +0.029 |
Emmy | +0.029 |
Neg logit contributions | |
we | -0.030 |
ep | -0.027 |
bel | -0.026 |
ilot | -0.024 |
ney | -0.024 |
Token | z |
Token ID | 1976 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
we | +0.049 |
ep | +0.042 |
bel | +0.041 |
anas | +0.040 |
ney | +0.038 |
Neg logit contributions | |
Penny | -0.051 |
Cindy | -0.051 |
Bruce | -0.050 |
Lilly | -0.049 |
Emmy | -0.049 |
Token | ig |
Token ID | 328 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
we | +0.167 |
men | +0.159 |
anas | +0.158 |
bel | +0.157 |
Some | +0.156 |
Neg logit contributions | |
Penny | -0.092 |
Cindy | -0.092 |
Lilly | -0.087 |
Bruce | -0.085 |
Holly | -0.084 |
Token | z |
Token ID | 89 |
Feature activation | -7.91e+00 |
Pos logit contributions | |
we | +0.133 |
Some | +0.121 |
Quick | +0.114 |
ep | +0.113 |
Thunder | +0.111 |
Neg logit contributions | |
Penny | -0.205 |
Cindy | -0.197 |
Emmy | -0.197 |
Lilly | -0.195 |
Bruce | -0.194 |
Token | ags |
Token ID | 3775 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
we | +0.326 |
bel | +0.287 |
ep | +0.273 |
anas | +0.271 |
ney | +0.271 |
Neg logit contributions | |
Bruce | -0.354 |
Penny | -0.353 |
Cindy | -0.342 |
Lilly | -0.335 |
Emmy | -0.332 |
Token | . |
Token ID | 13 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
we | +0.033 |
ep | +0.029 |
bel | +0.027 |
anas | +0.027 |
men | +0.026 |
Neg logit contributions | |
Bruce | -0.027 |
Penny | -0.026 |
Cindy | -0.026 |
Lilly | -0.025 |
Emmy | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
we | +0.030 |
ep | +0.028 |
bel | +0.026 |
men | +0.024 |
ity | +0.024 |
Neg logit contributions | |
Bruce | -0.034 |
Penny | -0.034 |
Cindy | -0.033 |
Lilly | -0.032 |
Emmy | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
we | +0.032 |
ep | +0.028 |
bel | +0.027 |
ity | +0.026 |
men | +0.026 |
Neg logit contributions | |
Bruce | -0.028 |
Penny | -0.028 |
Cindy | -0.027 |
Lilly | -0.027 |
Emmy | -0.026 |
Token | Bob |
Token ID | 18861 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
we | +0.021 |
bel | +0.018 |
ep | +0.017 |
ity | +0.017 |
ilot | +0.016 |
Neg logit contributions | |
Bruce | -0.030 |
Penny | -0.029 |
Cindy | -0.029 |
Lilly | -0.028 |
Sophie | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
we | +0.006 |
ep | +0.005 |
z | +0.005 |
bel | +0.005 |
songs | +0.005 |
Neg logit contributions | |
Bruce | -0.006 |
Penny | -0.006 |
Emmy | -0.006 |
Harriet | -0.006 |
Cindy | -0.006 |
Token | ran |
Token ID | 4966 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
we | +0.002 |
ep | +0.002 |
z | +0.001 |
bel | +0.001 |
men | +0.001 |
Neg logit contributions | |
Bruce | -0.002 |
Penny | -0.002 |
Cindy | -0.002 |
Harriet | -0.002 |
Emmy | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
we | +0.007 |
ep | +0.006 |
songs | +0.006 |
z | +0.006 |
angels | +0.006 |
Neg logit contributions | |
Bruce | -0.010 |
Penny | -0.009 |
Emmy | -0.009 |
Harriet | -0.009 |
Lilly | -0.009 |
Token | z |
Token ID | 1976 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
Bruce | +0.017 |
Penny | +0.017 |
Cindy | +0.016 |
Emmy | +0.016 |
Lilly | +0.016 |
Neg logit contributions | |
we | -0.016 |
ep | -0.014 |
bel | -0.013 |
men | -0.013 |
z | -0.013 |
Token | ig |
Token ID | 328 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
we | +0.154 |
ney | +0.141 |
songs | +0.138 |
song | +0.138 |
anas | +0.138 |
Neg logit contributions | |
Penny | -0.120 |
Cindy | -0.117 |
Lilly | -0.116 |
Bruce | -0.116 |
Sophie | -0.113 |
Token | z |
Token ID | 89 |
Feature activation | -7.90e+00 |
Pos logit contributions | |
songs | +0.091 |
we | +0.089 |
song | +0.086 |
anas | +0.084 |
Some | +0.082 |
Neg logit contributions | |
Penny | -0.240 |
Cindy | -0.236 |
Lilly | -0.234 |
Emmy | -0.230 |
Bruce | -0.228 |
Token | agging |
Token ID | 16406 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
we | +0.343 |
bel | +0.302 |
ney | +0.297 |
anas | +0.289 |
ep | +0.288 |
Neg logit contributions | |
Penny | -0.339 |
Bruce | -0.330 |
Cindy | -0.327 |
Lilly | -0.322 |
Sophie | -0.318 |
Token | this |
Token ID | 428 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
we | +0.122 |
ep | +0.109 |
anas | +0.102 |
bel | +0.101 |
men | +0.100 |
Neg logit contributions | |
Penny | -0.078 |
Bruce | -0.077 |
Cindy | -0.075 |
Lilly | -0.072 |
Emmy | -0.071 |
Token | way |
Token ID | 835 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
Penny | +0.025 |
Bruce | +0.025 |
Cindy | +0.024 |
Emmy | +0.023 |
Lilly | +0.023 |
Neg logit contributions | |
we | -0.023 |
ep | -0.021 |
bel | -0.019 |
men | -0.019 |
ilot | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
Bruce | +0.043 |
Penny | +0.042 |
Cindy | +0.040 |
Emmy | +0.039 |
Lilly | +0.039 |
Neg logit contributions | |
we | -0.042 |
ep | -0.037 |
bel | -0.035 |
z | -0.034 |
men | -0.034 |
Token | that |
Token ID | 326 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
we | +0.003 |
ep | +0.003 |
bel | +0.003 |
men | +0.003 |
angels | +0.003 |
Neg logit contributions | |
Bruce | -0.003 |
Penny | -0.003 |
Cindy | -0.003 |
Emmy | -0.003 |
Lilly | -0.003 |
Token | me |
Token ID | 502 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
we | +0.065 |
ep | +0.059 |
bel | +0.055 |
men | +0.053 |
ilot | +0.052 |
Neg logit contributions | |
Bruce | -0.063 |
Penny | -0.063 |
Cindy | -0.060 |
Emmy | -0.059 |
Lilly | -0.059 |
Token | adows |
Token ID | 9797 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
Penny | +0.112 |
Bruce | +0.111 |
Cindy | +0.108 |
Lilly | +0.105 |
Emmy | +0.104 |
Neg logit contributions | |
we | -0.114 |
ep | -0.104 |
bel | -0.097 |
men | -0.094 |
ilot | -0.091 |
Token | , |
Token ID | 11 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
we | +0.120 |
ep | +0.109 |
bel | +0.101 |
men | +0.098 |
ilot | +0.097 |
Neg logit contributions | |
Bruce | -0.115 |
Penny | -0.115 |
Cindy | -0.111 |
Emmy | -0.107 |
Lilly | -0.107 |
Token | z |
Token ID | 1976 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
Bruce | +0.016 |
Penny | +0.016 |
Cindy | +0.016 |
Emmy | +0.015 |
Lilly | +0.015 |
Neg logit contributions | |
we | -0.016 |
ep | -0.014 |
bel | -0.013 |
men | -0.013 |
z | -0.013 |
Token | ig |
Token ID | 328 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
we | +0.136 |
ep | +0.125 |
men | +0.119 |
ney | +0.118 |
bel | +0.117 |
Neg logit contributions | |
Penny | -0.134 |
Bruce | -0.132 |
Cindy | -0.130 |
Lilly | -0.125 |
Sophie | -0.123 |
Token | z |
Token ID | 89 |
Feature activation | -7.85e+00 |
Pos logit contributions | |
we | +0.096 |
ep | +0.080 |
anas | +0.077 |
songs | +0.075 |
ney | +0.074 |
Neg logit contributions | |
Penny | -0.238 |
Cindy | -0.233 |
Bruce | -0.231 |
Lilly | -0.227 |
Emmy | -0.225 |
Token | agging |
Token ID | 16406 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
we | +0.322 |
ep | +0.281 |
bel | +0.279 |
ney | +0.271 |
anas | +0.266 |
Neg logit contributions | |
Penny | -0.361 |
Bruce | -0.358 |
Cindy | -0.350 |
Lilly | -0.343 |
Sophie | -0.339 |
Token | with |
Token ID | 351 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
we | +0.101 |
ep | +0.089 |
bel | +0.083 |
men | +0.081 |
anas | +0.081 |
Neg logit contributions | |
Bruce | -0.092 |
Penny | -0.091 |
Cindy | -0.088 |
Lilly | -0.084 |
Emmy | -0.083 |
Token | joy |
Token ID | 8716 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
Penny | +0.030 |
Bruce | +0.030 |
Cindy | +0.029 |
Emmy | +0.028 |
Lilly | +0.028 |
Neg logit contributions | |
we | -0.038 |
ep | -0.035 |
bel | -0.032 |
men | -0.031 |
ilot | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
Bruce | +0.029 |
Penny | +0.029 |
Cindy | +0.028 |
Emmy | +0.027 |
Lilly | +0.027 |
Neg logit contributions | |
we | -0.031 |
ep | -0.029 |
bel | -0.027 |
men | -0.026 |
ilot | -0.026 |
Token | Eventually |
Token ID | 16178 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
we | +0.024 |
ep | +0.021 |
bel | +0.020 |
ilot | +0.020 |
men | +0.020 |
Neg logit contributions | |
Penny | -0.024 |
Bruce | -0.024 |
Cindy | -0.023 |
Emmy | -0.023 |
Lilly | -0.022 |
Token | check |
Token ID | 2198 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
ep | +0.004 |
bel | +0.003 |
ilot | +0.003 |
men | +0.003 |
we | +0.003 |
Neg logit contributions | |
Bruce | -0.006 |
Emmy | -0.006 |
Penny | -0.006 |
Cindy | -0.006 |
Jackie | -0.006 |
Token | for |
Token ID | 329 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
we | +0.001 |
ep | +0.001 |
anas | +0.001 |
ney | +0.001 |
bel | +0.001 |
Neg logit contributions | |
Penny | -0.001 |
Lilly | -0.001 |
Cindy | -0.001 |
Hannah | -0.001 |
Bruce | -0.001 |
Token | more |
Token ID | 517 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Penny | +0.000 |
Bruce | +0.000 |
Cindy | +0.000 |
Lilly | +0.000 |
Emmy | +0.000 |
Neg logit contributions | |
we | -0.001 |
ep | -0.001 |
bel | -0.000 |
ilot | -0.000 |
ney | -0.000 |
Token | z |
Token ID | 1976 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
Penny | +0.005 |
Cindy | +0.005 |
Bruce | +0.005 |
Lilly | +0.005 |
Emmy | +0.005 |
Neg logit contributions | |
we | -0.005 |
ep | -0.004 |
bel | -0.004 |
ilot | -0.004 |
anas | -0.004 |
Token | ig |
Token ID | 328 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
anas | +0.156 |
ney | +0.155 |
we | +0.154 |
song | +0.151 |
men | +0.151 |
Neg logit contributions | |
Penny | -0.099 |
Lilly | -0.094 |
Holly | -0.094 |
Cindy | -0.093 |
Hannah | -0.090 |
Token | z |
Token ID | 89 |
Feature activation | -7.84e+00 |
Pos logit contributions | |
songs | +0.127 |
anas | +0.125 |
Some | +0.121 |
Quick | +0.116 |
song | +0.116 |
Neg logit contributions | |
Penny | -0.199 |
Lilly | -0.195 |
Cindy | -0.192 |
Emmy | -0.188 |
Ag | -0.182 |
Token | ags |
Token ID | 3775 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
we | +0.344 |
bel | +0.323 |
ney | +0.305 |
anas | +0.301 |
ep | +0.291 |
Neg logit contributions | |
Penny | -0.324 |
Bruce | -0.311 |
Cindy | -0.305 |
Lilly | -0.304 |
Sophie | -0.300 |
Token | . |
Token ID | 13 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
we | +0.036 |
ep | +0.033 |
anas | +0.032 |
bel | +0.032 |
ilot | +0.031 |
Neg logit contributions | |
Penny | -0.026 |
Bruce | -0.026 |
Lilly | -0.025 |
Cindy | -0.025 |
Sophie | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
we | +0.035 |
ep | +0.032 |
bel | +0.029 |
men | +0.027 |
ilot | +0.027 |
Neg logit contributions | |
Penny | -0.046 |
Bruce | -0.046 |
Cindy | -0.044 |
Lilly | -0.044 |
Emmy | -0.043 |
Token | find |
Token ID | 1064 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
ep | +0.004 |
bel | +0.003 |
ilot | +0.003 |
we | +0.003 |
angels | +0.003 |
Neg logit contributions | |
Bruce | -0.006 |
Emmy | -0.006 |
Penny | -0.006 |
Cindy | -0.006 |
Lilly | -0.006 |
Token | none |
Token ID | 4844 |
Feature activation | +7.78e-03 |
Pos logit contributions | |
we | +0.034 |
ep | +0.031 |
bel | +0.028 |
anas | +0.027 |
ilot | +0.027 |
Neg logit contributions | |
Penny | -0.038 |
Bruce | -0.038 |
Cindy | -0.036 |
Lilly | -0.036 |
Emmy | -0.035 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
we | +0.006 |
ep | +0.006 |
men | +0.005 |
bel | +0.005 |
ilot | +0.005 |
Neg logit contributions | |
Penny | -0.008 |
Bruce | -0.008 |
Cindy | -0.007 |
Lilly | -0.007 |
Emmy | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
we | +0.085 |
ep | +0.078 |
bel | +0.073 |
men | +0.071 |
ilot | +0.070 |
Neg logit contributions | |
Penny | -0.065 |
Bruce | -0.065 |
Cindy | -0.062 |
Emmy | -0.060 |
Lilly | -0.060 |
Token | was |
Token ID | 373 |
Feature activation | -8.32e-02 |
Pos logit contributions | |
Penny | +0.014 |
Bruce | +0.013 |
Cindy | +0.013 |
Emmy | +0.013 |
Lilly | +0.013 |
Neg logit contributions | |
we | -0.012 |
ep | -0.011 |
bel | -0.011 |
ilot | -0.010 |
anas | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
we | +0.003 |
ep | +0.003 |
songs | +0.002 |
men | +0.002 |
song | +0.002 |
Neg logit contributions | |
Bruce | -0.004 |
Cindy | -0.004 |
Penny | -0.004 |
Harriet | -0.004 |
oured | -0.004 |
Token | co |
Token ID | 763 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Bruce | +0.015 |
Penny | +0.015 |
Cindy | +0.014 |
Emmy | +0.014 |
Lilly | +0.014 |
Neg logit contributions | |
we | -0.010 |
ep | -0.009 |
men | -0.008 |
bel | -0.008 |
songs | -0.008 |
Token | z |
Token ID | 89 |
Feature activation | -7.84e+00 |
Pos logit contributions | |
ep | +0.028 |
we | +0.026 |
Blood | +0.023 |
Some | +0.022 |
bel | +0.022 |
Neg logit contributions | |
Penny | -0.054 |
Cindy | -0.054 |
Lilly | -0.053 |
Bruce | -0.053 |
Hannah | -0.053 |
Token | iest |
Token ID | 6386 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
we | +0.321 |
ep | +0.290 |
bel | +0.280 |
ney | +0.264 |
men | +0.262 |
Neg logit contributions | |
Bruce | -0.358 |
Penny | -0.358 |
Cindy | -0.343 |
Lilly | -0.338 |
Sophie | -0.336 |
Token | shelter |
Token ID | 11772 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
we | +0.117 |
ep | +0.108 |
bel | +0.100 |
ilot | +0.096 |
men | +0.096 |
Neg logit contributions | |
Penny | -0.117 |
Bruce | -0.117 |
Cindy | -0.115 |
Lilly | -0.111 |
Emmy | -0.110 |
Token | ever |
Token ID | 1683 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
Bruce | +0.064 |
Penny | +0.064 |
Cindy | +0.061 |
Emmy | +0.060 |
Lilly | +0.059 |
Neg logit contributions | |
we | -0.060 |
ep | -0.054 |
bel | -0.050 |
men | -0.049 |
ilot | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
we | +0.121 |
ep | +0.102 |
ity | +0.094 |
z | +0.088 |
songs | +0.088 |
Neg logit contributions | |
Bruce | -0.167 |
Penny | -0.162 |
Cindy | -0.162 |
Harriet | -0.155 |
Hannah | -0.153 |
Token | had |
Token ID | 550 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
Bruce | +0.005 |
Penny | +0.005 |
Cindy | +0.005 |
Emmy | +0.005 |
Harriet | +0.005 |
Neg logit contributions | |
we | -0.005 |
ep | -0.005 |
bel | -0.005 |
men | -0.005 |
songs | -0.004 |
Token | while |
Token ID | 981 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Bruce | +0.011 |
Penny | +0.011 |
Cindy | +0.011 |
Emmy | +0.011 |
Lilly | +0.011 |
Neg logit contributions | |
we | -0.015 |
ep | -0.013 |
bel | -0.013 |
men | -0.012 |
ilot | -0.012 |
Token | writing |
Token ID | 3597 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
we | +0.085 |
ep | +0.076 |
men | +0.070 |
bel | +0.070 |
ilot | +0.069 |
Neg logit contributions | |
Penny | -0.078 |
Bruce | -0.077 |
Cindy | -0.074 |
Emmy | -0.073 |
Lilly | -0.072 |
Token | his |
Token ID | 465 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
we | +0.079 |
ep | +0.074 |
bel | +0.069 |
men | +0.067 |
ilot | +0.065 |
Neg logit contributions | |
Bruce | -0.071 |
Penny | -0.071 |
Cindy | -0.069 |
Lilly | -0.066 |
Emmy | -0.066 |
Token | z |
Token ID | 1976 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
we | +0.059 |
ep | +0.051 |
bel | +0.049 |
anas | +0.049 |
men | +0.048 |
Neg logit contributions | |
Penny | -0.059 |
Cindy | -0.057 |
Bruce | -0.057 |
Emmy | -0.055 |
Lilly | -0.055 |
Token | ig |
Token ID | 328 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
we | +0.146 |
men | +0.135 |
ep | +0.132 |
anas | +0.131 |
bel | +0.129 |
Neg logit contributions | |
Penny | -0.119 |
Cindy | -0.114 |
Lilly | -0.113 |
Bruce | -0.111 |
Emmy | -0.107 |
Token | z |
Token ID | 89 |
Feature activation | -7.81e+00 |
Pos logit contributions | |
we | +0.181 |
ep | +0.163 |
anas | +0.149 |
bel | +0.149 |
men | +0.146 |
Neg logit contributions | |
Penny | -0.177 |
Bruce | -0.172 |
Cindy | -0.166 |
Emmy | -0.165 |
Lilly | -0.164 |
Token | ags |
Token ID | 3775 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
we | +0.317 |
ep | +0.280 |
bel | +0.268 |
men | +0.256 |
anas | +0.256 |
Neg logit contributions | |
Penny | -0.362 |
Bruce | -0.361 |
Cindy | -0.350 |
Lilly | -0.343 |
Emmy | -0.341 |
Token | , |
Token ID | 11 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
we | +0.025 |
ep | +0.022 |
bel | +0.020 |
men | +0.020 |
ilot | +0.020 |
Neg logit contributions | |
Penny | -0.025 |
Bruce | -0.025 |
Cindy | -0.024 |
Emmy | -0.024 |
Lilly | -0.024 |
Token | he |
Token ID | 339 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
Bruce | +0.015 |
Penny | +0.015 |
Cindy | +0.014 |
Emmy | +0.014 |
Lilly | +0.014 |
Neg logit contributions | |
we | -0.014 |
ep | -0.013 |
bel | -0.012 |
men | -0.012 |
angels | -0.011 |
Token | heard |
Token ID | 2982 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
we | +0.025 |
ep | +0.023 |
bel | +0.021 |
men | +0.020 |
ilot | +0.020 |
Neg logit contributions | |
Bruce | -0.026 |
Penny | -0.026 |
Cindy | -0.025 |
Lilly | -0.024 |
Emmy | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
we | +0.153 |
ep | +0.137 |
bel | +0.127 |
ilot | +0.122 |
men | +0.122 |
Neg logit contributions | |
Penny | -0.171 |
Bruce | -0.171 |
Cindy | -0.165 |
Emmy | -0.161 |
Lilly | -0.161 |
Token | are |
Token ID | 389 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Bruce | +0.041 |
Penny | +0.040 |
Cindy | +0.039 |
Lilly | +0.038 |
Emmy | +0.038 |
Neg logit contributions | |
we | -0.039 |
ep | -0.035 |
bel | -0.033 |
men | -0.032 |
ilot | -0.032 |
Token | so |
Token ID | 523 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
we | +0.007 |
ep | +0.007 |
bel | +0.006 |
men | +0.006 |
ilot | +0.006 |
Neg logit contributions | |
Bruce | -0.008 |
Penny | -0.008 |
Cindy | -0.008 |
Emmy | -0.008 |
Lilly | -0.008 |
Token | many |
Token ID | 867 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Penny | +0.020 |
Bruce | +0.020 |
Cindy | +0.019 |
Emmy | +0.019 |
Lilly | +0.019 |
Neg logit contributions | |
we | -0.016 |
ep | -0.014 |
bel | -0.013 |
men | -0.013 |
ilot | -0.013 |
Token | z |
Token ID | 1976 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
we | +0.067 |
ep | +0.060 |
songs | +0.053 |
men | +0.052 |
bel | +0.052 |
Neg logit contributions | |
Penny | -0.100 |
Bruce | -0.100 |
Cindy | -0.096 |
Emmy | -0.094 |
Lilly | -0.094 |
Token | ig |
Token ID | 328 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
we | +0.120 |
ep | +0.109 |
bel | +0.102 |
men | +0.101 |
anas | +0.099 |
Neg logit contributions | |
Bruce | -0.142 |
Penny | -0.140 |
Cindy | -0.135 |
Lilly | -0.132 |
Emmy | -0.130 |
Token | z |
Token ID | 89 |
Feature activation | -7.78e+00 |
Pos logit contributions | |
we | +0.161 |
ep | +0.147 |
bel | +0.136 |
anas | +0.132 |
men | +0.132 |
Neg logit contributions | |
Penny | -0.169 |
Bruce | -0.168 |
Cindy | -0.162 |
Emmy | -0.158 |
Lilly | -0.158 |
Token | ags |
Token ID | 3775 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
we | +0.317 |
ep | +0.280 |
bel | +0.271 |
men | +0.256 |
anas | +0.255 |
Neg logit contributions | |
Bruce | -0.359 |
Penny | -0.357 |
Cindy | -0.345 |
Lilly | -0.337 |
Emmy | -0.335 |
Token | ," |
Token ID | 553 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
we | +0.013 |
ep | +0.012 |
bel | +0.011 |
men | +0.010 |
ilot | +0.010 |
Neg logit contributions | |
Bruce | -0.012 |
Penny | -0.012 |
Cindy | -0.011 |
Lilly | -0.011 |
Emmy | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
Penny | +0.064 |
Bruce | +0.064 |
Cindy | +0.061 |
Emmy | +0.060 |
Lilly | +0.059 |
Neg logit contributions | |
we | -0.090 |
ep | -0.082 |
bel | -0.077 |
men | -0.075 |
ilot | -0.074 |
Token | said |
Token ID | 531 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
we | +0.026 |
ep | +0.024 |
bel | +0.022 |
men | +0.022 |
ilot | +0.022 |
Neg logit contributions | |
Penny | -0.014 |
Bruce | -0.014 |
Cindy | -0.013 |
Lilly | -0.013 |
Emmy | -0.013 |
Token | nervously |
Token ID | 43324 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Bruce | +0.078 |
Penny | +0.078 |
Cindy | +0.075 |
Emmy | +0.073 |
Lilly | +0.073 |
Neg logit contributions | |
we | -0.079 |
ep | -0.072 |
bel | -0.066 |
men | -0.065 |
ilot | -0.064 |
Token | took |
Token ID | 1718 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
ep | +0.006 |
we | +0.006 |
bel | +0.005 |
ilot | +0.005 |
men | +0.005 |
Neg logit contributions | |
Bruce | -0.007 |
Penny | -0.007 |
Cindy | -0.007 |
Emmy | -0.007 |
Harriet | -0.007 |
Token | turns |
Token ID | 4962 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
we | +0.039 |
ep | +0.035 |
bel | +0.033 |
men | +0.032 |
ilot | +0.032 |
Neg logit contributions | |
Penny | -0.037 |
Bruce | -0.037 |
Cindy | -0.036 |
Emmy | -0.035 |
Lilly | -0.035 |
Token | making |
Token ID | 1642 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
we | +0.074 |
ep | +0.067 |
bel | +0.063 |
ilot | +0.061 |
men | +0.060 |
Neg logit contributions | |
Penny | -0.075 |
Bruce | -0.075 |
Cindy | -0.072 |
Lilly | -0.070 |
Emmy | -0.070 |
Token | z |
Token ID | 1976 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
we | +0.089 |
ep | +0.078 |
bel | +0.074 |
ney | +0.073 |
anas | +0.072 |
Neg logit contributions | |
Penny | -0.095 |
Bruce | -0.093 |
Cindy | -0.093 |
Lilly | -0.089 |
Emmy | -0.089 |
Token | ig |
Token ID | 328 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
we | +0.134 |
ney | +0.130 |
ep | +0.122 |
anas | +0.121 |
men | +0.121 |
Neg logit contributions | |
Penny | -0.140 |
Bruce | -0.130 |
Cindy | -0.129 |
Lilly | -0.127 |
Holly | -0.126 |
Token | z |
Token ID | 89 |
Feature activation | -7.76e+00 |
Pos logit contributions | |
anas | +0.102 |
Some | +0.102 |
Or | +0.098 |
we | +0.095 |
Quick | +0.093 |
Neg logit contributions | |
Penny | -0.227 |
Emmy | -0.218 |
Cindy | -0.214 |
Lilly | -0.214 |
Jackie | -0.209 |
Token | ags |
Token ID | 3775 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
we | +0.337 |
ney | +0.311 |
bel | +0.309 |
anas | +0.294 |
ep | +0.287 |
Neg logit contributions | |
Penny | -0.324 |
Bruce | -0.312 |
Lilly | -0.299 |
Cindy | -0.298 |
Emmy | -0.296 |
Token | with |
Token ID | 351 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
we | +0.034 |
anas | +0.031 |
ep | +0.030 |
bel | +0.030 |
ilot | +0.029 |
Neg logit contributions | |
Penny | -0.024 |
Bruce | -0.023 |
Lilly | -0.022 |
Cindy | -0.022 |
Emmy | -0.022 |
Token | their |
Token ID | 511 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Penny | +0.020 |
Bruce | +0.020 |
Cindy | +0.019 |
Lilly | +0.019 |
Emmy | +0.018 |
Neg logit contributions | |
we | -0.022 |
ep | -0.020 |
bel | -0.019 |
men | -0.018 |
ney | -0.018 |
Token | feet |
Token ID | 3625 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
we | +0.058 |
ep | +0.050 |
ney | +0.046 |
bel | +0.046 |
Some | +0.045 |
Neg logit contributions | |
Penny | -0.065 |
Bruce | -0.062 |
Cindy | -0.061 |
Emmy | -0.060 |
Lilly | -0.059 |
Token | on |
Token ID | 319 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
we | +0.055 |
ep | +0.049 |
bel | +0.046 |
men | +0.044 |
ilot | +0.044 |
Neg logit contributions | |
Penny | -0.057 |
Bruce | -0.056 |
Cindy | -0.054 |
Emmy | -0.053 |
Lilly | -0.053 |
Token | fierce |
Token ID | 14800 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
we | +0.008 |
ep | +0.007 |
bel | +0.007 |
men | +0.006 |
ilot | +0.006 |
Neg logit contributions | |
Penny | -0.011 |
Bruce | -0.011 |
Cindy | -0.011 |
Lilly | -0.011 |
Emmy | -0.011 |
Token | wind |
Token ID | 2344 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
we | +0.029 |
ep | +0.026 |
bel | +0.023 |
men | +0.022 |
ilot | +0.022 |
Neg logit contributions | |
Bruce | -0.045 |
Penny | -0.045 |
Cindy | -0.043 |
Emmy | -0.042 |
Lilly | -0.042 |
Token | blew |
Token ID | 17948 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
Bruce | +0.026 |
Penny | +0.026 |
Cindy | +0.025 |
Lilly | +0.024 |
Emmy | +0.024 |
Neg logit contributions | |
we | -0.027 |
ep | -0.024 |
bel | -0.023 |
ilot | -0.022 |
men | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
we | +0.023 |
ep | +0.022 |
bel | +0.020 |
men | +0.019 |
songs | +0.019 |
Neg logit contributions | |
Bruce | -0.019 |
Penny | -0.018 |
Cindy | -0.018 |
Harriet | -0.017 |
Emmy | -0.017 |
Token | un |
Token ID | 555 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
we | +0.015 |
ep | +0.014 |
bel | +0.013 |
men | +0.012 |
z | +0.012 |
Neg logit contributions | |
Bruce | -0.015 |
Penny | -0.014 |
Cindy | -0.014 |
Harriet | -0.014 |
Emmy | -0.014 |
Token | z |
Token ID | 89 |
Feature activation | -7.71e+00 |
Pos logit contributions | |
Bruce | +0.025 |
Cindy | +0.025 |
Penny | +0.025 |
Emmy | +0.024 |
Lilly | +0.024 |
Neg logit contributions | |
we | -0.015 |
ep | -0.012 |
ilot | -0.012 |
ity | -0.012 |
songs | -0.012 |
Token | ipped |
Token ID | 3949 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
we | +0.313 |
bel | +0.273 |
ep | +0.272 |
ney | +0.258 |
anas | +0.254 |
Neg logit contributions | |
Penny | -0.364 |
Bruce | -0.357 |
Cindy | -0.347 |
Lilly | -0.345 |
Emmy | -0.340 |
Token | her |
Token ID | 607 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
we | +0.069 |
ep | +0.063 |
bel | +0.060 |
men | +0.058 |
z | +0.057 |
Neg logit contributions | |
Bruce | -0.059 |
Penny | -0.057 |
Cindy | -0.053 |
Harriet | -0.053 |
Emmy | -0.052 |
Token | jacket |
Token ID | 15224 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
we | +0.030 |
ep | +0.028 |
bel | +0.026 |
men | +0.025 |
ilot | +0.025 |
Neg logit contributions | |
Penny | -0.029 |
Bruce | -0.029 |
Cindy | -0.028 |
Emmy | -0.027 |
Lilly | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
Penny | +0.061 |
Bruce | +0.061 |
Cindy | +0.059 |
Emmy | +0.057 |
Lilly | +0.056 |
Neg logit contributions | |
we | -0.076 |
ep | -0.069 |
bel | -0.065 |
men | -0.063 |
ilot | -0.063 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
we | +0.036 |
ep | +0.031 |
bel | +0.031 |
Blood | +0.029 |
ilot | +0.029 |
Neg logit contributions | |
Bruce | -0.034 |
Penny | -0.031 |
Cindy | -0.031 |
Harriet | -0.029 |
Emmy | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
we | +0.098 |
ep | +0.089 |
bel | +0.084 |
ilot | +0.082 |
ity | +0.081 |
Neg logit contributions | |
Penny | -0.068 |
Bruce | -0.068 |
Cindy | -0.065 |
Emmy | -0.063 |
Lilly | -0.063 |
Token | But |
Token ID | 887 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
we | +0.018 |
ep | +0.016 |
anas | +0.015 |
ney | +0.015 |
bel | +0.015 |
Neg logit contributions | |
Cindy | -0.019 |
Bruce | -0.018 |
Penny | -0.018 |
Emmy | -0.017 |
Harriet | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Cindy | +0.047 |
Bruce | +0.046 |
Penny | +0.046 |
Harriet | +0.045 |
Emmy | +0.044 |
Neg logit contributions | |
we | -0.037 |
ep | -0.035 |
bel | -0.031 |
men | -0.030 |
songs | -0.030 |
Token | z |
Token ID | 1976 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
Bruce | +0.005 |
Penny | +0.005 |
Cindy | +0.005 |
Lilly | +0.005 |
Emmy | +0.005 |
Neg logit contributions | |
we | -0.006 |
ep | -0.006 |
bel | -0.005 |
anas | -0.005 |
men | -0.005 |
Token | ig |
Token ID | 328 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
we | +0.117 |
ity | +0.098 |
ep | +0.098 |
bel | +0.098 |
songs | +0.096 |
Neg logit contributions | |
Bruce | -0.134 |
Penny | -0.131 |
Lilly | -0.128 |
Cindy | -0.127 |
Emmy | -0.124 |
Token | z |
Token ID | 89 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
we | +0.184 |
anas | +0.162 |
ep | +0.159 |
bel | +0.155 |
songs | +0.153 |
Neg logit contributions | |
Penny | -0.149 |
Cindy | -0.142 |
Bruce | -0.142 |
Lilly | -0.142 |
Emmy | -0.139 |
Token | ags |
Token ID | 3775 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
we | +0.344 |
ep | +0.306 |
bel | +0.305 |
anas | +0.285 |
men | +0.285 |
Neg logit contributions | |
Penny | -0.326 |
Bruce | -0.325 |
Cindy | -0.311 |
Lilly | -0.308 |
Emmy | -0.302 |
Token | weren |
Token ID | 6304 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
we | +0.029 |
ep | +0.025 |
anas | +0.025 |
ilot | +0.024 |
bel | +0.024 |
Neg logit contributions | |
Bruce | -0.023 |
Penny | -0.022 |
Cindy | -0.022 |
Lilly | -0.022 |
Emmy | -0.021 |
Token | 't |
Token ID | 470 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Penny | +0.040 |
Bruce | +0.040 |
Cindy | +0.038 |
Lilly | +0.038 |
Emmy | +0.037 |
Neg logit contributions | |
we | -0.036 |
ep | -0.033 |
bel | -0.029 |
ilot | -0.029 |
men | -0.029 |
Token | as |
Token ID | 355 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
we | +0.013 |
ep | +0.012 |
bel | +0.011 |
men | +0.011 |
ilot | +0.011 |
Neg logit contributions | |
Bruce | -0.012 |
Penny | -0.012 |
Cindy | -0.011 |
Emmy | -0.011 |
Lilly | -0.011 |
Token | easy |
Token ID | 2562 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
we | +0.017 |
ep | +0.015 |
bel | +0.014 |
ilot | +0.013 |
anas | +0.013 |
Neg logit contributions | |
Penny | -0.018 |
Bruce | -0.018 |
Cindy | -0.017 |
Lilly | -0.017 |
Emmy | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
we | +0.023 |
ep | +0.021 |
bel | +0.020 |
men | +0.019 |
ilot | +0.019 |
Neg logit contributions | |
Bruce | -0.022 |
Penny | -0.022 |
Cindy | -0.021 |
Emmy | -0.020 |
Lilly | -0.020 |
Token | stairs |
Token ID | 16046 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Bruce | +0.019 |
Penny | +0.019 |
Cindy | +0.018 |
Sophie | +0.018 |
Lilly | +0.018 |
Neg logit contributions | |
we | -0.015 |
ep | -0.013 |
bel | -0.012 |
men | -0.012 |
ney | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Bruce | +0.015 |
Penny | +0.015 |
Cindy | +0.015 |
Emmy | +0.014 |
Lilly | +0.014 |
Neg logit contributions | |
we | -0.016 |
ep | -0.014 |
bel | -0.013 |
men | -0.013 |
ilot | -0.013 |
Token | z |
Token ID | 1976 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
Bruce | +0.008 |
Penny | +0.007 |
Cindy | +0.007 |
Sophie | +0.007 |
Nancy | +0.007 |
Neg logit contributions | |
we | -0.008 |
ep | -0.007 |
bel | -0.007 |
men | -0.007 |
songs | -0.006 |
Token | ig |
Token ID | 328 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
we | +0.132 |
ep | +0.119 |
bel | +0.112 |
men | +0.110 |
ney | +0.110 |
Neg logit contributions | |
Penny | -0.140 |
Bruce | -0.138 |
Cindy | -0.135 |
Lilly | -0.133 |
Emmy | -0.130 |
Token | z |
Token ID | 89 |
Feature activation | -7.67e+00 |
Pos logit contributions | |
we | +0.104 |
ep | +0.089 |
anas | +0.085 |
bel | +0.081 |
ity | +0.080 |
Neg logit contributions | |
Penny | -0.215 |
Cindy | -0.209 |
Bruce | -0.208 |
Lilly | -0.205 |
Emmy | -0.204 |
Token | agged |
Token ID | 14655 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
we | +0.313 |
ep | +0.272 |
bel | +0.268 |
ney | +0.255 |
anas | +0.253 |
Neg logit contributions | |
Penny | -0.353 |
Bruce | -0.350 |
Cindy | -0.342 |
Lilly | -0.336 |
Emmy | -0.331 |
Token | around |
Token ID | 1088 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
we | +0.037 |
ep | +0.034 |
bel | +0.032 |
men | +0.031 |
ilot | +0.030 |
Neg logit contributions | |
Bruce | -0.034 |
Penny | -0.034 |
Cindy | -0.032 |
Emmy | -0.031 |
Lilly | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
Bruce | +0.031 |
Penny | +0.031 |
Cindy | +0.030 |
Lilly | +0.029 |
Emmy | +0.029 |
Neg logit contributions | |
we | -0.034 |
ep | -0.030 |
bel | -0.028 |
men | -0.027 |
angels | -0.027 |
Token | hallway |
Token ID | 23959 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Bruce | +0.021 |
Penny | +0.020 |
Cindy | +0.020 |
Lilly | +0.019 |
Emmy | +0.019 |
Neg logit contributions | |
we | -0.017 |
ep | -0.015 |
bel | -0.014 |
ney | -0.013 |
men | -0.013 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
we | +0.073 |
ep | +0.067 |
bel | +0.062 |
men | +0.060 |
ilot | +0.059 |
Neg logit contributions | |
Penny | -0.071 |
Bruce | -0.071 |
Cindy | -0.068 |
Emmy | -0.066 |
Lilly | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
we | +0.079 |
ep | +0.065 |
bel | +0.062 |
men | +0.061 |
songs | +0.060 |
Neg logit contributions | |
Bruce | -0.090 |
Penny | -0.088 |
Cindy | -0.084 |
Lilly | -0.082 |
Emmy | -0.082 |
Token | She |
Token ID | 1375 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
we | +0.013 |
ilot | +0.011 |
ep | +0.010 |
bel | +0.010 |
angels | +0.010 |
Neg logit contributions | |
Bruce | -0.016 |
Penny | -0.015 |
Lilly | -0.015 |
Emmy | -0.014 |
Jackie | -0.014 |
Token | z |
Token ID | 1976 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
Bruce | +0.059 |
Penny | +0.059 |
Cindy | +0.056 |
Lilly | +0.055 |
Emmy | +0.055 |
Neg logit contributions | |
we | -0.057 |
ep | -0.054 |
bel | -0.049 |
ilot | -0.046 |
men | -0.046 |
Token | ig |
Token ID | 328 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
we | +0.155 |
song | +0.140 |
ney | +0.140 |
songs | +0.140 |
men | +0.137 |
Neg logit contributions | |
Penny | -0.104 |
Cindy | -0.103 |
Lilly | -0.102 |
Hannah | -0.101 |
Bruce | -0.101 |
Token | - |
Token ID | 12 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
we | +0.088 |
songs | +0.078 |
anas | +0.077 |
song | +0.071 |
Some | +0.070 |
Neg logit contributions | |
Penny | -0.220 |
Cindy | -0.214 |
Lilly | -0.213 |
Emmy | -0.212 |
Bruce | -0.209 |
Token | z |
Token ID | 89 |
Feature activation | -7.63e+00 |
Pos logit contributions | |
we | +0.090 |
ilot | +0.090 |
anas | +0.089 |
ep | +0.086 |
ity | +0.086 |
Neg logit contributions | |
Cindy | -0.150 |
Emmy | -0.146 |
Penny | -0.143 |
Bruce | -0.142 |
Lilly | -0.142 |
Token | agged |
Token ID | 14655 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
we | +0.336 |
bel | +0.297 |
ep | +0.290 |
ney | +0.289 |
anas | +0.282 |
Neg logit contributions | |
Penny | -0.325 |
Bruce | -0.318 |
Cindy | -0.313 |
Lilly | -0.309 |
Emmy | -0.306 |
Token | up |
Token ID | 510 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
we | +0.035 |
ep | +0.031 |
bel | +0.029 |
ilot | +0.028 |
men | +0.028 |
Neg logit contributions | |
Penny | -0.035 |
Bruce | -0.035 |
Cindy | -0.034 |
Emmy | -0.033 |
Lilly | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -9.70e-03 |
Pos logit contributions | |
Penny | +0.108 |
Bruce | +0.107 |
Cindy | +0.104 |
Lilly | +0.101 |
Emmy | +0.101 |
Neg logit contributions | |
we | -0.100 |
ep | -0.090 |
bel | -0.083 |
men | -0.080 |
ilot | -0.080 |
Token | down |
Token ID | 866 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
we | +0.000 |
ep | +0.000 |
bel | +0.000 |
z | +0.000 |
men | +0.000 |
Neg logit contributions | |
Bruce | -0.000 |
Penny | -0.000 |
Cindy | -0.000 |
Emmy | -0.000 |
Lilly | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
we | +0.024 |
ep | +0.021 |
bel | +0.020 |
men | +0.019 |
ilot | +0.019 |
Neg logit contributions | |
Penny | -0.024 |
Bruce | -0.024 |
Cindy | -0.023 |
Emmy | -0.023 |
Lilly | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
Bruce | +0.004 |
Penny | +0.004 |
Cindy | +0.004 |
Emmy | +0.004 |
Harriet | +0.004 |
Neg logit contributions | |
we | -0.003 |
ep | -0.003 |
bel | -0.003 |
z | -0.003 |
men | -0.003 |
Token | their |
Token ID | 511 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
Bruce | +0.021 |
Penny | +0.021 |
Cindy | +0.020 |
Emmy | +0.020 |
Lilly | +0.020 |
Neg logit contributions | |
we | -0.024 |
ep | -0.022 |
bel | -0.021 |
men | -0.020 |
ilot | -0.020 |
Token | car |
Token ID | 1097 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
we | +0.035 |
ep | +0.032 |
bel | +0.029 |
men | +0.028 |
ilot | +0.028 |
Neg logit contributions | |
Bruce | -0.046 |
Penny | -0.046 |
Cindy | -0.044 |
Emmy | -0.043 |
Lilly | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
we | +0.078 |
ep | +0.066 |
bel | +0.061 |
ity | +0.061 |
ilot | +0.061 |
Neg logit contributions | |
Penny | -0.080 |
Bruce | -0.079 |
Cindy | -0.076 |
Emmy | -0.075 |
Lilly | -0.074 |
Token | " |
Token ID | 366 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
Bruce | +0.001 |
Penny | +0.001 |
Cindy | +0.001 |
Emmy | +0.001 |
Lilly | +0.001 |
Neg logit contributions | |
we | -0.001 |
ep | -0.001 |
bel | -0.001 |
men | -0.001 |
z | -0.001 |
Token | z |
Token ID | 89 |
Feature activation | -7.63e+00 |
Pos logit contributions | |
we | +0.034 |
men | +0.031 |
bel | +0.031 |
ep | +0.030 |
anas | +0.030 |
Neg logit contributions | |
Bruce | -0.043 |
Cindy | -0.043 |
Penny | -0.043 |
Lilly | -0.042 |
Emmy | -0.042 |
Token | ipped |
Token ID | 3949 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
we | +0.288 |
ep | +0.243 |
bel | +0.240 |
ney | +0.224 |
anas | +0.221 |
Neg logit contributions | |
Bruce | -0.378 |
Penny | -0.376 |
Cindy | -0.364 |
Lilly | -0.356 |
Emmy | -0.356 |
Token | " |
Token ID | 1 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
we | +0.062 |
ep | +0.059 |
bel | +0.053 |
men | +0.053 |
ilot | +0.052 |
Neg logit contributions | |
Penny | -0.056 |
Bruce | -0.055 |
Cindy | -0.053 |
Lilly | -0.052 |
Emmy | -0.051 |
Token | down |
Token ID | 866 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
we | +0.024 |
ep | +0.023 |
ity | +0.021 |
anas | +0.021 |
ilot | +0.021 |
Neg logit contributions | |
Penny | -0.023 |
Bruce | -0.023 |
Cindy | -0.023 |
Lilly | -0.023 |
Emmy | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
we | +0.027 |
ep | +0.025 |
bel | +0.023 |
men | +0.022 |
ilot | +0.022 |
Neg logit contributions | |
Penny | -0.024 |
Bruce | -0.024 |
Cindy | -0.023 |
Emmy | -0.022 |
Lilly | -0.022 |
Token | road |
Token ID | 2975 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
Penny | +0.017 |
Bruce | +0.017 |
Cindy | +0.016 |
Lilly | +0.016 |
Emmy | +0.016 |
Neg logit contributions | |
we | -0.013 |
ep | -0.012 |
bel | -0.011 |
men | -0.011 |
ilot | -0.010 |
Token | there |
Token ID | 612 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Penny | +0.031 |
Bruce | +0.029 |
Cindy | +0.029 |
Lilly | +0.028 |
Emmy | +0.028 |
Neg logit contributions | |
we | -0.052 |
anas | -0.049 |
bel | -0.047 |
songs | -0.046 |
men | -0.045 |
Token | was |
Token ID | 373 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Penny | +0.051 |
Lilly | +0.050 |
Bruce | +0.049 |
Sophie | +0.048 |
Cindy | +0.048 |
Neg logit contributions | |
we | -0.072 |
bel | -0.066 |
ep | -0.065 |
anas | -0.062 |
ilot | -0.061 |
Token | a |
Token ID | 257 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
Penny | +0.011 |
Bruce | +0.010 |
Cindy | +0.010 |
Lilly | +0.010 |
Emmy | +0.010 |
Neg logit contributions | |
we | -0.010 |
ep | -0.009 |
bel | -0.009 |
men | -0.008 |
anas | -0.008 |
Token | little |
Token ID | 1310 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Penny | +0.022 |
Bruce | +0.022 |
Cindy | +0.021 |
Lilly | +0.021 |
Emmy | +0.021 |
Neg logit contributions | |
we | -0.018 |
ep | -0.015 |
bel | -0.015 |
z | -0.014 |
anas | -0.014 |
Token | boy |
Token ID | 2933 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
we | +0.039 |
ep | +0.034 |
bel | +0.032 |
men | +0.030 |
ilot | +0.030 |
Neg logit contributions | |
Penny | -0.055 |
Bruce | -0.055 |
Cindy | -0.053 |
Lilly | -0.052 |
Emmy | -0.052 |
Token | named |
Token ID | 3706 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
we | +0.019 |
bel | +0.018 |
ilot | +0.017 |
angels | +0.017 |
ep | +0.017 |
Neg logit contributions | |
Penny | -0.007 |
Lilly | -0.006 |
Bruce | -0.006 |
Emmy | -0.006 |
Cindy | -0.006 |
Token | Tim |
Token ID | 5045 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
Bruce | +0.145 |
Penny | +0.144 |
Cindy | +0.142 |
Emmy | +0.135 |
Harriet | +0.134 |
Neg logit contributions | |
we | -0.159 |
ep | -0.149 |
men | -0.136 |
bel | -0.132 |
ilot | -0.131 |
Token | my |
Token ID | 1820 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Penny | +0.017 |
Bruce | +0.017 |
Lilly | +0.016 |
Emmy | +0.015 |
Cindy | +0.015 |
Neg logit contributions | |
we | -0.039 |
bel | -0.036 |
ilot | -0.034 |
men | -0.034 |
angels | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
we | +0.094 |
bel | +0.088 |
ilot | +0.082 |
men | +0.080 |
angels | +0.079 |
Neg logit contributions | |
Penny | -0.047 |
Bruce | -0.047 |
Emmy | -0.044 |
Lilly | -0.043 |
Cindy | -0.042 |
Token | Tim |
Token ID | 5045 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
Bruce | +0.018 |
Penny | +0.018 |
Lilly | +0.017 |
Cindy | +0.017 |
Emmy | +0.016 |
Neg logit contributions | |
we | -0.032 |
ep | -0.029 |
bel | -0.029 |
ilot | -0.027 |
ity | -0.027 |
Token | my |
Token ID | 1820 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Penny | +0.012 |
Bruce | +0.012 |
Emmy | +0.011 |
Lilly | +0.011 |
Cindy | +0.011 |
Neg logit contributions | |
we | -0.027 |
bel | -0.025 |
ilot | -0.024 |
men | -0.024 |
angels | -0.023 |
Token | others |
Token ID | 1854 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Penny | +0.026 |
Bruce | +0.026 |
Cindy | +0.026 |
Emmy | +0.025 |
Lilly | +0.025 |
Neg logit contributions | |
we | -0.023 |
ep | -0.021 |
bel | -0.019 |
men | -0.018 |
ilot | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Bruce | +0.082 |
Penny | +0.082 |
Cindy | +0.080 |
Lilly | +0.077 |
Emmy | +0.077 |
Neg logit contributions | |
we | -0.072 |
ep | -0.065 |
bel | -0.060 |
men | -0.058 |
ilot | -0.057 |
Token | " |
Token ID | 366 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
Bruce | +0.009 |
Cindy | +0.009 |
Sophie | +0.009 |
Harriet | +0.009 |
Penny | +0.009 |
Neg logit contributions | |
we | -0.010 |
men | -0.009 |
ep | -0.009 |
bel | -0.009 |
Blood | -0.009 |
Token | What |
Token ID | 2061 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
we | +0.028 |
ep | +0.026 |
ilot | +0.024 |
men | +0.024 |
bel | +0.024 |
Neg logit contributions | |
Penny | -0.034 |
Bruce | -0.034 |
Cindy | -0.032 |
Lilly | -0.032 |
Emmy | -0.032 |
Token | 's |
Token ID | 338 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
we | +0.006 |
ep | +0.005 |
bel | +0.005 |
ilot | +0.005 |
men | +0.005 |
Neg logit contributions | |
Penny | -0.005 |
Bruce | -0.005 |
Cindy | -0.005 |
Emmy | -0.005 |
Lilly | -0.005 |
Token | wrong |
Token ID | 2642 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
we | +0.010 |
ep | +0.010 |
ggy | +0.009 |
songs | +0.009 |
angels | +0.008 |
Neg logit contributions | |
Bruce | -0.008 |
Penny | -0.008 |
Cindy | -0.008 |
Lilly | -0.008 |
Emmy | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
Penny | +0.115 |
Bruce | +0.113 |
Cindy | +0.111 |
Emmy | +0.108 |
Lilly | +0.107 |
Neg logit contributions | |
we | -0.146 |
ep | -0.136 |
bel | -0.131 |
men | -0.131 |
ity | -0.127 |
Token | Benny |
Token ID | 44275 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Cindy | +0.021 |
Sophie | +0.020 |
Gab | +0.020 |
Harriet | +0.020 |
Bruce | +0.020 |
Neg logit contributions | |
we | -0.043 |
songs | -0.043 |
song | -0.042 |
men | -0.042 |
ep | -0.042 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
Bruce | +0.072 |
Cindy | +0.072 |
Penny | +0.069 |
Sophie | +0.067 |
Emmy | +0.067 |
Neg logit contributions | |
we | -0.076 |
ep | -0.074 |
men | -0.065 |
ity | -0.064 |
ney | -0.064 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Bruce | +0.077 |
Cindy | +0.075 |
Sophie | +0.073 |
Penny | +0.073 |
checkout | +0.072 |
Neg logit contributions | |
we | -0.106 |
ep | -0.094 |
Blood | -0.086 |
bel | -0.086 |
Some | -0.085 |
Token | the |
Token ID | 262 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
Cindy | +0.059 |
Bruce | +0.058 |
checkout | +0.056 |
Sophie | +0.056 |
Harriet | +0.056 |
Neg logit contributions | |
we | -0.097 |
ep | -0.089 |
men | -0.081 |
Ch | -0.080 |
songs | -0.080 |
Token | day |
Token ID | 1110 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
we | +0.072 |
ep | +0.064 |
anas | +0.059 |
bel | +0.058 |
z | +0.057 |
Neg logit contributions | |
Bruce | -0.044 |
Penny | -0.044 |
Lilly | -0.041 |
Cindy | -0.040 |
Jackie | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
we | +0.010 |
ep | +0.010 |
men | +0.009 |
bel | +0.009 |
ilot | +0.009 |
Neg logit contributions | |
Penny | -0.008 |
Bruce | -0.008 |
Emmy | -0.007 |
Cindy | -0.007 |
Lilly | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
Bruce | +0.035 |
Cindy | +0.033 |
Penny | +0.033 |
Sophie | +0.031 |
Lilly | +0.031 |
Neg logit contributions | |
we | -0.057 |
ep | -0.053 |
bel | -0.049 |
ney | -0.048 |
ity | -0.048 |
Token | small |
Token ID | 1402 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
Penny | +0.026 |
Bruce | +0.026 |
Cindy | +0.025 |
Emmy | +0.024 |
Lilly | +0.024 |
Neg logit contributions | |
we | -0.017 |
ep | -0.015 |
bel | -0.014 |
ilot | -0.013 |
men | -0.013 |
Token | girl |
Token ID | 2576 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
Bruce | +0.030 |
Penny | +0.030 |
Cindy | +0.029 |
Emmy | +0.028 |
Lilly | +0.028 |
Neg logit contributions | |
we | -0.017 |
ep | -0.015 |
bel | -0.014 |
men | -0.013 |
ilot | -0.013 |
Token | named |
Token ID | 3706 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
Bruce | +0.028 |
Penny | +0.028 |
Cindy | +0.027 |
Emmy | +0.026 |
Harriet | +0.025 |
Neg logit contributions | |
we | -0.027 |
ep | -0.024 |
bel | -0.022 |
men | -0.021 |
ilot | -0.021 |
Token | Sue |
Token ID | 26089 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
Bruce | +0.134 |
Penny | +0.128 |
Cindy | +0.123 |
Emmy | +0.120 |
Harriet | +0.118 |
Neg logit contributions | |
we | -0.154 |
men | -0.132 |
bel | -0.127 |
ep | -0.126 |
angels | -0.125 |
Token | was |
Token ID | 373 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
Bruce | +0.046 |
Cindy | +0.044 |
Penny | +0.044 |
Emmy | +0.042 |
Hannah | +0.042 |
Neg logit contributions | |
we | -0.033 |
ep | -0.032 |
men | -0.027 |
bel | -0.027 |
ney | -0.026 |
Token | visiting |
Token ID | 10013 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Bruce | +0.036 |
Penny | +0.035 |
Cindy | +0.034 |
Lilly | +0.034 |
Emmy | +0.033 |
Neg logit contributions | |
we | -0.033 |
ep | -0.031 |
bel | -0.027 |
men | -0.027 |
angels | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
we | +0.062 |
ep | +0.056 |
bel | +0.053 |
men | +0.052 |
angels | +0.051 |
Neg logit contributions | |
Penny | -0.054 |
Bruce | -0.053 |
Cindy | -0.051 |
Emmy | -0.051 |
Lilly | -0.050 |
Token | She |
Token ID | 1375 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Penny | +0.018 |
Bruce | +0.017 |
Emmy | +0.017 |
Lilly | +0.016 |
Cindy | +0.016 |
Neg logit contributions | |
we | -0.017 |
bel | -0.015 |
men | -0.015 |
ep | -0.015 |
ney | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
Penny | +0.082 |
Bruce | +0.082 |
Cindy | +0.079 |
Emmy | +0.077 |
Lilly | +0.077 |
Neg logit contributions | |
we | -0.053 |
ep | -0.047 |
bel | -0.042 |
men | -0.041 |
ilot | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
Bruce | +0.035 |
Penny | +0.035 |
Cindy | +0.034 |
Lilly | +0.033 |
Emmy | +0.033 |
Neg logit contributions | |
we | -0.031 |
ep | -0.028 |
bel | -0.026 |
men | -0.025 |
ilot | -0.025 |
Token | fierce |
Token ID | 14800 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Penny | +0.029 |
Bruce | +0.028 |
Cindy | +0.028 |
Lilly | +0.027 |
Emmy | +0.027 |
Neg logit contributions | |
we | -0.027 |
bel | -0.022 |
ep | -0.022 |
z | -0.020 |
ilot | -0.020 |
Token | little |
Token ID | 1310 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
we | +0.005 |
ep | +0.004 |
bel | +0.004 |
ilot | +0.003 |
men | +0.003 |
Neg logit contributions | |
Penny | -0.008 |
Bruce | -0.008 |
Cindy | -0.008 |
Lilly | -0.007 |
Emmy | -0.007 |
Token | dragon |
Token ID | 10441 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
we | +0.020 |
ep | +0.018 |
bel | +0.017 |
ilot | +0.015 |
anas | +0.015 |
Neg logit contributions | |
Penny | -0.032 |
Bruce | -0.032 |
Cindy | -0.031 |
Lilly | -0.031 |
Emmy | -0.030 |
Token | called |
Token ID | 1444 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
we | +0.088 |
ep | +0.081 |
bel | +0.077 |
angels | +0.075 |
anas | +0.075 |
Neg logit contributions | |
Bruce | -0.050 |
Penny | -0.050 |
Cindy | -0.045 |
Lilly | -0.045 |
Emmy | -0.044 |
Token | Red |
Token ID | 2297 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
Penny | +0.219 |
Bruce | +0.217 |
Cindy | +0.213 |
Emmy | +0.206 |
Lilly | +0.206 |
Neg logit contributions | |
we | -0.234 |
ep | -0.217 |
ilot | -0.202 |
men | -0.200 |
bel | -0.198 |
Token | . |
Token ID | 13 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
Bruce | +0.146 |
Penny | +0.144 |
Cindy | +0.139 |
Emmy | +0.136 |
Lilly | +0.134 |
Neg logit contributions | |
we | -0.155 |
ep | -0.138 |
bel | -0.134 |
ilot | -0.127 |
men | -0.125 |
Token | She |
Token ID | 1375 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Penny | +0.018 |
Bruce | +0.017 |
Sophie | +0.017 |
Lilly | +0.017 |
Jackie | +0.017 |
Neg logit contributions | |
we | -0.034 |
ep | -0.034 |
songs | -0.032 |
ilot | -0.031 |
angels | -0.031 |
Token | lived |
Token ID | 5615 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
Bruce | +0.076 |
Penny | +0.076 |
Cindy | +0.073 |
Emmy | +0.070 |
Lilly | +0.070 |
Neg logit contributions | |
we | -0.087 |
ep | -0.076 |
bel | -0.075 |
ilot | -0.072 |
men | -0.072 |
Token | in |
Token ID | 287 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Penny | +0.106 |
Bruce | +0.105 |
Cindy | +0.100 |
Lilly | +0.096 |
Emmy | +0.095 |
Neg logit contributions | |
we | -0.107 |
ep | -0.092 |
anas | -0.091 |
bel | -0.088 |
ilot | -0.088 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
we | +0.008 |
ep | +0.007 |
bel | +0.007 |
men | +0.007 |
ilot | +0.007 |
Neg logit contributions | |
Bruce | -0.004 |
Penny | -0.004 |
Cindy | -0.004 |
Emmy | -0.004 |
Lilly | -0.004 |
Token | there |
Token ID | 612 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Penny | +0.048 |
Bruce | +0.048 |
Lilly | +0.045 |
Cindy | +0.045 |
Emmy | +0.045 |
Neg logit contributions | |
we | -0.074 |
ep | -0.066 |
anas | -0.064 |
bel | -0.063 |
men | -0.063 |
Token | was |
Token ID | 373 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
Bruce | +0.069 |
Penny | +0.069 |
Cindy | +0.067 |
Lilly | +0.066 |
Emmy | +0.065 |
Neg logit contributions | |
we | -0.060 |
ep | -0.054 |
bel | -0.051 |
ilot | -0.048 |
men | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
Bruce | +0.040 |
Penny | +0.040 |
Cindy | +0.038 |
Emmy | +0.037 |
Lilly | +0.037 |
Neg logit contributions | |
we | -0.031 |
ep | -0.028 |
bel | -0.026 |
men | -0.025 |
ilot | -0.025 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Penny | +0.027 |
Bruce | +0.026 |
Cindy | +0.026 |
Lilly | +0.025 |
Emmy | +0.025 |
Neg logit contributions | |
we | -0.025 |
ep | -0.020 |
bel | -0.020 |
z | -0.019 |
ilot | -0.018 |
Token | named |
Token ID | 3706 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
Penny | +0.006 |
Bruce | +0.005 |
Lilly | +0.005 |
Emmy | +0.005 |
Cindy | +0.005 |
Neg logit contributions | |
we | -0.014 |
bel | -0.013 |
ilot | -0.013 |
ep | -0.013 |
angels | -0.012 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
Bruce | +0.145 |
Penny | +0.145 |
Cindy | +0.140 |
Emmy | +0.134 |
Lilly | +0.133 |
Neg logit contributions | |
we | -0.182 |
ep | -0.168 |
bel | -0.157 |
men | -0.155 |
ilot | -0.151 |
Token | my |
Token ID | 1820 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Penny | +0.021 |
Bruce | +0.020 |
Lilly | +0.019 |
Emmy | +0.018 |
Cindy | +0.017 |
Neg logit contributions | |
we | -0.051 |
bel | -0.046 |
ilot | -0.045 |
men | -0.044 |
angels | -0.044 |
Token | who |
Token ID | 508 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
we | +0.072 |
bel | +0.065 |
ilot | +0.064 |
ep | +0.062 |
men | +0.062 |
Neg logit contributions | |
Penny | -0.044 |
Bruce | -0.044 |
Emmy | -0.042 |
Lilly | -0.040 |
Cindy | -0.040 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
we | +0.016 |
ep | +0.013 |
ilot | +0.013 |
bel | +0.013 |
angels | +0.012 |
Neg logit contributions | |
Penny | -0.015 |
Bruce | -0.015 |
Cindy | -0.014 |
Emmy | -0.014 |
Lilly | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
Bruce | +0.054 |
Penny | +0.054 |
Cindy | +0.052 |
Emmy | +0.050 |
Lilly | +0.050 |
Neg logit contributions | |
we | -0.066 |
ep | -0.061 |
ilot | -0.061 |
ney | -0.058 |
ity | -0.057 |
Token | on |
Token ID | 319 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
we | +0.044 |
ep | +0.037 |
ity | +0.036 |
anas | +0.036 |
ilot | +0.036 |
Neg logit contributions | |
Penny | -0.040 |
Bruce | -0.040 |
Cindy | -0.039 |
Emmy | -0.038 |
Lilly | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
we | +0.024 |
ep | +0.021 |
bel | +0.021 |
ilot | +0.020 |
ity | +0.020 |
Neg logit contributions | |
Penny | -0.017 |
Bruce | -0.017 |
Cindy | -0.017 |
Emmy | -0.016 |
Lilly | -0.016 |
Token | big |
Token ID | 1263 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Penny | +0.017 |
Bruce | +0.017 |
Cindy | +0.017 |
Emmy | +0.016 |
Lilly | +0.016 |
Neg logit contributions | |
we | -0.015 |
ep | -0.012 |
bel | -0.012 |
ilot | -0.012 |
ity | -0.012 |
Token | road |
Token ID | 2975 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
we | +0.013 |
ep | +0.012 |
bel | +0.010 |
men | +0.010 |
ilot | +0.010 |
Neg logit contributions | |
Bruce | -0.017 |
Penny | -0.017 |
Cindy | -0.016 |
Emmy | -0.016 |
Lilly | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
we | +0.034 |
ep | +0.031 |
bel | +0.028 |
ilot | +0.028 |
ity | +0.028 |
Neg logit contributions | |
Bruce | -0.032 |
Penny | -0.032 |
Cindy | -0.031 |
Emmy | -0.030 |
Lilly | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
Bruce | +0.012 |
Penny | +0.012 |
Cindy | +0.012 |
Emmy | +0.011 |
Lilly | +0.011 |
Neg logit contributions | |
we | -0.010 |
ep | -0.009 |
bel | -0.008 |
men | -0.008 |
ilot | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
Penny | +0.014 |
Bruce | +0.014 |
Lilly | +0.014 |
Cindy | +0.014 |
Emmy | +0.013 |
Neg logit contributions | |
we | -0.017 |
ep | -0.016 |
bel | -0.015 |
ity | -0.015 |
anas | -0.015 |
Token | But |
Token ID | 1537 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
Penny | +0.018 |
Bruce | +0.017 |
Cindy | +0.017 |
Lilly | +0.017 |
Emmy | +0.016 |
Neg logit contributions | |
we | -0.013 |
bel | -0.012 |
ep | -0.011 |
men | -0.011 |
anas | -0.011 |
Token | then |
Token ID | 788 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Bruce | +0.024 |
Penny | +0.023 |
Cindy | +0.022 |
Emmy | +0.022 |
Lilly | +0.021 |
Neg logit contributions | |
we | -0.028 |
ep | -0.026 |
bel | -0.024 |
men | -0.024 |
ilot | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
Bruce | +0.038 |
Penny | +0.037 |
Cindy | +0.036 |
Emmy | +0.035 |
Lilly | +0.034 |
Neg logit contributions | |
we | -0.056 |
ep | -0.052 |
bel | -0.048 |
men | -0.048 |
ilot | -0.047 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Penny | +0.036 |
Bruce | +0.036 |
Cindy | +0.035 |
Lilly | +0.034 |
Emmy | +0.034 |
Neg logit contributions | |
we | -0.035 |
ep | -0.032 |
bel | -0.029 |
men | -0.028 |
ilot | -0.028 |
Token | big |
Token ID | 1263 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
Penny | +0.024 |
Bruce | +0.024 |
Cindy | +0.023 |
Emmy | +0.023 |
Lilly | +0.023 |
Neg logit contributions | |
we | -0.015 |
ep | -0.013 |
bel | -0.012 |
ilot | -0.011 |
men | -0.011 |
Token | vehicle |
Token ID | 4038 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ep | +0.007 |
we | +0.006 |
men | +0.006 |
song | +0.005 |
ney | +0.005 |
Neg logit contributions | |
Bruce | -0.013 |
Penny | -0.012 |
Cindy | -0.012 |
Emmy | -0.012 |
Lilly | -0.012 |
Token | driving |
Token ID | 5059 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
we | +0.067 |
ep | +0.060 |
ilot | +0.058 |
ity | +0.057 |
anas | +0.057 |
Neg logit contributions | |
Bruce | -0.066 |
Penny | -0.065 |
Cindy | -0.064 |
Emmy | -0.062 |
Lilly | -0.061 |
Token | down |
Token ID | 866 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
we | +0.107 |
anas | +0.095 |
ilot | +0.092 |
ity | +0.091 |
ep | +0.090 |
Neg logit contributions | |
Bruce | -0.066 |
Penny | -0.065 |
Cindy | -0.063 |
Emmy | -0.062 |
Lilly | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
we | +0.014 |
ep | +0.013 |
bel | +0.012 |
ity | +0.012 |
anas | +0.012 |
Neg logit contributions | |
Penny | -0.009 |
Bruce | -0.009 |
Cindy | -0.009 |
Lilly | -0.009 |
Emmy | -0.009 |
Token | road |
Token ID | 2975 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
Penny | +0.040 |
Bruce | +0.040 |
Cindy | +0.039 |
Lilly | +0.038 |
Emmy | +0.038 |
Neg logit contributions | |
we | -0.028 |
ep | -0.026 |
bel | -0.023 |
men | -0.023 |
ney | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
we | +0.032 |
ep | +0.028 |
bel | +0.026 |
ilot | +0.026 |
men | +0.025 |
Neg logit contributions | |
Bruce | -0.034 |
Penny | -0.034 |
Cindy | -0.033 |
Emmy | -0.032 |
Lilly | -0.032 |
Token | He |
Token ID | 679 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Penny | +0.016 |
Bruce | +0.016 |
Cindy | +0.015 |
Emmy | +0.015 |
Lilly | +0.015 |
Neg logit contributions | |
we | -0.015 |
ep | -0.014 |
bel | -0.013 |
men | -0.012 |
ilot | -0.012 |
Token | wanted |
Token ID | 2227 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
Bruce | +0.005 |
Penny | +0.005 |
Cindy | +0.005 |
Emmy | +0.005 |
Lilly | +0.005 |
Neg logit contributions | |
we | -0.008 |
ilot | -0.007 |
bel | -0.007 |
angels | -0.007 |
room | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
Bruce | +0.024 |
Penny | +0.024 |
Cindy | +0.023 |
Emmy | +0.023 |
Lilly | +0.022 |
Neg logit contributions | |
we | -0.027 |
ep | -0.024 |
bel | -0.023 |
ilot | -0.022 |
ity | -0.022 |
Token | hold |
Token ID | 1745 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
we | +0.002 |
ep | +0.002 |
ity | +0.001 |
bel | +0.001 |
anas | +0.001 |
Neg logit contributions | |
Bruce | -0.001 |
Cindy | -0.001 |
Penny | -0.001 |
Emmy | -0.001 |
Lilly | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
we | +0.072 |
ep | +0.064 |
bel | +0.060 |
men | +0.057 |
ilot | +0.056 |
Neg logit contributions | |
Bruce | -0.082 |
Penny | -0.081 |
Cindy | -0.078 |
Lilly | -0.076 |
Emmy | -0.076 |
Token | finish |
Token ID | 5461 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
we | +0.011 |
ep | +0.010 |
bel | +0.010 |
men | +0.009 |
angels | +0.009 |
Neg logit contributions | |
Bruce | -0.012 |
Penny | -0.011 |
Cindy | -0.011 |
Lilly | -0.011 |
Emmy | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
Bruce | +0.011 |
Cindy | +0.010 |
Penny | +0.010 |
Emmy | +0.009 |
Lilly | +0.009 |
Neg logit contributions | |
we | -0.011 |
ep | -0.010 |
bel | -0.009 |
angels | -0.008 |
men | -0.008 |
Token | work |
Token ID | 670 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
we | +0.040 |
ep | +0.036 |
ilot | +0.034 |
bel | +0.033 |
men | +0.033 |
Neg logit contributions | |
Penny | -0.028 |
Bruce | -0.027 |
Cindy | -0.026 |
Emmy | -0.026 |
Lilly | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
we | +0.006 |
ep | +0.005 |
bel | +0.005 |
men | +0.004 |
ilot | +0.004 |
Neg logit contributions | |
Bruce | -0.007 |
Penny | -0.007 |
Cindy | -0.007 |
Lilly | -0.006 |
Emmy | -0.006 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
we | +0.030 |
ep | +0.025 |
bel | +0.024 |
men | +0.023 |
ilot | +0.023 |
Neg logit contributions | |
Bruce | -0.043 |
Penny | -0.042 |
Cindy | -0.041 |
Emmy | -0.040 |
Harriet | -0.039 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
Bruce | +0.123 |
Penny | +0.123 |
Cindy | +0.119 |
Emmy | +0.116 |
Lilly | +0.116 |
Neg logit contributions | |
we | -0.096 |
ep | -0.085 |
bel | -0.079 |
men | -0.075 |
ilot | -0.075 |
Token | upon |
Token ID | 2402 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
we | +0.099 |
ep | +0.091 |
bel | +0.087 |
ilot | +0.084 |
men | +0.084 |
Neg logit contributions | |
Bruce | -0.093 |
Penny | -0.090 |
Cindy | -0.089 |
Emmy | -0.084 |
Harriet | -0.083 |
Token | a |
Token ID | 257 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
we | +0.032 |
men | +0.029 |
ep | +0.028 |
ney | +0.028 |
bel | +0.028 |
Neg logit contributions | |
Penny | -0.019 |
Bruce | -0.018 |
Sophie | -0.017 |
Emmy | -0.017 |
Lilly | -0.016 |
Token | time |
Token ID | 640 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Penny | +0.015 |
Bruce | +0.014 |
Sophie | +0.014 |
Lilly | +0.013 |
Cindy | +0.013 |
Neg logit contributions | |
we | -0.031 |
bel | -0.027 |
men | -0.026 |
ep | -0.026 |
angels | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
we | +0.014 |
ep | +0.013 |
bel | +0.013 |
men | +0.012 |
ilot | +0.012 |
Neg logit contributions | |
Bruce | -0.008 |
Penny | -0.008 |
Cindy | -0.008 |
Emmy | -0.007 |
Lilly | -0.007 |
Token | want |
Token ID | 765 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
we | +0.003 |
ep | +0.003 |
ity | +0.002 |
song | +0.002 |
songs | +0.002 |
Neg logit contributions | |
Cindy | -0.003 |
Bruce | -0.003 |
Penny | -0.003 |
Emmy | -0.003 |
Harriet | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
we | +0.019 |
ep | +0.015 |
men | +0.015 |
songs | +0.015 |
angels | +0.015 |
Neg logit contributions | |
Cindy | -0.029 |
Bruce | -0.029 |
Penny | -0.028 |
Emmy | -0.028 |
Lilly | -0.027 |
Token | try |
Token ID | 1949 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
we | +0.011 |
ep | +0.010 |
ity | +0.009 |
bel | +0.009 |
men | +0.009 |
Neg logit contributions | |
Penny | -0.012 |
Bruce | -0.012 |
Cindy | -0.012 |
Emmy | -0.011 |
Harriet | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
we | +0.033 |
ep | +0.029 |
men | +0.026 |
bel | +0.026 |
angels | +0.026 |
Neg logit contributions | |
Bruce | -0.032 |
Penny | -0.031 |
Cindy | -0.031 |
Emmy | -0.030 |
Lilly | -0.029 |
Token | ." |
Token ID | 526 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
Penny | +0.015 |
Bruce | +0.015 |
Cindy | +0.014 |
Lilly | +0.014 |
Emmy | +0.014 |
Neg logit contributions | |
we | -0.017 |
ep | -0.015 |
bel | -0.015 |
ilot | -0.014 |
men | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Penny | +0.029 |
Bruce | +0.029 |
Cindy | +0.028 |
Lilly | +0.027 |
Emmy | +0.027 |
Neg logit contributions | |
we | -0.024 |
ep | -0.022 |
bel | -0.020 |
men | -0.020 |
ilot | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
we | +0.007 |
ep | +0.006 |
bel | +0.006 |
men | +0.005 |
ity | +0.005 |
Neg logit contributions | |
Penny | -0.007 |
Bruce | -0.007 |
Cindy | -0.007 |
Lilly | -0.007 |
Emmy | -0.006 |
Token | I |
Token ID | 40 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
we | +0.004 |
ep | +0.004 |
bel | +0.004 |
men | +0.004 |
ilot | +0.003 |
Neg logit contributions | |
Penny | -0.007 |
Cindy | -0.006 |
Bruce | -0.006 |
Hannah | -0.006 |
Holly | -0.006 |
Token | zzy |
Token ID | 31570 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
Bruce | +0.110 |
Penny | +0.109 |
Cindy | +0.105 |
Emmy | +0.103 |
Harriet | +0.100 |
Neg logit contributions | |
we | -0.094 |
ep | -0.090 |
bel | -0.086 |
ilot | -0.081 |
z | -0.078 |
Token | was |
Token ID | 373 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
we | +0.040 |
ep | +0.036 |
bel | +0.033 |
men | +0.032 |
ilot | +0.032 |
Neg logit contributions | |
Bruce | -0.040 |
Penny | -0.040 |
Cindy | -0.038 |
Emmy | -0.037 |
Lilly | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Penny | +0.009 |
Bruce | +0.009 |
Emmy | +0.009 |
Cindy | +0.009 |
Lilly | +0.009 |
Neg logit contributions | |
ep | -0.007 |
we | -0.007 |
ggy | -0.006 |
ilot | -0.006 |
bel | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
we | +0.004 |
ep | +0.004 |
bel | +0.003 |
men | +0.003 |
ilot | +0.003 |
Neg logit contributions | |
Bruce | -0.004 |
Cindy | -0.004 |
Penny | -0.004 |
Harriet | -0.004 |
Emmy | -0.004 |
Token | goodbye |
Token ID | 24829 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
Bruce | +0.077 |
Penny | +0.077 |
Cindy | +0.074 |
Emmy | +0.072 |
Lilly | +0.072 |
Neg logit contributions | |
we | -0.085 |
ep | -0.078 |
bel | -0.073 |
ilot | -0.070 |
men | -0.070 |
Token | so |
Token ID | 523 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Penny | +0.014 |
Bruce | +0.014 |
Cindy | +0.013 |
Lilly | +0.013 |
Emmy | +0.013 |
Neg logit contributions | |
we | -0.015 |
ep | -0.014 |
bel | -0.013 |
ilot | -0.013 |
men | -0.012 |
Token | that |
Token ID | 326 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
Penny | +0.010 |
Bruce | +0.010 |
Cindy | +0.010 |
Lilly | +0.010 |
Emmy | +0.010 |
Neg logit contributions | |
we | -0.013 |
ep | -0.012 |
anas | -0.011 |
ilot | -0.011 |
bel | -0.011 |
Token | even |
Token ID | 772 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
Bruce | +0.035 |
Penny | +0.034 |
Cindy | +0.034 |
Emmy | +0.033 |
Lilly | +0.032 |
Neg logit contributions | |
we | -0.029 |
ep | -0.026 |
men | -0.025 |
bel | -0.024 |
angels | -0.023 |
Token | when |
Token ID | 618 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
we | +0.025 |
ep | +0.023 |
bel | +0.022 |
men | +0.021 |
songs | +0.020 |
Neg logit contributions | |
Bruce | -0.023 |
Penny | -0.023 |
Cindy | -0.022 |
Emmy | -0.021 |
Lilly | -0.021 |
Token | they |
Token ID | 484 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
we | +0.020 |
ep | +0.018 |
men | +0.017 |
bel | +0.017 |
angels | +0.016 |
Neg logit contributions | |
Bruce | -0.024 |
Penny | -0.024 |
Cindy | -0.024 |
Emmy | -0.023 |
Lilly | -0.023 |
Token | were |
Token ID | 547 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
we | +0.007 |
ep | +0.007 |
bel | +0.007 |
men | +0.006 |
ilot | +0.006 |
Neg logit contributions | |
Cindy | -0.009 |
Bruce | -0.009 |
Penny | -0.009 |
Emmy | -0.009 |
Harriet | -0.009 |
Token | apart |
Token ID | 5475 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ep | +0.009 |
we | +0.008 |
bel | +0.007 |
ilot | +0.007 |
men | +0.007 |
Neg logit contributions | |
Bruce | -0.009 |
Penny | -0.008 |
Cindy | -0.008 |
Emmy | -0.008 |
Lilly | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
Bruce | +0.047 |
Cindy | +0.047 |
Penny | +0.047 |
Harriet | +0.044 |
Emmy | +0.044 |
Neg logit contributions | |
we | -0.050 |
ep | -0.044 |
men | -0.042 |
bel | -0.041 |
angels | -0.040 |
Token | they |
Token ID | 484 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Penny | +0.026 |
Bruce | +0.026 |
Cindy | +0.025 |
Emmy | +0.024 |
Lilly | +0.024 |
Neg logit contributions | |
we | -0.021 |
ep | -0.019 |
bel | -0.018 |
men | -0.017 |
angels | -0.017 |
Token | forever |
Token ID | 8097 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Bruce | +0.047 |
Penny | +0.047 |
Cindy | +0.046 |
Emmy | +0.044 |
Lilly | +0.043 |
Neg logit contributions | |
we | -0.052 |
ep | -0.046 |
bel | -0.043 |
men | -0.042 |
ilot | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
we | +0.049 |
ep | +0.044 |
bel | +0.041 |
men | +0.039 |
ilot | +0.039 |
Neg logit contributions | |
Penny | -0.057 |
Bruce | -0.057 |
Cindy | -0.056 |
Emmy | -0.054 |
Lilly | -0.054 |
Token | ever |
Token ID | 1683 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
we | +0.002 |
ep | +0.002 |
bel | +0.002 |
men | +0.002 |
ilot | +0.002 |
Neg logit contributions | |
Bruce | -0.002 |
Penny | -0.002 |
Cindy | -0.002 |
Emmy | -0.002 |
Lilly | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
we | +0.124 |
ep | +0.103 |
angels | +0.099 |
men | +0.099 |
songs | +0.098 |
Neg logit contributions | |
Bruce | -0.134 |
Penny | -0.132 |
Cindy | -0.130 |
Emmy | -0.127 |
Harriet | -0.125 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
we | +0.032 |
ep | +0.028 |
bel | +0.026 |
men | +0.025 |
ilot | +0.025 |
Neg logit contributions | |
Bruce | -0.040 |
Penny | -0.040 |
Cindy | -0.039 |
Emmy | -0.038 |
Lilly | -0.038 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Bruce | +0.133 |
Penny | +0.132 |
Cindy | +0.128 |
Emmy | +0.124 |
Lilly | +0.124 |
Neg logit contributions | |
we | -0.134 |
ep | -0.120 |
bel | -0.110 |
men | -0.108 |
ilot | -0.108 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
we | +0.083 |
ep | +0.076 |
bel | +0.072 |
ilot | +0.070 |
men | +0.070 |
Neg logit contributions | |
Bruce | -0.068 |
Penny | -0.067 |
Cindy | -0.065 |
Emmy | -0.062 |
Lilly | -0.061 |
Token | a |
Token ID | 257 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
we | +0.014 |
men | +0.012 |
bel | +0.012 |
ep | +0.012 |
ney | +0.012 |
Neg logit contributions | |
Penny | -0.008 |
Bruce | -0.008 |
Emmy | -0.007 |
Sophie | -0.007 |
Cindy | -0.007 |
Token | time |
Token ID | 640 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
Penny | +0.021 |
Bruce | +0.020 |
Sophie | +0.020 |
Cindy | +0.019 |
Lilly | +0.019 |
Neg logit contributions | |
we | -0.043 |
bel | -0.038 |
men | -0.037 |
ep | -0.037 |
angels | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Bruce | +0.001 |
Penny | +0.001 |
Cindy | +0.001 |
Emmy | +0.001 |
Lilly | +0.001 |
Neg logit contributions | |
we | -0.002 |
ep | -0.002 |
bel | -0.002 |
ilot | -0.002 |
men | -0.002 |
Token | there |
Token ID | 612 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Penny | +0.054 |
Bruce | +0.054 |
Cindy | +0.052 |
Lilly | +0.051 |
Emmy | +0.050 |
Neg logit contributions | |
we | -0.072 |
ep | -0.065 |
bel | -0.062 |
anas | -0.061 |
men | -0.061 |
Token | their |
Token ID | 511 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
we | +0.050 |
bel | +0.044 |
ney | +0.044 |
ep | +0.043 |
z | +0.041 |
Neg logit contributions | |
Penny | -0.044 |
Bruce | -0.043 |
Cindy | -0.042 |
Sophie | -0.041 |
Lilly | -0.041 |
Token | face |
Token ID | 1986 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
we | +0.067 |
ep | +0.057 |
Some | +0.054 |
men | +0.053 |
Ch | +0.052 |
Neg logit contributions | |
Penny | -0.071 |
Cindy | -0.069 |
Bruce | -0.067 |
Sophie | -0.067 |
Lilly | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
we | +0.059 |
ep | +0.055 |
bel | +0.054 |
anas | +0.051 |
ilot | +0.050 |
Neg logit contributions | |
Penny | -0.043 |
Bruce | -0.040 |
Lilly | -0.039 |
Cindy | -0.039 |
Sophie | -0.039 |
Token | They |
Token ID | 1119 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
we | +0.034 |
ep | +0.033 |
bel | +0.030 |
ity | +0.029 |
z | +0.028 |
Neg logit contributions | |
Penny | -0.035 |
Bruce | -0.034 |
Cindy | -0.033 |
Lilly | -0.033 |
Sophie | -0.033 |
Token | are |
Token ID | 389 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
ep | +0.003 |
we | +0.003 |
bel | +0.002 |
ilot | +0.002 |
songs | +0.002 |
Neg logit contributions | |
Bruce | -0.004 |
Penny | -0.004 |
Cindy | -0.004 |
Emmy | -0.004 |
Lilly | -0.003 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
we | +0.019 |
ep | +0.018 |
bel | +0.016 |
men | +0.015 |
angels | +0.015 |
Neg logit contributions | |
Bruce | -0.027 |
Penny | -0.027 |
Cindy | -0.026 |
Emmy | -0.026 |
Lilly | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
we | +0.139 |
ep | +0.139 |
bel | +0.128 |
ilot | +0.125 |
ney | +0.123 |
Neg logit contributions | |
Penny | -0.114 |
Bruce | -0.111 |
Cindy | -0.107 |
Lilly | -0.106 |
Sophie | -0.105 |
Token | Their |
Token ID | 5334 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
we | +0.035 |
ep | +0.033 |
bel | +0.030 |
ity | +0.028 |
men | +0.028 |
Neg logit contributions | |
Penny | -0.039 |
Bruce | -0.039 |
Cindy | -0.038 |
Lilly | -0.037 |
Emmy | -0.036 |
Token | moms |
Token ID | 34015 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
we | +0.046 |
ep | +0.041 |
bel | +0.037 |
anas | +0.035 |
ilot | +0.035 |
Neg logit contributions | |
Penny | -0.062 |
Bruce | -0.061 |
Cindy | -0.060 |
Lilly | -0.058 |
Emmy | -0.058 |
Token | are |
Token ID | 389 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
Bruce | +0.056 |
Penny | +0.055 |
Emmy | +0.054 |
Cindy | +0.054 |
Lilly | +0.053 |
Neg logit contributions | |
we | -0.044 |
ep | -0.044 |
men | -0.038 |
angels | -0.038 |
ilot | -0.037 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
we | +0.020 |
ep | +0.019 |
bel | +0.017 |
men | +0.017 |
angels | +0.016 |
Neg logit contributions | |
Bruce | -0.024 |
Penny | -0.024 |
Cindy | -0.023 |
Emmy | -0.023 |
Lilly | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Bruce | +0.011 |
Penny | +0.011 |
Cindy | +0.011 |
Emmy | +0.010 |
Lilly | +0.010 |
Neg logit contributions | |
we | -0.009 |
ep | -0.009 |
bel | -0.008 |
men | -0.008 |
ity | -0.008 |
Token | wonderful |
Token ID | 7932 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
Penny | +0.012 |
Bruce | +0.012 |
Cindy | +0.011 |
Emmy | +0.011 |
Lilly | +0.011 |
Neg logit contributions | |
we | -0.012 |
ep | -0.011 |
bel | -0.010 |
men | -0.010 |
ilot | -0.010 |
Token | story |
Token ID | 1621 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Bruce | +0.027 |
Penny | +0.027 |
Cindy | +0.026 |
Emmy | +0.025 |
Lilly | +0.025 |
Neg logit contributions | |
we | -0.020 |
ep | -0.018 |
bel | -0.017 |
men | -0.016 |
ilot | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
we | +0.095 |
ep | +0.087 |
men | +0.080 |
ilot | +0.078 |
bel | +0.078 |
Neg logit contributions | |
Bruce | -0.103 |
Penny | -0.100 |
Cindy | -0.097 |
Lilly | -0.093 |
Emmy | -0.093 |
Token | You |
Token ID | 921 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
we | +0.005 |
ep | +0.005 |
ilot | +0.004 |
bel | +0.004 |
anas | +0.004 |
Neg logit contributions | |
Bruce | -0.006 |
Penny | -0.006 |
Cindy | -0.006 |
Emmy | -0.005 |
Harriet | -0.005 |
Token | know |
Token ID | 760 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Cindy | +0.074 |
Bruce | +0.074 |
Penny | +0.071 |
Sophie | +0.069 |
Hannah | +0.068 |
Neg logit contributions | |
ep | -0.065 |
we | -0.062 |
ilot | -0.059 |
bel | -0.056 |
ity | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
we | +0.074 |
ep | +0.067 |
angels | +0.063 |
men | +0.063 |
ity | +0.061 |
Neg logit contributions | |
Bruce | -0.070 |
Penny | -0.069 |
Cindy | -0.066 |
Lilly | -0.064 |
Emmy | -0.064 |
Token | stories |
Token ID | 3923 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
Bruce | +0.028 |
Penny | +0.027 |
Cindy | +0.026 |
Emmy | +0.026 |
Lilly | +0.025 |
Neg logit contributions | |
we | -0.032 |
ep | -0.029 |
bel | -0.027 |
men | -0.026 |
songs | -0.026 |
Token | are |
Token ID | 389 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Bruce | +0.026 |
Penny | +0.026 |
Cindy | +0.025 |
Lilly | +0.024 |
Emmy | +0.024 |
Neg logit contributions | |
we | -0.026 |
ep | -0.023 |
bel | -0.022 |
men | -0.022 |
ilot | -0.021 |
Token | important |
Token ID | 1593 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
we | +0.004 |
ep | +0.004 |
men | +0.004 |
bel | +0.004 |
songs | +0.004 |
Neg logit contributions | |
Bruce | -0.004 |
Penny | -0.004 |
Cindy | -0.004 |
Emmy | -0.004 |
Lilly | -0.004 |
Token | because |
Token ID | 780 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
Bruce | +0.152 |
Penny | +0.151 |
Cindy | +0.146 |
Lilly | +0.142 |
Emmy | +0.142 |
Neg logit contributions | |
we | -0.140 |
ep | -0.123 |
bel | -0.116 |
men | -0.113 |
ilot | -0.110 |
Token | said |
Token ID | 531 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Bruce | +0.016 |
Penny | +0.016 |
Cindy | +0.015 |
Emmy | +0.014 |
Lilly | +0.014 |
Neg logit contributions | |
we | -0.027 |
ep | -0.025 |
bel | -0.024 |
men | -0.023 |
ilot | -0.023 |
Token | his |
Token ID | 465 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Bruce | +0.045 |
Penny | +0.045 |
Cindy | +0.045 |
Emmy | +0.042 |
Sophie | +0.041 |
Neg logit contributions | |
we | -0.061 |
ep | -0.057 |
bel | -0.053 |
men | -0.052 |
ilot | -0.050 |
Token | friend |
Token ID | 1545 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
we | +0.061 |
bel | +0.052 |
ep | +0.049 |
anas | +0.046 |
ney | +0.044 |
Neg logit contributions | |
Bruce | -0.081 |
Penny | -0.081 |
Cindy | -0.078 |
Lilly | -0.077 |
Emmy | -0.074 |
Token | Lily |
Token ID | 20037 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
we | +0.031 |
ep | +0.028 |
bel | +0.026 |
men | +0.025 |
ilot | +0.025 |
Neg logit contributions | |
Bruce | -0.035 |
Penny | -0.035 |
Cindy | -0.034 |
Emmy | -0.032 |
Lilly | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
Bruce | +0.039 |
Penny | +0.039 |
Cindy | +0.038 |
Emmy | +0.037 |
Lilly | +0.037 |
Neg logit contributions | |
we | -0.033 |
ep | -0.029 |
bel | -0.027 |
men | -0.026 |
ilot | -0.026 |
Token | " |
Token ID | 366 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
we | +0.027 |
ep | +0.024 |
bel | +0.021 |
men | +0.021 |
ilot | +0.021 |
Neg logit contributions | |
Bruce | -0.041 |
Penny | -0.041 |
Cindy | -0.040 |
Emmy | -0.039 |
Lilly | -0.039 |
Token | We |
Token ID | 1135 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
ep | +0.058 |
ilot | +0.056 |
men | +0.054 |
ggy | +0.052 |
anas | +0.052 |
Neg logit contributions | |
Bruce | -0.073 |
Penny | -0.071 |
Emmy | -0.066 |
Cindy | -0.066 |
Lilly | -0.065 |
Token | 'll |
Token ID | 1183 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
Penny | +0.044 |
Cindy | +0.043 |
Bruce | +0.043 |
Sophie | +0.043 |
Harriet | +0.042 |
Neg logit contributions | |
ep | -0.034 |
we | -0.031 |
ilot | -0.031 |
as | -0.030 |
ney | -0.028 |
Token | always |
Token ID | 1464 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
we | +0.001 |
ep | +0.001 |
ilot | +0.001 |
anas | +0.001 |
bel | +0.001 |
Neg logit contributions | |
Penny | -0.001 |
Bruce | -0.001 |
Cindy | -0.001 |
Sophie | -0.001 |
Lilly | -0.001 |
Token | be |
Token ID | 307 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
we | +0.037 |
ep | +0.035 |
bel | +0.031 |
ilot | +0.030 |
men | +0.030 |
Neg logit contributions | |
Penny | -0.039 |
Bruce | -0.039 |
Cindy | -0.038 |
Lilly | -0.037 |
Emmy | -0.037 |
Token | here |
Token ID | 994 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
we | +0.045 |
ep | +0.044 |
bel | +0.036 |
men | +0.036 |
ilot | +0.035 |
Neg logit contributions | |
Bruce | -0.058 |
Penny | -0.057 |
Cindy | -0.056 |
Emmy | -0.054 |
Lilly | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Penny | +0.005 |
Emmy | +0.005 |
Cindy | +0.005 |
Lilly | +0.005 |
Bruce | +0.005 |
Neg logit contributions | |
we | -0.006 |
ep | -0.006 |
ity | -0.006 |
bel | -0.006 |
men | -0.005 |
Token | After |
Token ID | 3260 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Penny | +0.007 |
Emmy | +0.007 |
Cindy | +0.007 |
Bruce | +0.007 |
Lilly | +0.007 |
Neg logit contributions | |
we | -0.005 |
ilot | -0.004 |
ep | -0.004 |
bel | -0.004 |
men | -0.004 |
Token | they |
Token ID | 484 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
Bruce | +0.009 |
Penny | +0.009 |
Cindy | +0.009 |
Emmy | +0.009 |
Lilly | +0.009 |
Neg logit contributions | |
we | -0.008 |
ep | -0.007 |
bel | -0.007 |
men | -0.006 |
ilot | -0.006 |
Token | organized |
Token ID | 8389 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Bruce | +0.003 |
Cindy | +0.003 |
Penny | +0.002 |
Harriet | +0.002 |
Emmy | +0.002 |
Neg logit contributions | |
ep | -0.003 |
we | -0.003 |
bel | -0.003 |
room | -0.002 |
as | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Bruce | +0.078 |
Penny | +0.071 |
Gab | +0.070 |
Cindy | +0.070 |
Harriet | +0.069 |
Neg logit contributions | |
we | -0.038 |
ep | -0.038 |
songs | -0.036 |
men | -0.033 |
angels | -0.033 |
Token | game |
Token ID | 983 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Penny | +0.020 |
Bruce | +0.020 |
Cindy | +0.020 |
Emmy | +0.019 |
Lilly | +0.019 |
Neg logit contributions | |
we | -0.012 |
ep | -0.010 |
bel | -0.009 |
ilot | -0.009 |
men | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
we | +0.073 |
men | +0.065 |
ep | +0.065 |
bel | +0.064 |
room | +0.062 |
Neg logit contributions | |
Bruce | -0.066 |
Penny | -0.062 |
Cindy | -0.061 |
Harriet | -0.059 |
Emmy | -0.058 |
Token | all |
Token ID | 477 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
Bruce | +0.028 |
Penny | +0.026 |
Cindy | +0.025 |
Harriet | +0.025 |
Emmy | +0.025 |
Neg logit contributions | |
we | -0.031 |
ep | -0.027 |
bel | -0.026 |
men | -0.026 |
songs | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
we | +0.032 |
ep | +0.031 |
bel | +0.029 |
men | +0.027 |
songs | +0.027 |
Neg logit contributions | |
Bruce | -0.035 |
Penny | -0.033 |
Cindy | -0.033 |
Harriet | -0.032 |
Emmy | -0.031 |
Token | kids |
Token ID | 3988 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Bruce | +0.019 |
Penny | +0.019 |
Cindy | +0.018 |
Emmy | +0.018 |
Lilly | +0.018 |
Neg logit contributions | |
we | -0.011 |
ep | -0.009 |
bel | -0.008 |
men | -0.008 |
ilot | -0.008 |
Token | were |
Token ID | 547 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Bruce | +0.014 |
Cindy | +0.014 |
Penny | +0.014 |
Harriet | +0.013 |
Emmy | +0.013 |
Neg logit contributions | |
we | -0.012 |
ep | -0.011 |
bel | -0.011 |
men | -0.010 |
as | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
Penny | +0.003 |
Bruce | +0.003 |
Cindy | +0.003 |
Emmy | +0.003 |
Lilly | +0.003 |
Neg logit contributions | |
we | -0.003 |
ep | -0.003 |
bel | -0.003 |
men | -0.002 |
ilot | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
we | +0.017 |
ep | +0.016 |
bel | +0.015 |
songs | +0.014 |
men | +0.014 |
Neg logit contributions | |
Bruce | -0.013 |
Penny | -0.013 |
Cindy | -0.012 |
Emmy | -0.012 |
Lilly | -0.012 |
Token | g |
Token ID | 308 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Penny | +0.022 |
Bruce | +0.022 |
Cindy | +0.021 |
Lilly | +0.021 |
Emmy | +0.021 |
Neg logit contributions | |
we | -0.018 |
ep | -0.016 |
bel | -0.015 |
men | -0.014 |
ilot | -0.014 |
Token | az |
Token ID | 1031 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
we | +0.088 |
ep | +0.084 |
bel | +0.078 |
men | +0.076 |
Ch | +0.075 |
Neg logit contributions | |
Bruce | -0.068 |
Penny | -0.067 |
Lilly | -0.066 |
Emmy | -0.065 |
Jackie | -0.064 |
Token | eb |
Token ID | 1765 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
we | +0.118 |
ep | +0.107 |
bel | +0.104 |
men | +0.102 |
angels | +0.101 |
Neg logit contributions | |
Bruce | -0.106 |
Penny | -0.104 |
Cindy | -0.103 |
Emmy | -0.100 |
Lilly | -0.099 |
Token | o |
Token ID | 78 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
we | +0.176 |
bel | +0.152 |
songs | +0.150 |
Mark | +0.146 |
Some | +0.146 |
Neg logit contributions | |
Penny | -0.200 |
Bruce | -0.198 |
Emmy | -0.189 |
Lilly | -0.189 |
Cindy | -0.188 |
Token | and |
Token ID | 290 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
we | +0.205 |
ep | +0.186 |
bel | +0.176 |
men | +0.168 |
anas | +0.166 |
Neg logit contributions | |
Penny | -0.199 |
Bruce | -0.198 |
Cindy | -0.190 |
Lilly | -0.186 |
Emmy | -0.186 |
Token | went |
Token ID | 1816 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
we | +0.001 |
ep | +0.001 |
bel | +0.001 |
men | +0.000 |
songs | +0.000 |
Neg logit contributions | |
Bruce | -0.001 |
Penny | -0.001 |
Cindy | -0.000 |
Emmy | -0.000 |
Lilly | -0.000 |
Token | back |
Token ID | 736 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
we | +0.013 |
ep | +0.013 |
bel | +0.011 |
z | +0.011 |
men | +0.011 |
Neg logit contributions | |
Bruce | -0.013 |
Penny | -0.012 |
Emmy | -0.012 |
Cindy | -0.012 |
Jackie | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
we | +0.022 |
ep | +0.020 |
bel | +0.019 |
men | +0.018 |
z | +0.018 |
Neg logit contributions | |
Bruce | -0.020 |
Penny | -0.020 |
Cindy | -0.019 |
Emmy | -0.019 |
Lilly | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
we | +0.011 |
ep | +0.010 |
angels | +0.009 |
songs | +0.009 |
song | +0.009 |
Neg logit contributions | |
Bruce | -0.011 |
Penny | -0.011 |
Cindy | -0.011 |
Emmy | -0.010 |
Lilly | -0.010 |
Token | liked |
Token ID | 8288 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
Penny | +0.086 |
Bruce | +0.084 |
Cindy | +0.081 |
Emmy | +0.080 |
Lilly | +0.080 |
Neg logit contributions | |
we | -0.085 |
ep | -0.075 |
bel | -0.073 |
ilot | -0.071 |
men | -0.071 |
Token | to |
Token ID | 284 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Penny | +0.013 |
Bruce | +0.013 |
Cindy | +0.013 |
Emmy | +0.012 |
Lilly | +0.012 |
Neg logit contributions | |
we | -0.018 |
ep | -0.018 |
ilot | -0.017 |
ity | -0.016 |
ney | -0.016 |
Token | play |
Token ID | 711 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
Penny | +0.005 |
Bruce | +0.005 |
Lilly | +0.004 |
Emmy | +0.004 |
Cindy | +0.004 |
Neg logit contributions | |
we | -0.009 |
ep | -0.008 |
men | -0.007 |
bel | -0.007 |
as | -0.007 |
Token | hide |
Token ID | 7808 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
we | +0.004 |
ilot | +0.004 |
ney | +0.004 |
ep | +0.004 |
as | +0.004 |
Neg logit contributions | |
Penny | -0.003 |
Bruce | -0.003 |
Lilly | -0.003 |
Cindy | -0.003 |
Emmy | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Penny | +0.142 |
Bruce | +0.138 |
Cindy | +0.135 |
Lilly | +0.134 |
Emmy | +0.131 |
Neg logit contributions | |
we | -0.097 |
ep | -0.084 |
ilot | -0.080 |
bel | -0.076 |
men | -0.075 |
Token | and |
Token ID | 392 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
we | +0.060 |
ep | +0.052 |
ilot | +0.045 |
men | +0.040 |
anas | +0.039 |
Neg logit contributions | |
Penny | -0.149 |
Bruce | -0.148 |
Cindy | -0.143 |
Lilly | -0.143 |
Emmy | -0.142 |
Token | - |
Token ID | 12 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
we | +0.118 |
ep | +0.103 |
ilot | +0.093 |
bel | +0.087 |
ney | +0.083 |
Neg logit contributions | |
Penny | -0.326 |
Bruce | -0.317 |
Cindy | -0.315 |
Lilly | -0.310 |
Emmy | -0.309 |
Token | seek |
Token ID | 36163 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
we | +0.124 |
ep | +0.116 |
ilot | +0.107 |
men | +0.104 |
ity | +0.104 |
Neg logit contributions | |
Bruce | -0.089 |
Penny | -0.088 |
Cindy | -0.085 |
Emmy | -0.081 |
Lilly | -0.081 |
Token | with |
Token ID | 351 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Penny | +0.001 |
Bruce | +0.001 |
Lilly | +0.001 |
Sophie | +0.001 |
Holly | +0.001 |
Neg logit contributions | |
we | -0.002 |
ep | -0.002 |
ilot | -0.002 |
ney | -0.002 |
anas | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
Bruce | +0.043 |
Penny | +0.042 |
Cindy | +0.040 |
Emmy | +0.039 |
Lilly | +0.039 |
Neg logit contributions | |
we | -0.066 |
ep | -0.062 |
bel | -0.058 |
men | -0.056 |
ilot | -0.056 |
Token | friends |
Token ID | 2460 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
Penny | +0.001 |
Bruce | +0.001 |
Cindy | +0.001 |
Lilly | +0.001 |
Emmy | +0.001 |
Neg logit contributions | |
we | -0.001 |
ep | -0.000 |
bel | -0.000 |
ity | -0.000 |
anas | -0.000 |
Token | M |
Token ID | 44 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
we | +0.023 |
ep | +0.019 |
bel | +0.018 |
songs | +0.018 |
men | +0.018 |
Neg logit contributions | |
Penny | -0.031 |
Sophie | -0.031 |
Jackie | -0.030 |
Harriet | -0.029 |
Bruce | -0.029 |
Token | ama |
Token ID | 1689 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
we | +0.182 |
bel | +0.160 |
ep | +0.154 |
songs | +0.149 |
Ch | +0.142 |
Neg logit contributions | |
Jackie | -0.158 |
Sophie | -0.155 |
Penny | -0.149 |
Lilly | -0.148 |
Bruce | -0.146 |
Token | shouted |
Token ID | 17293 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
we | +0.027 |
ep | +0.024 |
bel | +0.023 |
ilot | +0.022 |
men | +0.022 |
Neg logit contributions | |
Penny | -0.022 |
Bruce | -0.022 |
Cindy | -0.021 |
Lilly | -0.021 |
Emmy | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
Bruce | +0.046 |
Penny | +0.045 |
Cindy | +0.043 |
Emmy | +0.042 |
Lilly | +0.041 |
Neg logit contributions | |
we | -0.059 |
ep | -0.052 |
bel | -0.050 |
men | -0.049 |
ilot | -0.048 |
Token | " |
Token ID | 366 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Penny | +0.013 |
Bruce | +0.013 |
Cindy | +0.013 |
Lilly | +0.012 |
Emmy | +0.012 |
Neg logit contributions | |
we | -0.011 |
ep | -0.010 |
bel | -0.009 |
ney | -0.009 |
ity | -0.009 |
Token | Jamie |
Token ID | 48337 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
bel | +0.052 |
ggy | +0.052 |
ilot | +0.051 |
men | +0.051 |
anas | +0.050 |
Neg logit contributions | |
Sophie | -0.060 |
Penny | -0.058 |
Lilly | -0.058 |
Jackie | -0.057 |
Emmy | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
we | +0.242 |
ep | +0.224 |
bel | +0.207 |
men | +0.206 |
ilot | +0.206 |
Neg logit contributions | |
Bruce | -0.162 |
Penny | -0.161 |
Cindy | -0.154 |
Emmy | -0.148 |
Lilly | -0.147 |
Token | no |
Token ID | 645 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
Penny | +0.009 |
Bruce | +0.009 |
Cindy | +0.009 |
Lilly | +0.009 |
Emmy | +0.009 |
Neg logit contributions | |
we | -0.012 |
ep | -0.012 |
bel | -0.011 |
ilot | -0.011 |
men | -0.010 |
Token | ! |
Token ID | 0 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
we | +0.144 |
ep | +0.132 |
bel | +0.122 |
men | +0.120 |
ilot | +0.119 |
Neg logit contributions | |
Bruce | -0.116 |
Penny | -0.116 |
Cindy | -0.111 |
Emmy | -0.107 |
Lilly | -0.107 |
Token | You |
Token ID | 921 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
we | +0.065 |
ep | +0.062 |
bel | +0.058 |
ity | +0.055 |
songs | +0.055 |
Neg logit contributions | |
Penny | -0.054 |
Bruce | -0.053 |
Cindy | -0.051 |
Lilly | -0.051 |
Emmy | -0.050 |
Token | shouldn |
Token ID | 6584 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
Bruce | +0.048 |
Penny | +0.047 |
Cindy | +0.047 |
Lilly | +0.044 |
Emmy | +0.044 |
Neg logit contributions | |
we | -0.051 |
ep | -0.049 |
bel | -0.045 |
ilot | -0.044 |
men | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
we | +0.089 |
ep | +0.082 |
bel | +0.074 |
men | +0.074 |
ilot | +0.072 |
Neg logit contributions | |
Penny | -0.069 |
Bruce | -0.069 |
Cindy | -0.066 |
Emmy | -0.064 |
Lilly | -0.064 |
Token | keep |
Token ID | 1394 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
we | +0.018 |
ep | +0.017 |
bel | +0.015 |
men | +0.015 |
ilot | +0.015 |
Neg logit contributions | |
Bruce | -0.020 |
Penny | -0.020 |
Cindy | -0.019 |
Emmy | -0.018 |
Lilly | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
Bruce | +0.057 |
Penny | +0.057 |
Cindy | +0.055 |
Emmy | +0.052 |
Sophie | +0.052 |
Neg logit contributions | |
we | -0.063 |
ep | -0.058 |
men | -0.050 |
angels | -0.049 |
bel | -0.049 |
Token | ash |
Token ID | 12530 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Penny | +0.002 |
Bruce | +0.002 |
Cindy | +0.002 |
Lilly | +0.002 |
Emmy | +0.002 |
Neg logit contributions | |
we | -0.002 |
ep | -0.002 |
bel | -0.002 |
ilot | -0.002 |
anas | -0.002 |
Token | tr |
Token ID | 2213 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
Penny | +0.007 |
Bruce | +0.007 |
Lilly | +0.007 |
Cindy | +0.007 |
Emmy | +0.007 |
Neg logit contributions | |
we | -0.006 |
ep | -0.005 |
Some | -0.005 |
anas | -0.005 |
bel | -0.005 |
Token | ay |
Token ID | 323 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
we | +0.122 |
songs | +0.114 |
anas | +0.108 |
song | +0.107 |
ep | +0.106 |
Neg logit contributions | |
Emmy | -0.126 |
Lilly | -0.123 |
Penny | -0.122 |
Cindy | -0.117 |
Jackie | -0.113 |
Token | safe |
Token ID | 3338 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
we | +0.218 |
ep | +0.194 |
bel | +0.193 |
anas | +0.184 |
men | +0.181 |
Neg logit contributions | |
Penny | -0.189 |
Bruce | -0.186 |
Emmy | -0.185 |
Cindy | -0.182 |
Lilly | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
Bruce | +0.088 |
Penny | +0.088 |
Cindy | +0.087 |
Lilly | +0.083 |
Emmy | +0.083 |
Neg logit contributions | |
we | -0.068 |
ep | -0.059 |
bel | -0.055 |
men | -0.053 |
ney | -0.052 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
we | +0.022 |
ep | +0.019 |
ilot | +0.018 |
ney | +0.018 |
bel | +0.018 |
Neg logit contributions | |
Penny | -0.029 |
Bruce | -0.029 |
Cindy | -0.028 |
Emmy | -0.028 |
Lilly | -0.027 |
Token | Jack |
Token ID | 14295 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
Bruce | +0.141 |
Penny | +0.140 |
Cindy | +0.136 |
Emmy | +0.132 |
Lilly | +0.131 |
Neg logit contributions | |
we | -0.128 |
ep | -0.114 |
bel | -0.104 |
ilot | -0.103 |
men | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
ep | +0.020 |
we | +0.019 |
ney | +0.016 |
ity | +0.015 |
anas | +0.015 |
Neg logit contributions | |
Bruce | -0.035 |
Cindy | -0.035 |
Penny | -0.034 |
Emmy | -0.033 |
Stella | -0.032 |
Token | " |
Token ID | 366 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
Penny | +0.017 |
Bruce | +0.017 |
Cindy | +0.016 |
Lilly | +0.016 |
Emmy | +0.016 |
Neg logit contributions | |
we | -0.024 |
ep | -0.022 |
ney | -0.021 |
bel | -0.021 |
anas | -0.020 |
Token | A |
Token ID | 32 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
men | +0.031 |
ep | +0.030 |
anas | +0.030 |
we | +0.030 |
ilot | +0.029 |
Neg logit contributions | |
Penny | -0.033 |
Bruce | -0.032 |
Emmy | -0.032 |
Cindy | -0.032 |
Lilly | -0.031 |
Token | br |
Token ID | 1671 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
we | +0.039 |
ep | +0.034 |
bel | +0.032 |
anas | +0.030 |
men | +0.030 |
Neg logit contributions | |
Penny | -0.042 |
Bruce | -0.041 |
Cindy | -0.039 |
Emmy | -0.038 |
Lilly | -0.038 |
Token | ac |
Token ID | 330 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
we | +0.106 |
ggy | +0.075 |
anas | +0.075 |
men | +0.073 |
song | +0.073 |
Neg logit contributions | |
Penny | -0.148 |
Lilly | -0.140 |
Jackie | -0.138 |
Bruce | -0.137 |
Emmy | -0.135 |
Token | ad |
Token ID | 324 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
we | +0.246 |
bel | +0.217 |
anas | +0.211 |
men | +0.204 |
ower | +0.203 |
Neg logit contributions | |
Bruce | -0.135 |
Penny | -0.130 |
aback | -0.121 |
Sophie | -0.120 |
Lilly | -0.118 |
Token | ab |
Token ID | 397 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
we | +0.135 |
bel | +0.117 |
ep | +0.117 |
men | +0.108 |
ney | +0.107 |
Neg logit contributions | |
Penny | -0.143 |
Bruce | -0.141 |
Cindy | -0.133 |
Lilly | -0.131 |
Emmy | -0.131 |
Token | ra |
Token ID | 430 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
we | +0.218 |
ep | +0.187 |
Some | +0.172 |
ney | +0.171 |
men | +0.168 |
Neg logit contributions | |
Penny | -0.276 |
Bruce | -0.275 |
Cindy | -0.263 |
Sophie | -0.254 |
Lilly | -0.253 |
Token | !" |
Token ID | 2474 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
we | +0.156 |
ep | +0.143 |
bel | +0.133 |
men | +0.129 |
ilot | +0.129 |
Neg logit contributions | |
Bruce | -0.133 |
Penny | -0.133 |
Cindy | -0.128 |
Emmy | -0.123 |
Lilly | -0.123 |
Token | and |
Token ID | 290 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
Penny | +0.022 |
Bruce | +0.022 |
Cindy | +0.021 |
Lilly | +0.021 |
Emmy | +0.020 |
Neg logit contributions | |
we | -0.022 |
ep | -0.020 |
bel | -0.019 |
men | -0.018 |
ity | -0.018 |
Token | everyone |
Token ID | 2506 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Penny | +0.003 |
Bruce | +0.003 |
Cindy | +0.003 |
Lilly | +0.003 |
Emmy | +0.003 |
Neg logit contributions | |
we | -0.004 |
ep | -0.003 |
bel | -0.003 |
ilot | -0.003 |
men | -0.003 |
Token | would |
Token ID | 561 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
Penny | +0.017 |
Bruce | +0.017 |
Cindy | +0.016 |
Emmy | +0.016 |
Lilly | +0.016 |
Neg logit contributions | |
we | -0.017 |
ep | -0.016 |
bel | -0.014 |
men | -0.014 |
ilot | -0.014 |