Token | ags |
Token ID | 3775 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
opard | +0.115 |
ho | +0.099 |
pads | +0.090 |
affe | +0.090 |
ang | +0.089 |
Neg logit contributions | |
prise | -0.217 |
dessert | -0.212 |
Katie | -0.205 |
Jimmy | -0.205 |
Ethan | -0.204 |
Token | . |
Token ID | 13 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
ebra | +0.139 |
opard | +0.139 |
ite | +0.134 |
affe | +0.133 |
ites | +0.132 |
Neg logit contributions | |
Katie | -0.151 |
James | -0.146 |
Annie | -0.145 |
Jimmy | -0.145 |
Ethan | -0.145 |
Token | He |
Token ID | 679 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
ebra | +0.007 |
s | +0.007 |
gers | +0.006 |
opard | +0.006 |
ang | +0.006 |
Neg logit contributions | |
prise | -0.017 |
install | -0.015 |
Katie | -0.015 |
dining | -0.015 |
Esk | -0.014 |
Token | wrote |
Token ID | 2630 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
ebra | +0.019 |
s | +0.018 |
opard | +0.017 |
gers | +0.017 |
ang | +0.017 |
Neg logit contributions | |
prise | -0.024 |
install | -0.023 |
Katie | -0.022 |
Ethan | -0.022 |
Baby | -0.022 |
Token | z |
Token ID | 1976 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
ebra | +0.016 |
opard | +0.015 |
ang | +0.014 |
ite | +0.014 |
ites | +0.014 |
Neg logit contributions | |
Katie | -0.013 |
prise | -0.013 |
install | -0.012 |
Ethan | -0.012 |
Jimmy | -0.012 |
Token | ig |
Token ID | 328 |
Feature activation | +7.04e+00 |
Pos logit contributions | |
affe | +0.176 |
pads | +0.173 |
s | +0.172 |
opard | +0.165 |
tail | +0.163 |
Neg logit contributions | |
prise | -0.310 |
Ethan | -0.276 |
install | -0.267 |
Esk | -0.264 |
Katie | -0.263 |
Token | z |
Token ID | 89 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
ebra | +0.210 |
ang | +0.198 |
gers | +0.196 |
opard | +0.194 |
ites | +0.187 |
Neg logit contributions | |
install | -0.471 |
Katie | -0.466 |
Annie | -0.457 |
Ethan | -0.456 |
James | -0.453 |
Token | ags |
Token ID | 3775 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
opard | +0.139 |
pads | +0.120 |
ang | +0.119 |
ho | +0.118 |
s | +0.114 |
Neg logit contributions | |
prise | -0.235 |
Jimmy | -0.233 |
Katie | -0.231 |
dessert | -0.229 |
Ethan | -0.228 |
Token | on |
Token ID | 319 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
ebra | +0.193 |
opard | +0.193 |
affe | +0.185 |
ites | +0.185 |
ang | +0.184 |
Neg logit contributions | |
Katie | -0.178 |
James | -0.168 |
Sus | -0.168 |
Annie | -0.166 |
Jimmy | -0.164 |
Token | walls |
Token ID | 7714 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
ebra | +0.150 |
opard | +0.140 |
s | +0.140 |
ang | +0.137 |
gers | +0.136 |
Neg logit contributions | |
prise | -0.149 |
Katie | -0.143 |
install | -0.142 |
Ethan | -0.140 |
Baby | -0.137 |
Token | , |
Token ID | 11 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
Katie | +0.016 |
Annie | +0.016 |
Jimmy | +0.016 |
James | +0.015 |
install | +0.015 |
Neg logit contributions | |
opard | -0.010 |
ebra | -0.010 |
arrows | -0.009 |
gers | -0.009 |
ites | -0.009 |
Token | their |
Token ID | 511 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
prise | +0.144 |
install | +0.139 |
Katie | +0.138 |
Ethan | +0.136 |
Baby | +0.135 |
Neg logit contributions | |
ebra | -0.079 |
opard | -0.070 |
s | -0.069 |
ang | -0.068 |
gers | -0.067 |
Token | mouths |
Token ID | 28552 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
prise | +0.098 |
install | +0.093 |
Katie | +0.093 |
Ethan | +0.091 |
Baby | +0.090 |
Neg logit contributions | |
ebra | -0.054 |
s | -0.048 |
opard | -0.047 |
gers | -0.046 |
ang | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
ebra | +0.032 |
s | +0.027 |
opard | +0.026 |
ang | +0.026 |
gers | +0.026 |
Neg logit contributions | |
prise | -0.095 |
install | -0.092 |
Katie | -0.091 |
Ethan | -0.090 |
Baby | -0.089 |
Token | say |
Token ID | 910 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
prise | +0.025 |
Katie | +0.023 |
install | +0.022 |
Ethan | +0.022 |
dining | +0.022 |
Neg logit contributions | |
s | -0.025 |
ebra | -0.024 |
legs | -0.024 |
arrows | -0.024 |
gers | -0.023 |
Token | " |
Token ID | 366 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
ebra | +0.023 |
opard | +0.020 |
ang | +0.020 |
s | +0.020 |
gers | +0.020 |
Neg logit contributions | |
prise | -0.041 |
Katie | -0.039 |
install | -0.039 |
Ethan | -0.038 |
Baby | -0.038 |
Token | ah |
Token ID | 993 |
Feature activation | +7.00e+00 |
Pos logit contributions | |
ebra | +0.034 |
s | +0.032 |
opard | +0.031 |
gers | +0.031 |
ang | +0.031 |
Neg logit contributions | |
prise | -0.043 |
install | -0.041 |
Katie | -0.041 |
Ethan | -0.040 |
Baby | -0.039 |
Token | h |
Token ID | 71 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
ebra | +0.245 |
gers | +0.216 |
ang | +0.212 |
ites | +0.210 |
opard | +0.209 |
Neg logit contributions | |
prise | -0.477 |
install | -0.451 |
Katie | -0.448 |
Baby | -0.441 |
Ethan | -0.436 |
Token | ". |
Token ID | 1911 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ebra | +0.044 |
arrows | +0.043 |
gers | +0.041 |
ted | +0.041 |
ites | +0.040 |
Neg logit contributions | |
prise | -0.056 |
Katie | -0.052 |
install | -0.051 |
Baby | -0.050 |
Ethan | -0.049 |
Token | The |
Token ID | 383 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
prise | +0.085 |
install | +0.078 |
Katie | +0.077 |
Ethan | +0.075 |
Esk | +0.074 |
Neg logit contributions | |
ebra | -0.057 |
s | -0.056 |
opard | -0.051 |
gers | -0.051 |
ang | -0.050 |
Token | doctor |
Token ID | 6253 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ebra | +0.047 |
opard | +0.043 |
s | +0.043 |
legs | +0.042 |
gers | +0.042 |
Neg logit contributions | |
prise | -0.048 |
Katie | -0.048 |
Ethan | -0.044 |
install | -0.044 |
Annie | -0.044 |
Token | sometimes |
Token ID | 3360 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
prise | +0.026 |
Katie | +0.024 |
dining | +0.024 |
perfection | +0.024 |
Ethan | +0.024 |
Neg logit contributions | |
s | -0.018 |
ebra | -0.017 |
opard | -0.016 |
affe | -0.015 |
legs | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ebra | +0.012 |
opard | +0.011 |
ites | +0.011 |
ang | +0.011 |
ite | +0.011 |
Neg logit contributions | |
Katie | -0.012 |
prise | -0.012 |
Annie | -0.011 |
install | -0.011 |
Jimmy | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
Katie | +0.010 |
Ethan | +0.010 |
Baby | +0.010 |
Sus | +0.010 |
Em | +0.010 |
Neg logit contributions | |
ebra | -0.010 |
gers | -0.009 |
ites | -0.009 |
ang | -0.009 |
s | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
prise | +0.022 |
install | +0.021 |
Katie | +0.021 |
Ethan | +0.020 |
Baby | +0.020 |
Neg logit contributions | |
ebra | -0.020 |
opard | -0.019 |
s | -0.018 |
gers | -0.018 |
ang | -0.018 |
Token | When |
Token ID | 2215 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
install | +0.017 |
prise | +0.016 |
Ethan | +0.016 |
Esk | +0.015 |
Baby | +0.015 |
Neg logit contributions | |
ebra | -0.019 |
ites | -0.017 |
arms | -0.016 |
legs | -0.016 |
ite | -0.016 |
Token | Din |
Token ID | 23448 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
ebra | +0.028 |
affe | +0.027 |
opard | +0.025 |
ang | +0.025 |
ites | +0.025 |
Neg logit contributions | |
Baby | -0.022 |
Ethan | -0.022 |
Katie | -0.021 |
Em | -0.021 |
Sus | -0.021 |
Token | ah |
Token ID | 993 |
Feature activation | +6.87e+00 |
Pos logit contributions | |
ebra | +0.003 |
s | +0.003 |
gers | +0.003 |
opard | +0.002 |
legs | +0.002 |
Neg logit contributions | |
prise | -0.010 |
install | -0.010 |
Katie | -0.009 |
Ethan | -0.009 |
Esk | -0.009 |
Token | reached |
Token ID | 4251 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ebra | +0.359 |
opard | +0.337 |
gers | +0.327 |
ang | +0.325 |
ites | +0.321 |
Neg logit contributions | |
prise | -0.345 |
install | -0.331 |
Katie | -0.328 |
Ethan | -0.317 |
Baby | -0.314 |
Token | the |
Token ID | 262 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
ebra | +0.059 |
opard | +0.057 |
affe | +0.055 |
ang | +0.055 |
s | +0.054 |
Neg logit contributions | |
prise | -0.049 |
Katie | -0.049 |
install | -0.046 |
Annie | -0.045 |
Baby | -0.045 |
Token | lake |
Token ID | 13546 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ebra | +0.031 |
ang | +0.030 |
ites | +0.029 |
opard | +0.029 |
s | +0.029 |
Neg logit contributions | |
prise | -0.031 |
Katie | -0.029 |
install | -0.029 |
dessert | -0.028 |
dining | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
prise | +0.113 |
Katie | +0.113 |
install | +0.110 |
Baby | +0.108 |
Annie | +0.108 |
Neg logit contributions | |
ebra | -0.048 |
opard | -0.043 |
ang | -0.041 |
ites | -0.040 |
gers | -0.040 |
Token | she |
Token ID | 673 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ebra | +0.029 |
affe | +0.026 |
ites | +0.026 |
agging | +0.025 |
ang | +0.025 |
Neg logit contributions | |
Ethan | -0.030 |
Baby | -0.029 |
Katie | -0.029 |
Sus | -0.029 |
Em | -0.029 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
prise | +0.017 |
install | +0.016 |
Ethan | +0.015 |
Katie | +0.015 |
dining | +0.015 |
Neg logit contributions | |
ebra | -0.015 |
s | -0.014 |
ite | -0.014 |
ang | -0.014 |
opard | -0.014 |
Token | |
Token ID | 220 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
Katie | +0.048 |
Annie | +0.047 |
Laura | +0.045 |
Jessie | +0.044 |
Jamie | +0.043 |
Neg logit contributions | |
opard | -0.103 |
ebra | -0.097 |
ites | -0.096 |
ite | -0.095 |
ang | -0.095 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ebra | +0.024 |
s | +0.022 |
opard | +0.021 |
ang | +0.021 |
gers | +0.021 |
Neg logit contributions | |
prise | -0.032 |
install | -0.030 |
Katie | -0.029 |
Ethan | -0.029 |
dining | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
Katie | +0.006 |
Annie | +0.006 |
Jamie | +0.006 |
Jamie | +0.005 |
Laura | +0.005 |
Neg logit contributions | |
clubs | -0.013 |
ebra | -0.013 |
opard | -0.013 |
gers | -0.013 |
ite | -0.013 |
Token | Le |
Token ID | 3123 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Jamie | +0.008 |
Laura | +0.008 |
Laura | +0.008 |
Jason | +0.008 |
Katie | +0.008 |
Neg logit contributions | |
clubs | -0.011 |
opard | -0.011 |
ites | -0.010 |
ebra | -0.010 |
ang | -0.010 |
Token | ah |
Token ID | 993 |
Feature activation | +6.82e+00 |
Pos logit contributions | |
gers | +0.130 |
ebra | +0.127 |
clubs | +0.126 |
arrows | +0.125 |
ites | +0.125 |
Neg logit contributions | |
prise | -0.139 |
Katie | -0.126 |
Annie | -0.121 |
Esk | -0.119 |
Jimmy | -0.118 |
Token | replied |
Token ID | 8712 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ebra | +0.349 |
s | +0.324 |
opard | +0.319 |
gers | +0.315 |
ang | +0.315 |
Neg logit contributions | |
prise | -0.359 |
install | -0.339 |
Katie | -0.335 |
Ethan | -0.328 |
Baby | -0.324 |
Token | , |
Token ID | 11 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ebra | +0.052 |
ites | +0.047 |
ang | +0.046 |
gers | +0.045 |
opard | +0.044 |
Neg logit contributions | |
prise | -0.099 |
dessert | -0.096 |
Katie | -0.096 |
Baby | -0.095 |
install | -0.094 |
Token | " |
Token ID | 366 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
ebra | +0.047 |
s | +0.044 |
opard | +0.042 |
ang | +0.039 |
gers | +0.039 |
Neg logit contributions | |
prise | -0.119 |
install | -0.113 |
Katie | -0.110 |
Ethan | -0.108 |
Esk | -0.107 |
Token | I |
Token ID | 40 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
ebra | +0.030 |
gers | +0.027 |
ang | +0.027 |
opard | +0.027 |
s | +0.027 |
Neg logit contributions | |
prise | -0.024 |
install | -0.023 |
Katie | -0.022 |
Baby | -0.022 |
Ethan | -0.022 |
Token | have |
Token ID | 423 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
prise | +0.048 |
dining | +0.047 |
Katie | +0.047 |
install | +0.046 |
Ethan | +0.045 |
Neg logit contributions | |
s | -0.054 |
ebra | -0.050 |
opard | -0.048 |
ite | -0.048 |
ang | -0.047 |
Token | ummy |
Token ID | 13513 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ebra | +0.006 |
s | +0.005 |
ang | +0.005 |
opard | +0.005 |
gers | +0.005 |
Neg logit contributions | |
prise | -0.012 |
install | -0.012 |
Katie | -0.012 |
Ethan | -0.012 |
Esk | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
prise | +0.149 |
install | +0.141 |
Esk | +0.139 |
perfection | +0.137 |
dining | +0.135 |
Neg logit contributions | |
ebra | -0.039 |
s | -0.038 |
opard | -0.029 |
ted | -0.029 |
gers | -0.027 |
Token | Daddy |
Token ID | 26926 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
s | +0.002 |
ebra | +0.002 |
ted | +0.002 |
legs | +0.002 |
gers | +0.002 |
Neg logit contributions | |
prise | -0.003 |
install | -0.003 |
agna | -0.002 |
igor | -0.002 |
Esk | -0.002 |
Token | took |
Token ID | 1718 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
prise | +0.216 |
install | +0.199 |
Esk | +0.198 |
perfection | +0.197 |
dining | +0.195 |
Neg logit contributions | |
s | -0.122 |
ebra | -0.111 |
ted | -0.104 |
ite | -0.098 |
ites | -0.096 |
Token | Lil |
Token ID | 16342 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
prise | +0.020 |
install | +0.019 |
Acc | +0.019 |
dining | +0.019 |
Esk | +0.018 |
Neg logit contributions | |
s | -0.021 |
ted | -0.020 |
gers | -0.020 |
ebra | -0.019 |
arrows | -0.019 |
Token | ah |
Token ID | 993 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
ebra | +0.045 |
gers | +0.040 |
opard | +0.040 |
ang | +0.040 |
legs | +0.040 |
Neg logit contributions | |
prise | -0.061 |
install | -0.059 |
Katie | -0.059 |
Ethan | -0.058 |
Baby | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ebra | +0.298 |
opard | +0.269 |
gers | +0.261 |
ang | +0.259 |
ites | +0.246 |
Neg logit contributions | |
prise | -0.412 |
install | -0.385 |
Katie | -0.380 |
dessert | -0.372 |
dining | -0.369 |
Token | the |
Token ID | 262 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
every | +0.005 |
clubs | +0.004 |
ebra | +0.004 |
tail | +0.004 |
arrows | +0.004 |
Neg logit contributions | |
prise | -0.015 |
Acc | -0.014 |
igor | -0.014 |
agna | -0.014 |
gen | -0.014 |
Token | park |
Token ID | 3952 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
ebra | +0.010 |
opard | +0.009 |
s | +0.009 |
gers | +0.008 |
ite | +0.008 |
Neg logit contributions | |
prise | -0.017 |
install | -0.016 |
Katie | -0.016 |
izz | -0.016 |
Esk | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Katie | +0.022 |
Sus | +0.021 |
Jimmy | +0.021 |
install | +0.021 |
prise | +0.021 |
Neg logit contributions | |
ebra | -0.025 |
opard | -0.023 |
affe | -0.022 |
arrows | -0.022 |
ang | -0.021 |
Token | The |
Token ID | 383 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
ebra | +0.007 |
s | +0.007 |
ang | +0.007 |
gers | +0.007 |
opard | +0.007 |
Neg logit contributions | |
prise | -0.009 |
install | -0.008 |
Katie | -0.008 |
dessert | -0.008 |
dining | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
prise | +0.012 |
install | +0.011 |
Katie | +0.011 |
Ethan | +0.010 |
dining | +0.010 |
Neg logit contributions | |
ebra | -0.006 |
s | -0.006 |
opard | -0.006 |
legs | -0.005 |
gers | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
ebra | +0.002 |
opard | +0.002 |
gers | +0.002 |
ang | +0.002 |
ites | +0.002 |
Neg logit contributions | |
prise | -0.002 |
install | -0.002 |
Ethan | -0.002 |
Baby | -0.002 |
Katie | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
ebra | +0.021 |
ang | +0.019 |
ites | +0.018 |
gers | +0.018 |
opard | +0.017 |
Neg logit contributions | |
prise | -0.042 |
Katie | -0.040 |
dessert | -0.040 |
Baby | -0.040 |
Ethan | -0.040 |
Token | A |
Token ID | 32 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ebra | +0.043 |
s | +0.041 |
opard | +0.040 |
ang | +0.040 |
gers | +0.039 |
Neg logit contributions | |
prise | -0.050 |
install | -0.047 |
Katie | -0.047 |
dining | -0.045 |
Ethan | -0.045 |
Token | aa |
Token ID | 7252 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
prise | +0.010 |
install | +0.010 |
Katie | +0.010 |
Ethan | +0.010 |
Baby | +0.010 |
Neg logit contributions | |
ebra | -0.004 |
s | -0.004 |
opard | -0.004 |
gers | -0.004 |
ang | -0.004 |
Token | ah |
Token ID | 993 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
ites | +0.119 |
ebra | +0.116 |
gers | +0.112 |
pads | +0.112 |
ang | +0.111 |
Neg logit contributions | |
prise | -0.176 |
Baby | -0.165 |
Ethan | -0.164 |
Katie | -0.163 |
Esk | -0.161 |
Token | - |
Token ID | 12 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
ebra | +0.372 |
gers | +0.358 |
ites | +0.356 |
clubs | +0.348 |
s | +0.342 |
Neg logit contributions | |
prise | -0.309 |
install | -0.274 |
Esk | -0.272 |
Katie | -0.272 |
bake | -0.267 |
Token | ch |
Token ID | 354 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
ebra | +0.128 |
gers | +0.118 |
legs | +0.116 |
clubs | +0.116 |
ites | +0.114 |
Neg logit contributions | |
prise | -0.196 |
Ethan | -0.186 |
Katie | -0.185 |
Baby | -0.184 |
install | -0.182 |
Token | oo |
Token ID | 2238 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
ebra | +0.102 |
ites | +0.099 |
gers | +0.099 |
s | +0.098 |
arrows | +0.097 |
Neg logit contributions | |
prise | -0.203 |
Baby | -0.189 |
install | -0.188 |
Katie | -0.187 |
dessert | -0.187 |
Token | !". |
Token ID | 48220 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
ebra | +0.178 |
ites | +0.173 |
ang | +0.170 |
gers | +0.167 |
s | +0.166 |
Neg logit contributions | |
prise | -0.132 |
Baby | -0.126 |
Katie | -0.122 |
Ethan | -0.122 |
Jimmy | -0.120 |
Token | Then |
Token ID | 3244 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
prise | +0.045 |
install | +0.043 |
Katie | +0.043 |
Ethan | +0.042 |
Baby | +0.042 |
Neg logit contributions | |
ebra | -0.030 |
s | -0.027 |
opard | -0.026 |
gers | -0.026 |
ang | -0.026 |
Token | her |
Token ID | 607 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
ebra | +0.033 |
legs | +0.031 |
s | +0.030 |
skills | +0.030 |
every | +0.030 |
Neg logit contributions | |
prise | -0.053 |
install | -0.048 |
Acc | -0.047 |
Esk | -0.046 |
dining | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
prise | +0.022 |
install | +0.021 |
Katie | +0.021 |
Ethan | +0.020 |
Baby | +0.020 |
Neg logit contributions | |
ebra | -0.011 |
s | -0.010 |
opard | -0.009 |
gers | -0.009 |
ang | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
prise | +0.051 |
install | +0.046 |
Esk | +0.046 |
dining | +0.044 |
Acc | +0.044 |
Neg logit contributions | |
s | -0.030 |
legs | -0.030 |
ebra | -0.028 |
gers | -0.027 |
arrows | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
prise | +0.001 |
install | +0.001 |
Katie | +0.001 |
Ethan | +0.001 |
Baby | +0.001 |
Neg logit contributions | |
ebra | -0.000 |
s | -0.000 |
opard | -0.000 |
gers | -0.000 |
ang | -0.000 |
Token | ny |
Token ID | 3281 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ebra | +0.027 |
s | +0.026 |
opard | +0.025 |
ang | +0.025 |
gers | +0.025 |
Neg logit contributions | |
prise | -0.037 |
install | -0.035 |
Katie | -0.034 |
dining | -0.034 |
Esk | -0.034 |
Token | ah |
Token ID | 993 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
ebra | +0.081 |
s | +0.072 |
opard | +0.070 |
gers | +0.069 |
ang | +0.068 |
Neg logit contributions | |
prise | -0.179 |
install | -0.172 |
Katie | -0.171 |
Ethan | -0.168 |
Baby | -0.166 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ebra | +0.288 |
s | +0.258 |
opard | +0.257 |
gers | +0.257 |
ang | +0.255 |
Neg logit contributions | |
prise | -0.405 |
install | -0.384 |
Katie | -0.382 |
Ethan | -0.373 |
Baby | -0.371 |
Token | n |
Token ID | 299 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
ebra | +0.049 |
legs | +0.047 |
arrows | +0.045 |
affe | +0.044 |
s | +0.044 |
Neg logit contributions | |
prise | -0.065 |
dining | -0.061 |
install | -0.061 |
Katie | -0.059 |
Esk | -0.057 |
Token | yah |
Token ID | 46848 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
ebra | +0.030 |
s | +0.027 |
ang | +0.027 |
opard | +0.027 |
gers | +0.026 |
Neg logit contributions | |
prise | -0.044 |
install | -0.042 |
Katie | -0.042 |
Ethan | -0.041 |
Baby | -0.041 |
Token | !" |
Token ID | 2474 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
prise | +0.045 |
install | +0.043 |
Katie | +0.043 |
Ethan | +0.042 |
Baby | +0.042 |
Neg logit contributions | |
ebra | -0.030 |
s | -0.027 |
opard | -0.027 |
gers | -0.027 |
ang | -0.027 |
Token | |
Token ID | 220 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
prise | +0.062 |
Esk | +0.051 |
install | +0.050 |
gen | +0.048 |
erupt | +0.048 |
Neg logit contributions | |
s | -0.041 |
legs | -0.036 |
every | -0.034 |
ted | -0.033 |
ebra | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Katie | +0.001 |
Baby | +0.001 |
Ethan | +0.001 |
prise | +0.001 |
install | +0.001 |
Neg logit contributions | |
ebra | -0.002 |
gers | -0.002 |
opard | -0.001 |
ang | -0.001 |
ites | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
prise | +0.017 |
Katie | +0.016 |
install | +0.016 |
Ethan | +0.016 |
Baby | +0.016 |
Neg logit contributions | |
ebra | -0.016 |
opard | -0.015 |
gers | -0.015 |
s | -0.015 |
ang | -0.014 |
Token | One |
Token ID | 3198 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Ethan | +0.013 |
install | +0.012 |
Er | +0.012 |
prise | +0.012 |
Em | +0.011 |
Neg logit contributions | |
ebra | -0.018 |
legs | -0.017 |
arms | -0.017 |
gers | -0.016 |
ang | -0.016 |
Token | day |
Token ID | 1110 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
ebra | +0.088 |
opard | +0.077 |
s | +0.077 |
ites | +0.076 |
gers | +0.076 |
Neg logit contributions | |
prise | -0.147 |
Katie | -0.140 |
install | -0.140 |
Baby | -0.138 |
dessert | -0.137 |
Token | Din |
Token ID | 23448 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
ebra | +0.098 |
ites | +0.085 |
affe | +0.085 |
gers | +0.083 |
skills | +0.083 |
Neg logit contributions | |
Baby | -0.159 |
Ethan | -0.159 |
Katie | -0.153 |
Em | -0.153 |
Sus | -0.152 |
Token | ah |
Token ID | 993 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
ebra | +0.001 |
s | +0.000 |
gers | +0.000 |
ang | +0.000 |
opard | +0.000 |
Neg logit contributions | |
prise | -0.002 |
install | -0.002 |
Katie | -0.002 |
Ethan | -0.002 |
Esk | -0.002 |
Token | went |
Token ID | 1816 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
ebra | +0.337 |
opard | +0.309 |
s | +0.305 |
gers | +0.304 |
ang | +0.304 |
Neg logit contributions | |
prise | -0.356 |
install | -0.338 |
Katie | -0.335 |
Ethan | -0.326 |
Baby | -0.324 |
Token | for |
Token ID | 329 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
ebra | +0.028 |
opard | +0.027 |
affe | +0.026 |
ang | +0.026 |
ites | +0.025 |
Neg logit contributions | |
prise | -0.029 |
install | -0.028 |
dessert | -0.028 |
Katie | -0.028 |
repair | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
ebra | +0.096 |
gers | +0.091 |
legs | +0.091 |
arrows | +0.090 |
s | +0.086 |
Neg logit contributions | |
prise | -0.121 |
install | -0.116 |
Acc | -0.114 |
Katie | -0.112 |
dining | -0.112 |
Token | long |
Token ID | 890 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
prise | +0.029 |
install | +0.028 |
dining | +0.027 |
Esk | +0.027 |
Katie | +0.027 |
Neg logit contributions | |
s | -0.019 |
ebra | -0.019 |
opard | -0.017 |
gers | -0.017 |
ite | -0.017 |
Token | walk |
Token ID | 2513 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ebra | +0.099 |
opard | +0.096 |
s | +0.094 |
ang | +0.093 |
ites | +0.093 |
Neg logit contributions | |
Katie | -0.067 |
dessert | -0.065 |
Baby | -0.065 |
prise | -0.065 |
Ethan | -0.064 |
Token | snack |
Token ID | 26906 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
prise | +0.037 |
install | +0.036 |
Ethan | +0.035 |
Katie | +0.035 |
Esk | +0.033 |
Neg logit contributions | |
ebra | -0.036 |
gers | -0.033 |
opard | -0.033 |
affe | -0.032 |
s | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ebra | +0.025 |
ang | +0.022 |
opard | +0.022 |
s | +0.021 |
ites | +0.021 |
Neg logit contributions | |
prise | -0.032 |
Katie | -0.031 |
install | -0.031 |
dessert | -0.030 |
Baby | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
Katie | +0.007 |
prise | +0.007 |
Baby | +0.007 |
Ethan | +0.007 |
install | +0.007 |
Neg logit contributions | |
ebra | -0.007 |
gers | -0.007 |
opard | -0.007 |
s | -0.007 |
ang | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
prise | +0.026 |
install | +0.024 |
Katie | +0.024 |
Ethan | +0.023 |
Baby | +0.023 |
Neg logit contributions | |
ebra | -0.028 |
s | -0.026 |
opard | -0.025 |
gers | -0.025 |
ang | -0.025 |
Token | Far |
Token ID | 21428 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
prise | +0.025 |
install | +0.024 |
Ethan | +0.023 |
Katie | +0.023 |
Baby | +0.022 |
Neg logit contributions | |
ebra | -0.026 |
legs | -0.023 |
s | -0.023 |
gers | -0.023 |
opard | -0.023 |
Token | ah |
Token ID | 993 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
prise | +0.133 |
Ethan | +0.132 |
install | +0.130 |
Katie | +0.128 |
Esk | +0.128 |
Neg logit contributions | |
pads | -0.093 |
legs | -0.091 |
ebra | -0.091 |
clubs | -0.090 |
arrows | -0.088 |
Token | and |
Token ID | 290 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
ebra | +0.336 |
gers | +0.315 |
opard | +0.309 |
ites | +0.302 |
ang | +0.299 |
Neg logit contributions | |
prise | -0.342 |
Katie | -0.327 |
install | -0.324 |
Baby | -0.316 |
Ethan | -0.313 |
Token | the |
Token ID | 262 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ebra | +0.028 |
s | +0.027 |
gers | +0.026 |
opard | +0.026 |
ite | +0.026 |
Neg logit contributions | |
Baby | -0.021 |
Katie | -0.021 |
Ethan | -0.021 |
Jimmy | -0.020 |
Annie | -0.020 |
Token | bunny |
Token ID | 44915 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
ebra | +0.010 |
s | +0.009 |
opard | +0.009 |
gers | +0.009 |
ang | +0.009 |
Neg logit contributions | |
prise | -0.018 |
install | -0.017 |
Katie | -0.017 |
Ethan | -0.017 |
Baby | -0.016 |
Token | were |
Token ID | 547 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ebra | +0.027 |
opard | +0.025 |
ang | +0.024 |
gers | +0.024 |
ites | +0.024 |
Neg logit contributions | |
prise | -0.028 |
Baby | -0.027 |
install | -0.027 |
Katie | -0.027 |
Ethan | -0.027 |
Token | best |
Token ID | 1266 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
prise | +0.096 |
install | +0.091 |
Katie | +0.088 |
Ethan | +0.086 |
dining | +0.084 |
Neg logit contributions | |
ebra | -0.087 |
s | -0.081 |
ang | -0.079 |
opard | -0.079 |
gers | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
ebra | +0.038 |
s | +0.036 |
gers | +0.034 |
opard | +0.034 |
ang | +0.033 |
Neg logit contributions | |
prise | -0.063 |
install | -0.060 |
Katie | -0.059 |
Ethan | -0.058 |
Baby | -0.058 |
Token | |
Token ID | 220 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
ebra | +0.005 |
opard | +0.004 |
gers | +0.004 |
ites | +0.004 |
ang | +0.004 |
Neg logit contributions | |
Katie | -0.003 |
Annie | -0.003 |
Baby | -0.003 |
Jessie | -0.003 |
prise | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
s | +0.012 |
ebra | +0.012 |
ang | +0.011 |
opard | +0.011 |
ites | +0.010 |
Neg logit contributions | |
prise | -0.019 |
install | -0.018 |
dessert | -0.018 |
dining | -0.017 |
Esk | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
prise | +0.015 |
Katie | +0.015 |
install | +0.014 |
Ethan | +0.014 |
Baby | +0.014 |
Neg logit contributions | |
ebra | -0.015 |
opard | -0.014 |
gers | -0.014 |
s | -0.013 |
ang | -0.013 |
Token | Le |
Token ID | 3123 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
prise | +0.011 |
Jamie | +0.011 |
Laura | +0.011 |
sure | +0.010 |
Jason | +0.010 |
Neg logit contributions | |
ebra | -0.017 |
clubs | -0.015 |
gers | -0.015 |
opard | -0.014 |
ted | -0.014 |
Token | ah |
Token ID | 993 |
Feature activation | +6.66e+00 |
Pos logit contributions | |
clubs | +0.133 |
gers | +0.131 |
arrows | +0.128 |
ebra | +0.126 |
skills | +0.125 |
Neg logit contributions | |
prise | -0.117 |
Jamie | -0.111 |
Katie | -0.111 |
Jamie | -0.108 |
Annie | -0.107 |
Token | stepped |
Token ID | 10764 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
ebra | +0.355 |
opard | +0.328 |
gers | +0.324 |
s | +0.320 |
ang | +0.319 |
Neg logit contributions | |
prise | -0.331 |
Katie | -0.316 |
install | -0.315 |
Ethan | -0.302 |
Baby | -0.301 |
Token | out |
Token ID | 503 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
prise | +0.018 |
install | +0.017 |
Katie | +0.017 |
Ethan | +0.016 |
Baby | +0.016 |
Neg logit contributions | |
ebra | -0.018 |
opard | -0.016 |
s | -0.016 |
ang | -0.016 |
gers | -0.016 |
Token | of |
Token ID | 286 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
ebra | +0.007 |
opard | +0.007 |
ites | +0.006 |
gers | +0.006 |
ite | +0.006 |
Neg logit contributions | |
Katie | -0.008 |
Annie | -0.008 |
Sus | -0.007 |
prise | -0.007 |
install | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
prise | +0.028 |
install | +0.027 |
Katie | +0.026 |
Ethan | +0.026 |
Esk | +0.026 |
Neg logit contributions | |
ebra | -0.022 |
s | -0.020 |
gers | -0.020 |
legs | -0.020 |
ang | -0.020 |
Token | room |
Token ID | 2119 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
ebra | +0.003 |
s | +0.003 |
gers | +0.003 |
legs | +0.003 |
ite | +0.003 |
Neg logit contributions | |
prise | -0.002 |
Katie | -0.002 |
Ethan | -0.002 |
install | -0.002 |
Baby | -0.002 |
Token | friend |
Token ID | 1545 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
ebra | +0.053 |
ites | +0.048 |
gers | +0.048 |
ang | +0.046 |
s | +0.045 |
Neg logit contributions | |
prise | -0.089 |
dessert | -0.087 |
Katie | -0.086 |
Baby | -0.085 |
install | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
ebra | +0.181 |
ites | +0.163 |
opard | +0.161 |
ang | +0.160 |
gers | +0.156 |
Neg logit contributions | |
Katie | -0.218 |
Jimmy | -0.213 |
prise | -0.211 |
Baby | -0.211 |
Annie | -0.208 |
Token |
|
Token ID | 198 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
ebra | +0.002 |
ig | +0.002 |
ang | +0.002 |
ites | +0.002 |
ite | +0.002 |
Neg logit contributions | |
Katie | -0.001 |
Emma | -0.001 |
Jimmy | -0.001 |
Daddy | -0.001 |
Jessie | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
Katie | +0.014 |
prise | +0.013 |
sure | +0.013 |
Annie | +0.013 |
Jimmy | +0.013 |
Neg logit contributions | |
ebra | -0.029 |
gers | -0.026 |
clubs | -0.026 |
opard | -0.026 |
tails | -0.026 |
Token | Le |
Token ID | 3123 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
Laura | +0.013 |
Jason | +0.013 |
sure | +0.013 |
Kat | +0.013 |
Baby | +0.012 |
Neg logit contributions | |
ebra | -0.024 |
ig | -0.021 |
ite | -0.021 |
arms | -0.021 |
sed | -0.020 |
Token | ah |
Token ID | 993 |
Feature activation | +6.62e+00 |
Pos logit contributions | |
gers | +0.140 |
clubs | +0.139 |
legs | +0.138 |
skills | +0.138 |
ebra | +0.136 |
Neg logit contributions | |
prise | -0.104 |
Katie | -0.096 |
Jason | -0.091 |
Jason | -0.089 |
Jimmy | -0.089 |
Token | took |
Token ID | 1718 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ebra | +0.354 |
gers | +0.322 |
opard | +0.322 |
ang | +0.319 |
ites | +0.314 |
Neg logit contributions | |
prise | -0.329 |
Katie | -0.313 |
install | -0.311 |
Baby | -0.301 |
Ethan | -0.297 |
Token | Polly |
Token ID | 36898 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ebra | +0.014 |
ang | +0.013 |
opard | +0.013 |
ite | +0.013 |
ites | +0.012 |
Neg logit contributions | |
Katie | -0.008 |
Baby | -0.008 |
Jimmy | -0.008 |
Emma | -0.008 |
sure | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
ebra | +0.065 |
s | +0.059 |
opard | +0.058 |
gers | +0.057 |
ang | +0.057 |
Neg logit contributions | |
prise | -0.107 |
install | -0.103 |
Katie | -0.102 |
Ethan | -0.100 |
Baby | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
ebra | +0.021 |
s | +0.020 |
arrows | +0.020 |
legs | +0.019 |
gers | +0.019 |
Neg logit contributions | |
prise | -0.031 |
install | -0.029 |
Ethan | -0.029 |
Esk | -0.029 |
dining | -0.028 |
Token | vet |
Token ID | 20202 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
ebra | +0.018 |
opard | +0.017 |
s | +0.016 |
gers | +0.016 |
legs | +0.015 |
Neg logit contributions | |
prise | -0.025 |
install | -0.024 |
Katie | -0.024 |
Ethan | -0.024 |
Annie | -0.023 |
Token | â |
Token ID | 22940 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
prise | +0.000 |
install | +0.000 |
dining | +0.000 |
dessert | +0.000 |
Esk | +0.000 |
Neg logit contributions | |
ebra | -0.000 |
s | -0.000 |
ang | -0.000 |
ite | -0.000 |
opard | -0.000 |
Token | € |
Token ID | 26391 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
prise | +0.044 |
install | +0.041 |
Katie | +0.040 |
Ethan | +0.039 |
Baby | +0.039 |
Neg logit contributions | |
ebra | -0.075 |
opard | -0.070 |
s | -0.070 |
gers | -0.069 |
ang | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
prise | +0.031 |
Katie | +0.030 |
install | +0.029 |
Ethan | +0.029 |
Baby | +0.029 |
Neg logit contributions | |
ebra | -0.030 |
opard | -0.027 |
gers | -0.027 |
s | -0.027 |
ang | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
prise | +0.035 |
install | +0.033 |
Katie | +0.033 |
Ethan | +0.032 |
dessert | +0.032 |
Neg logit contributions | |
ebra | -0.028 |
s | -0.027 |
ang | -0.026 |
opard | -0.026 |
gers | -0.026 |
Token | Le |
Token ID | 3123 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
prise | +0.031 |
install | +0.029 |
Katie | +0.029 |
Ethan | +0.029 |
Baby | +0.028 |
Neg logit contributions | |
ebra | -0.027 |
s | -0.025 |
opard | -0.025 |
legs | -0.024 |
gers | -0.024 |
Token | ah |
Token ID | 993 |
Feature activation | +6.60e+00 |
Pos logit contributions | |
gers | +0.094 |
ebra | +0.094 |
arrows | +0.093 |
clubs | +0.091 |
opard | +0.088 |
Neg logit contributions | |
prise | -0.173 |
Katie | -0.165 |
Baby | -0.159 |
Annie | -0.158 |
Ethan | -0.157 |
Token | was |
Token ID | 373 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
ebra | +0.339 |
opard | +0.315 |
gers | +0.309 |
ang | +0.304 |
s | +0.304 |
Neg logit contributions | |
prise | -0.333 |
Katie | -0.322 |
install | -0.317 |
Ethan | -0.311 |
Baby | -0.308 |
Token | frustrated |
Token ID | 14718 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
ebra | +0.033 |
ang | +0.032 |
s | +0.031 |
legs | +0.031 |
gers | +0.031 |
Neg logit contributions | |
prise | -0.039 |
install | -0.037 |
dining | -0.034 |
Katie | -0.034 |
Ethan | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ebra | +0.019 |
opard | +0.017 |
ites | +0.016 |
gers | +0.015 |
ang | +0.015 |
Neg logit contributions | |
Katie | -0.028 |
Jimmy | -0.028 |
Ethan | -0.028 |
install | -0.028 |
Baby | -0.028 |
Token | but |
Token ID | 475 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
ebra | +0.019 |
s | +0.018 |
opard | +0.017 |
gers | +0.017 |
ang | +0.017 |
Neg logit contributions | |
prise | -0.025 |
install | -0.024 |
Katie | -0.024 |
Ethan | -0.023 |
Baby | -0.023 |
Token | her |
Token ID | 607 |
Feature activation | -6.39e-03 |
Pos logit contributions | |
ebra | +0.009 |
s | +0.008 |
opard | +0.008 |
gers | +0.008 |
ang | +0.008 |
Neg logit contributions | |
prise | -0.012 |
Katie | -0.011 |
install | -0.011 |
Ethan | -0.011 |
Baby | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
prise | +0.020 |
install | +0.019 |
Katie | +0.019 |
dining | +0.018 |
Esk | +0.018 |
Neg logit contributions | |
s | -0.013 |
ebra | -0.013 |
ang | -0.012 |
opard | -0.012 |
ites | -0.012 |
Token | John |
Token ID | 7554 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
prise | +0.017 |
install | +0.016 |
Katie | +0.016 |
Ethan | +0.015 |
Baby | +0.015 |
Neg logit contributions | |
ebra | -0.015 |
s | -0.014 |
opard | -0.014 |
gers | -0.013 |
ang | -0.013 |
Token | : |
Token ID | 25 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
prise | +0.158 |
Katie | +0.152 |
install | +0.152 |
Baby | +0.149 |
Ethan | +0.148 |
Neg logit contributions | |
ebra | -0.108 |
gers | -0.097 |
opard | -0.097 |
s | -0.094 |
ang | -0.094 |
Token | " |
Token ID | 366 |
Feature activation | -5.73e-02 |
Pos logit contributions | |
prise | +0.159 |
install | +0.151 |
Katie | +0.145 |
dining | +0.144 |
Esk | +0.143 |
Neg logit contributions | |
ebra | -0.079 |
s | -0.072 |
opard | -0.070 |
gers | -0.069 |
ang | -0.067 |
Token | Wo |
Token ID | 49450 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
prise | +0.003 |
dining | +0.003 |
install | +0.003 |
dessert | +0.003 |
Katie | +0.003 |
Neg logit contributions | |
ebra | -0.003 |
opard | -0.002 |
ang | -0.002 |
gers | -0.002 |
s | -0.002 |
Token | ah |
Token ID | 993 |
Feature activation | +6.60e+00 |
Pos logit contributions | |
arrows | +0.010 |
legs | +0.010 |
pads | +0.009 |
gers | +0.009 |
ebra | +0.009 |
Neg logit contributions | |
prise | -0.029 |
install | -0.026 |
Katie | -0.026 |
Sus | -0.025 |
Ethan | -0.025 |
Token | there |
Token ID | 612 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
ebra | +0.272 |
gers | +0.262 |
ites | +0.257 |
s | +0.250 |
arrows | +0.250 |
Neg logit contributions | |
prise | -0.396 |
Katie | -0.364 |
install | -0.363 |
Esk | -0.361 |
Baby | -0.354 |
Token | Max |
Token ID | 5436 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
prise | +0.026 |
install | +0.026 |
perfection | +0.025 |
Ethan | +0.024 |
Acc | +0.024 |
Neg logit contributions | |
s | -0.008 |
ebra | -0.007 |
legs | -0.006 |
opard | -0.006 |
ang | -0.006 |
Token | ! |
Token ID | 0 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
prise | +0.022 |
install | +0.021 |
Katie | +0.020 |
dining | +0.020 |
perfection | +0.020 |
Neg logit contributions | |
ebra | -0.012 |
s | -0.011 |
opard | -0.011 |
ang | -0.010 |
gers | -0.010 |
Token | That |
Token ID | 1320 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ebra | +0.034 |
opard | +0.031 |
s | +0.030 |
affe | +0.030 |
ite | +0.030 |
Neg logit contributions | |
prise | -0.040 |
install | -0.038 |
dining | -0.036 |
dessert | -0.035 |
Katie | -0.035 |
Token | bear |
Token ID | 6842 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
prise | +0.056 |
install | +0.053 |
Katie | +0.053 |
Ethan | +0.052 |
Baby | +0.052 |
Neg logit contributions | |
ebra | -0.049 |
ang | -0.045 |
ites | -0.044 |
opard | -0.044 |
s | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
prise | +0.022 |
install | +0.020 |
Katie | +0.020 |
Ethan | +0.020 |
Baby | +0.019 |
Neg logit contributions | |
ebra | -0.010 |
s | -0.010 |
gers | -0.009 |
opard | -0.009 |
ang | -0.009 |
Token | |
Token ID | 220 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Katie | +0.009 |
Laura | +0.009 |
Jessie | +0.009 |
Annie | +0.009 |
Jamie | +0.008 |
Neg logit contributions | |
ebra | -0.016 |
ang | -0.015 |
ites | -0.015 |
opard | -0.015 |
clubs | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
s | +0.005 |
ebra | +0.005 |
ang | +0.004 |
opard | +0.004 |
gers | +0.004 |
Neg logit contributions | |
prise | -0.008 |
install | -0.007 |
Katie | -0.007 |
Ethan | -0.007 |
dining | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
Katie | +0.016 |
prise | +0.016 |
Annie | +0.016 |
Jimmy | +0.015 |
Ethan | +0.014 |
Neg logit contributions | |
ebra | -0.027 |
opard | -0.026 |
gers | -0.024 |
clubs | -0.024 |
arrows | -0.024 |
Token | Le |
Token ID | 3123 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
Laura | +0.012 |
Jamie | +0.012 |
Laura | +0.011 |
prise | +0.011 |
Jason | +0.010 |
Neg logit contributions | |
clubs | -0.025 |
ebra | -0.025 |
ites | -0.024 |
ang | -0.024 |
opard | -0.024 |
Token | ah |
Token ID | 993 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
clubs | +0.128 |
ebra | +0.127 |
gers | +0.127 |
arrows | +0.126 |
opard | +0.125 |
Neg logit contributions | |
prise | -0.116 |
Katie | -0.108 |
Annie | -0.101 |
Jamie | -0.099 |
Jimmy | -0.099 |
Token | 's |
Token ID | 338 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
ebra | +0.340 |
opard | +0.311 |
s | +0.308 |
gers | +0.308 |
ang | +0.306 |
Neg logit contributions | |
prise | -0.341 |
Katie | -0.323 |
install | -0.322 |
Ethan | -0.311 |
Baby | -0.309 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
prise | +0.035 |
install | +0.033 |
dessert | +0.033 |
Katie | +0.033 |
Baby | +0.032 |
Neg logit contributions | |
ebra | -0.035 |
s | -0.033 |
ang | -0.032 |
ites | -0.032 |
gers | -0.032 |
Token | my |
Token ID | 1820 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
prise | +0.016 |
perfection | +0.015 |
install | +0.015 |
Esk | +0.015 |
agna | +0.014 |
Neg logit contributions | |
s | -0.015 |
ebra | -0.015 |
ite | -0.013 |
ang | -0.013 |
ted | -0.013 |
Token | asked |
Token ID | 1965 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
prise | +0.147 |
perfection | +0.140 |
Esk | +0.137 |
dining | +0.134 |
dessert | +0.134 |
Neg logit contributions | |
s | -0.099 |
ebra | -0.091 |
ted | -0.083 |
ite | -0.079 |
opard | -0.079 |
Token | her |
Token ID | 607 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Katie | +0.117 |
Annie | +0.113 |
prise | +0.112 |
Jimmy | +0.109 |
Baby | +0.109 |
Neg logit contributions | |
ebra | -0.142 |
opard | -0.138 |
ite | -0.137 |
ites | -0.137 |
ang | -0.135 |
Token | fast |
Token ID | 3049 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
s | +0.099 |
gers | +0.092 |
ebra | +0.091 |
ang | +0.091 |
legs | +0.090 |
Neg logit contributions | |
prise | -0.118 |
install | -0.108 |
dining | -0.107 |
agna | -0.103 |
Ethan | -0.101 |
Token | as |
Token ID | 355 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ebra | +0.114 |
opard | +0.106 |
ang | +0.103 |
ites | +0.100 |
s | +0.100 |
Neg logit contributions | |
Ethan | -0.138 |
Katie | -0.136 |
Jimmy | -0.134 |
Baby | -0.134 |
install | -0.133 |
Token | a |
Token ID | 257 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
ebra | +0.074 |
s | +0.067 |
opard | +0.066 |
gers | +0.065 |
ang | +0.065 |
Neg logit contributions | |
prise | -0.116 |
install | -0.111 |
Katie | -0.111 |
Ethan | -0.108 |
Baby | -0.107 |
Token | che |
Token ID | 1125 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
prise | +0.021 |
install | +0.020 |
Katie | +0.020 |
Ethan | +0.020 |
Baby | +0.019 |
Neg logit contributions | |
ebra | -0.018 |
s | -0.016 |
opard | -0.016 |
gers | -0.016 |
ang | -0.016 |
Token | et |
Token ID | 316 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
s | +0.039 |
ites | +0.036 |
ite | +0.035 |
ebra | +0.035 |
gers | +0.035 |
Neg logit contributions | |
prise | -0.032 |
install | -0.031 |
izz | -0.031 |
perfection | -0.031 |
cooked | -0.031 |
Token | ah |
Token ID | 993 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
ebra | +0.177 |
ites | +0.168 |
gers | +0.167 |
opard | +0.164 |
ang | +0.162 |
Neg logit contributions | |
Ethan | -0.223 |
Katie | -0.223 |
install | -0.219 |
Baby | -0.217 |
Jimmy | -0.213 |
Token | ! |
Token ID | 0 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
ebra | +0.314 |
gers | +0.294 |
ites | +0.290 |
opard | +0.289 |
ang | +0.279 |
Neg logit contributions | |
prise | -0.347 |
Katie | -0.337 |
install | -0.331 |
Annie | -0.318 |
Ethan | -0.317 |
Token | Her |
Token ID | 2332 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
ebra | +0.015 |
s | +0.014 |
opard | +0.014 |
gers | +0.014 |
ang | +0.014 |
Neg logit contributions | |
prise | -0.018 |
install | -0.017 |
Katie | -0.017 |
Ethan | -0.017 |
Baby | -0.017 |
Token | life |
Token ID | 1204 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
prise | +0.045 |
Katie | +0.044 |
install | +0.043 |
Baby | +0.042 |
dessert | +0.042 |
Neg logit contributions | |
ebra | -0.046 |
s | -0.043 |
ang | -0.043 |
gers | -0.042 |
ites | -0.041 |
Token | was |
Token ID | 373 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Katie | +0.039 |
prise | +0.038 |
install | +0.038 |
Ethan | +0.037 |
Baby | +0.037 |
Neg logit contributions | |
ebra | -0.041 |
opard | -0.037 |
ang | -0.037 |
s | -0.035 |
ites | -0.035 |
Token | now |
Token ID | 783 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
ebra | +0.011 |
s | +0.010 |
gers | +0.010 |
opard | +0.010 |
ang | +0.010 |
Neg logit contributions | |
prise | -0.010 |
install | -0.010 |
Katie | -0.009 |
Ethan | -0.009 |
dining | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
prise | +0.031 |
install | +0.029 |
dining | +0.028 |
Esk | +0.027 |
Katie | +0.027 |
Neg logit contributions | |
ebra | -0.022 |
legs | -0.020 |
s | -0.020 |
arrows | -0.019 |
opard | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
prise | +0.024 |
install | +0.023 |
Katie | +0.023 |
Ethan | +0.022 |
Baby | +0.022 |
Neg logit contributions | |
ebra | -0.013 |
s | -0.012 |
opard | -0.012 |
ang | -0.012 |
gers | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
prise | +0.026 |
install | +0.024 |
Esk | +0.023 |
dessert | +0.023 |
dining | +0.022 |
Neg logit contributions | |
ebra | -0.014 |
s | -0.013 |
ang | -0.013 |
opard | -0.013 |
legs | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
prise | +0.038 |
install | +0.036 |
Katie | +0.035 |
dessert | +0.035 |
dining | +0.035 |
Neg logit contributions | |
ebra | -0.025 |
s | -0.024 |
ang | -0.023 |
opard | -0.023 |
gers | -0.022 |
Token | Far |
Token ID | 21428 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
prise | +0.034 |
install | +0.032 |
Katie | +0.032 |
Ethan | +0.031 |
Baby | +0.031 |
Neg logit contributions | |
ebra | -0.024 |
s | -0.022 |
opard | -0.022 |
gers | -0.021 |
ang | -0.021 |
Token | ah |
Token ID | 993 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
prise | +0.165 |
Katie | +0.160 |
install | +0.160 |
Ethan | +0.159 |
Baby | +0.155 |
Neg logit contributions | |
ebra | -0.104 |
legs | -0.094 |
opard | -0.093 |
s | -0.093 |
pads | -0.092 |
Token | and |
Token ID | 290 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ebra | +0.332 |
gers | +0.306 |
opard | +0.305 |
ites | +0.299 |
s | +0.299 |
Neg logit contributions | |
prise | -0.337 |
install | -0.323 |
Katie | -0.322 |
Ethan | -0.312 |
Baby | -0.311 |
Token | the |
Token ID | 262 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
ebra | +0.011 |
s | +0.010 |
opard | +0.010 |
gers | +0.010 |
ang | +0.009 |
Neg logit contributions | |
prise | -0.011 |
Katie | -0.011 |
install | -0.011 |
Ethan | -0.011 |
Baby | -0.011 |
Token | bunny |
Token ID | 44915 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
ebra | +0.020 |
opard | +0.018 |
legs | +0.018 |
gers | +0.018 |
s | +0.018 |
Neg logit contributions | |
prise | -0.031 |
install | -0.029 |
Katie | -0.029 |
Ethan | -0.028 |
Baby | -0.028 |
Token | became |
Token ID | 2627 |
Feature activation | +5.50e-03 |
Pos logit contributions | |
ebra | +0.034 |
opard | +0.031 |
ang | +0.030 |
gers | +0.029 |
ites | +0.029 |
Neg logit contributions | |
prise | -0.035 |
install | -0.035 |
Baby | -0.035 |
Katie | -0.035 |
Ethan | -0.034 |
Token | good |
Token ID | 922 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ebra | +0.000 |
s | +0.000 |
opard | +0.000 |
ang | +0.000 |
gers | +0.000 |
Neg logit contributions | |
prise | -0.000 |
install | -0.000 |
Katie | -0.000 |
Ethan | -0.000 |
Baby | -0.000 |
Token | He |
Token ID | 679 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
prise | +0.032 |
install | +0.028 |
Katie | +0.027 |
dining | +0.027 |
dessert | +0.027 |
Neg logit contributions | |
s | -0.011 |
legs | -0.011 |
ebra | -0.011 |
gers | -0.010 |
opard | -0.010 |
Token | said |
Token ID | 531 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
prise | +0.002 |
install | +0.001 |
Katie | +0.001 |
Ethan | +0.001 |
dining | +0.001 |
Neg logit contributions | |
ebra | -0.001 |
s | -0.001 |
gers | -0.001 |
opard | -0.001 |
ang | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ebra | +0.018 |
ang | +0.016 |
opard | +0.015 |
ites | +0.015 |
gers | +0.015 |
Neg logit contributions | |
prise | -0.041 |
Katie | -0.040 |
Baby | -0.039 |
Ethan | -0.039 |
install | -0.039 |
Token | " |
Token ID | 366 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
ebra | +0.039 |
s | +0.036 |
opard | +0.035 |
gers | +0.033 |
ang | +0.033 |
Neg logit contributions | |
prise | -0.091 |
install | -0.086 |
Katie | -0.084 |
Ethan | -0.083 |
Esk | -0.082 |
Token | Wo |
Token ID | 49450 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
ebra | +0.015 |
s | +0.014 |
opard | +0.014 |
ang | +0.014 |
gers | +0.014 |
Neg logit contributions | |
prise | -0.017 |
install | -0.016 |
Katie | -0.016 |
dining | -0.016 |
dessert | -0.015 |
Token | ah |
Token ID | 993 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
ebra | +0.008 |
s | +0.007 |
ang | +0.007 |
opard | +0.007 |
gers | +0.006 |
Neg logit contributions | |
prise | -0.019 |
install | -0.019 |
Katie | -0.019 |
Ethan | -0.019 |
Baby | -0.018 |
Token | ! |
Token ID | 0 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
ebra | +0.259 |
s | +0.234 |
opard | +0.231 |
gers | +0.230 |
ang | +0.227 |
Neg logit contributions | |
prise | -0.418 |
install | -0.397 |
Katie | -0.394 |
Ethan | -0.386 |
Baby | -0.384 |
Token | What |
Token ID | 1867 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ebra | +0.046 |
opard | +0.042 |
ite | +0.042 |
ang | +0.041 |
s | +0.041 |
Neg logit contributions | |
prise | -0.055 |
install | -0.052 |
dining | -0.050 |
Katie | -0.049 |
dessert | -0.048 |
Token | should |
Token ID | 815 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
prise | +0.100 |
install | +0.098 |
Katie | +0.096 |
Ethan | +0.096 |
dining | +0.096 |
Neg logit contributions | |
s | -0.071 |
ebra | -0.065 |
arrows | -0.064 |
legs | -0.063 |
gers | -0.063 |
Token | I |
Token ID | 314 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
prise | +0.040 |
install | +0.037 |
dining | +0.036 |
Katie | +0.035 |
plug | +0.034 |
Neg logit contributions | |
ebra | -0.030 |
s | -0.029 |
legs | -0.028 |
gers | -0.027 |
ite | -0.027 |
Token | do |
Token ID | 466 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
Katie | +0.058 |
prise | +0.058 |
dining | +0.056 |
Acc | +0.055 |
Annie | +0.055 |
Neg logit contributions | |
s | -0.037 |
ebra | -0.036 |
ite | -0.035 |
legs | -0.034 |
gers | -0.033 |
Token | then |
Token ID | 788 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ebra | +0.015 |
s | +0.014 |
opard | +0.013 |
gers | +0.013 |
ang | +0.013 |
Neg logit contributions | |
prise | -0.021 |
install | -0.020 |
Katie | -0.019 |
Esk | -0.019 |
dining | -0.019 |
Token | he |
Token ID | 339 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
ebra | +0.019 |
s | +0.018 |
gers | +0.017 |
opard | +0.017 |
ang | +0.017 |
Neg logit contributions | |
prise | -0.033 |
install | -0.032 |
Esk | -0.030 |
Katie | -0.030 |
dining | -0.030 |
Token | realized |
Token ID | 6939 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ebra | +0.017 |
s | +0.016 |
opard | +0.016 |
gers | +0.016 |
ang | +0.016 |
Neg logit contributions | |
prise | -0.019 |
install | -0.018 |
Katie | -0.017 |
Ethan | -0.017 |
Baby | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
ebra | +0.005 |
s | +0.004 |
gers | +0.004 |
opard | +0.004 |
ang | +0.004 |
Neg logit contributions | |
prise | -0.008 |
install | -0.007 |
Katie | -0.007 |
dining | -0.007 |
Ethan | -0.007 |
Token | Far |
Token ID | 6755 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
prise | +0.048 |
install | +0.045 |
dining | +0.043 |
Katie | +0.043 |
Ethan | +0.042 |
Neg logit contributions | |
ebra | -0.029 |
s | -0.029 |
legs | -0.028 |
arrows | -0.028 |
gers | -0.027 |
Token | ah |
Token ID | 993 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
prise | +0.089 |
install | +0.085 |
Katie | +0.083 |
Ethan | +0.082 |
Baby | +0.081 |
Neg logit contributions | |
ebra | -0.074 |
s | -0.068 |
opard | -0.067 |
gers | -0.066 |
ang | -0.066 |
Token | was |
Token ID | 373 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
ebra | +0.319 |
gers | +0.291 |
opard | +0.289 |
ang | +0.285 |
ites | +0.283 |
Neg logit contributions | |
prise | -0.353 |
install | -0.332 |
Katie | -0.330 |
Ethan | -0.319 |
Baby | -0.318 |
Token | friendly |
Token ID | 8030 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
legs | +0.027 |
ebra | +0.026 |
arrows | +0.026 |
gers | +0.026 |
tail | +0.026 |
Neg logit contributions | |
prise | -0.038 |
install | -0.035 |
Katie | -0.034 |
Ethan | -0.033 |
dining | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
ebra | +0.039 |
ang | +0.035 |
opard | +0.034 |
ites | +0.033 |
s | +0.032 |
Neg logit contributions | |
Katie | -0.084 |
prise | -0.084 |
Jimmy | -0.082 |
Baby | -0.082 |
Annie | -0.082 |
Token | He |
Token ID | 679 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
prise | +0.016 |
install | +0.015 |
dessert | +0.014 |
dining | +0.014 |
Esk | +0.014 |
Neg logit contributions | |
ebra | -0.008 |
s | -0.007 |
ang | -0.007 |
opard | -0.007 |
affe | -0.007 |
Token | hopped |
Token ID | 45230 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
prise | +0.003 |
install | +0.003 |
Katie | +0.003 |
Ethan | +0.003 |
Baby | +0.003 |
Neg logit contributions | |
ebra | -0.003 |
opard | -0.003 |
s | -0.003 |
ang | -0.003 |
gers | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
prise | +0.076 |
Katie | +0.073 |
install | +0.073 |
Ethan | +0.072 |
Baby | +0.072 |
Neg logit contributions | |
ebra | -0.028 |
opard | -0.024 |
s | -0.024 |
ang | -0.023 |
gers | -0.023 |
Token | Emma |
Token ID | 18966 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
s | +0.060 |
every | +0.057 |
gers | +0.056 |
legs | +0.056 |
ebra | +0.055 |
Neg logit contributions | |
prise | -0.024 |
Esk | -0.021 |
install | -0.019 |
Acc | -0.017 |
erupt | -0.016 |
Token | decided |
Token ID | 3066 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
prise | +0.185 |
install | +0.173 |
Katie | +0.168 |
Esk | +0.168 |
Ethan | +0.166 |
Neg logit contributions | |
ebra | -0.136 |
s | -0.132 |
gers | -0.122 |
opard | -0.122 |
ang | -0.121 |
Token | a |
Token ID | 257 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
prise | +0.019 |
install | +0.018 |
Katie | +0.018 |
Esk | +0.018 |
Ethan | +0.018 |
Neg logit contributions | |
ebra | -0.007 |
s | -0.007 |
gers | -0.006 |
opard | -0.006 |
ang | -0.006 |
Token | pony |
Token ID | 26902 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
prise | +0.019 |
Esk | +0.018 |
install | +0.018 |
Ethan | +0.018 |
izz | +0.017 |
Neg logit contributions | |
s | -0.015 |
ebra | -0.014 |
legs | -0.014 |
opard | -0.014 |
gers | -0.013 |
Token | tail |
Token ID | 13199 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
ebra | +0.146 |
ang | +0.132 |
opard | +0.131 |
s | +0.131 |
ites | +0.130 |
Neg logit contributions | |
prise | -0.178 |
install | -0.170 |
Katie | -0.169 |
Ethan | -0.163 |
Baby | -0.161 |
Token | wasn |
Token ID | 2492 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
ebra | +0.345 |
ang | +0.320 |
opard | +0.312 |
ites | +0.310 |
s | +0.307 |
Neg logit contributions | |
prise | -0.337 |
Katie | -0.320 |
install | -0.315 |
dessert | -0.301 |
Ethan | -0.296 |
Token | 't |
Token ID | 470 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
prise | +0.012 |
install | +0.011 |
dining | +0.011 |
Katie | +0.011 |
Esk | +0.011 |
Neg logit contributions | |
s | -0.006 |
ebra | -0.006 |
ang | -0.006 |
ite | -0.006 |
opard | -0.006 |
Token | so |
Token ID | 523 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
legs | +0.011 |
s | +0.010 |
tail | +0.010 |
ang | +0.010 |
pads | +0.010 |
Neg logit contributions | |
prise | -0.015 |
Acc | -0.015 |
install | -0.015 |
dining | -0.014 |
agna | -0.014 |
Token | important |
Token ID | 1593 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
prise | +0.094 |
install | +0.089 |
dining | +0.087 |
Esk | +0.084 |
Ethan | +0.084 |
Neg logit contributions | |
s | -0.078 |
ebra | -0.075 |
gers | -0.074 |
ang | -0.073 |
legs | -0.073 |
Token | after |
Token ID | 706 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Katie | +0.006 |
Ethan | +0.006 |
Jimmy | +0.006 |
dessert | +0.006 |
prise | +0.006 |
Neg logit contributions | |
ebra | -0.005 |
opard | -0.005 |
ite | -0.004 |
ites | -0.004 |
ang | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
ebra | +0.020 |
s | +0.019 |
opard | +0.019 |
ang | +0.019 |
gers | +0.019 |
Neg logit contributions | |
prise | -0.022 |
install | -0.022 |
Katie | -0.020 |
Ethan | -0.020 |
dining | -0.020 |
Token | girl |
Token ID | 2576 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
prise | +0.046 |
install | +0.043 |
Katie | +0.042 |
Ethan | +0.041 |
dining | +0.040 |
Neg logit contributions | |
ebra | -0.046 |
opard | -0.043 |
s | -0.043 |
ang | -0.042 |
gers | -0.041 |
Token | named |
Token ID | 3706 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ebra | +0.039 |
gers | +0.037 |
opard | +0.036 |
arrows | +0.035 |
ites | +0.035 |
Neg logit contributions | |
prise | -0.041 |
Katie | -0.038 |
Baby | -0.038 |
install | -0.038 |
Annie | -0.037 |
Token | Reb |
Token ID | 15652 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
ebra | +0.111 |
s | +0.111 |
opard | +0.106 |
ang | +0.105 |
legs | +0.104 |
Neg logit contributions | |
prise | -0.101 |
install | -0.098 |
Ethan | -0.095 |
Esk | -0.094 |
Nathan | -0.091 |
Token | ek |
Token ID | 988 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
prise | +0.024 |
install | +0.023 |
Katie | +0.023 |
Baby | +0.023 |
Ethan | +0.023 |
Neg logit contributions | |
ebra | -0.027 |
opard | -0.024 |
s | -0.024 |
ang | -0.024 |
gers | -0.024 |
Token | ah |
Token ID | 993 |
Feature activation | +6.51e+00 |
Pos logit contributions | |
ebra | +0.058 |
ites | +0.056 |
gers | +0.056 |
legs | +0.054 |
arrows | +0.054 |
Neg logit contributions | |
prise | -0.084 |
Katie | -0.081 |
Ethan | -0.080 |
Baby | -0.080 |
install | -0.079 |
Token | who |
Token ID | 508 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
ebra | +0.283 |
gers | +0.269 |
ites | +0.258 |
arrows | +0.254 |
opard | +0.254 |
Neg logit contributions | |
prise | -0.376 |
Katie | -0.357 |
install | -0.351 |
Ethan | -0.345 |
Baby | -0.343 |
Token | was |
Token ID | 373 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
prise | +0.130 |
Katie | +0.124 |
install | +0.124 |
Ethan | +0.119 |
Baby | +0.119 |
Neg logit contributions | |
ebra | -0.093 |
s | -0.087 |
opard | -0.086 |
gers | -0.085 |
ang | -0.083 |
Token | very |
Token ID | 845 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
ang | +0.020 |
ebra | +0.020 |
opard | +0.019 |
legs | +0.019 |
s | +0.017 |
Neg logit contributions | |
prise | -0.037 |
install | -0.035 |
Katie | -0.033 |
perfection | -0.032 |
dining | -0.032 |
Token | eager |
Token ID | 11069 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
prise | +0.053 |
install | +0.051 |
Katie | +0.050 |
dining | +0.048 |
Ethan | +0.048 |
Neg logit contributions | |
ebra | -0.045 |
ang | -0.044 |
opard | -0.043 |
s | -0.043 |
gers | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
ebra | +0.004 |
ang | +0.003 |
opard | +0.003 |
ites | +0.003 |
gers | +0.003 |
Neg logit contributions | |
prise | -0.006 |
Katie | -0.006 |
dessert | -0.006 |
install | -0.006 |
Baby | -0.006 |
Token | 's |
Token ID | 338 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
prise | +0.081 |
Katie | +0.076 |
dining | +0.075 |
install | +0.075 |
Ethan | +0.075 |
Neg logit contributions | |
s | -0.048 |
ebra | -0.042 |
opard | -0.039 |
legs | -0.039 |
ite | -0.038 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
prise | +0.008 |
dining | +0.008 |
Katie | +0.008 |
install | +0.008 |
Annie | +0.007 |
Neg logit contributions | |
tail | -0.008 |
legs | -0.008 |
every | -0.008 |
arrows | -0.008 |
pads | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
prise | +0.233 |
install | +0.229 |
dining | +0.222 |
Ethan | +0.221 |
Katie | +0.221 |
Neg logit contributions | |
s | -0.046 |
ebra | -0.041 |
legs | -0.036 |
opard | -0.031 |
gers | -0.030 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
legs | +0.024 |
ebra | +0.024 |
s | +0.023 |
arrows | +0.022 |
affe | +0.022 |
Neg logit contributions | |
prise | -0.028 |
install | -0.026 |
dining | -0.025 |
Ethan | -0.023 |
plug | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
prise | +0.079 |
install | +0.076 |
Katie | +0.075 |
Ethan | +0.074 |
Baby | +0.073 |
Neg logit contributions | |
ebra | -0.044 |
s | -0.040 |
opard | -0.039 |
gers | -0.038 |
ang | -0.038 |
Token | Acc |
Token ID | 6366 |
Feature activation | -7.50e+00 |
Pos logit contributions | |
prise | +0.023 |
install | +0.021 |
Katie | +0.021 |
Ethan | +0.021 |
Baby | +0.020 |
Neg logit contributions | |
ebra | -0.023 |
s | -0.021 |
opard | -0.021 |
ang | -0.021 |
gers | -0.021 |
Token | idents |
Token ID | 3231 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
prise | +0.289 |
install | +0.271 |
Katie | +0.268 |
Ethan | +0.261 |
Baby | +0.257 |
Neg logit contributions | |
ebra | -0.484 |
opard | -0.451 |
s | -0.450 |
gers | -0.449 |
ang | -0.447 |
Token | happen |
Token ID | 1645 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
prise | +0.042 |
Katie | +0.038 |
Baby | +0.036 |
dining | +0.036 |
Ethan | +0.035 |
Neg logit contributions | |
s | -0.078 |
ebra | -0.074 |
gers | -0.072 |
opard | -0.071 |
ite | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
prise | +0.250 |
Katie | +0.240 |
install | +0.240 |
Baby | +0.235 |
Ethan | +0.234 |
Neg logit contributions | |
ebra | -0.188 |
ang | -0.167 |
opard | -0.167 |
ites | -0.162 |
ite | -0.161 |
Token | Let |
Token ID | 3914 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
prise | +0.014 |
install | +0.014 |
Katie | +0.014 |
Ethan | +0.013 |
Baby | +0.013 |
Neg logit contributions | |
ebra | -0.015 |
s | -0.014 |
opard | -0.013 |
gers | -0.013 |
ang | -0.013 |
Token | 's |
Token ID | 338 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
prise | +0.088 |
install | +0.083 |
Katie | +0.081 |
Esk | +0.081 |
dining | +0.080 |
Neg logit contributions | |
s | -0.060 |
ebra | -0.059 |
gers | -0.054 |
opard | -0.052 |
ites | -0.052 |
Token | are |
Token ID | 389 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Katie | +0.056 |
prise | +0.055 |
install | +0.054 |
dining | +0.052 |
Annie | +0.052 |
Neg logit contributions | |
s | -0.048 |
ebra | -0.047 |
gers | -0.044 |
ite | -0.044 |
opard | -0.043 |
Token | proud |
Token ID | 6613 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
install | +0.075 |
prise | +0.074 |
shave | +0.069 |
Ethan | +0.068 |
Katie | +0.068 |
Neg logit contributions | |
ebra | -0.040 |
tail | -0.039 |
ang | -0.039 |
legs | -0.038 |
friends | -0.037 |
Token | of |
Token ID | 286 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
prise | +0.007 |
install | +0.007 |
Katie | +0.007 |
Ethan | +0.007 |
Baby | +0.007 |
Neg logit contributions | |
ebra | -0.003 |
s | -0.002 |
opard | -0.002 |
gers | -0.002 |
ang | -0.002 |
Token | you |
Token ID | 345 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
install | +0.026 |
prise | +0.025 |
Katie | +0.024 |
Ethan | +0.023 |
dining | +0.023 |
Neg logit contributions | |
ebra | -0.028 |
s | -0.026 |
ang | -0.025 |
ites | -0.025 |
opard | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +8.67e-03 |
Pos logit contributions | |
prise | +0.042 |
Katie | +0.039 |
install | +0.039 |
Ethan | +0.038 |
Baby | +0.038 |
Neg logit contributions | |
ebra | -0.042 |
opard | -0.038 |
ang | -0.038 |
s | -0.038 |
gers | -0.038 |
Token | Acc |
Token ID | 6366 |
Feature activation | -7.36e+00 |
Pos logit contributions | |
ebra | +0.000 |
opard | +0.000 |
s | +0.000 |
ang | +0.000 |
ite | +0.000 |
Neg logit contributions | |
prise | -0.000 |
install | -0.000 |
Katie | -0.000 |
dining | -0.000 |
dessert | -0.000 |
Token | idents |
Token ID | 3231 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
prise | +0.301 |
install | +0.280 |
Katie | +0.277 |
Ethan | +0.269 |
Baby | +0.265 |
Neg logit contributions | |
ebra | -0.463 |
s | -0.435 |
opard | -0.432 |
gers | -0.428 |
ang | -0.427 |
Token | happen |
Token ID | 1645 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
prise | +0.044 |
Katie | +0.039 |
install | +0.039 |
Baby | +0.039 |
dining | +0.037 |
Neg logit contributions | |
s | -0.078 |
ebra | -0.073 |
gers | -0.072 |
opard | -0.070 |
affe | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
prise | +0.234 |
Katie | +0.222 |
install | +0.221 |
Ethan | +0.216 |
Baby | +0.215 |
Neg logit contributions | |
ebra | -0.196 |
opard | -0.177 |
ang | -0.176 |
s | -0.174 |
gers | -0.172 |
Token | We |
Token ID | 775 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
prise | +0.003 |
install | +0.003 |
Katie | +0.003 |
dessert | +0.003 |
dining | +0.003 |
Neg logit contributions | |
ebra | -0.003 |
s | -0.003 |
opard | -0.003 |
ang | -0.003 |
gers | -0.003 |
Token | can |
Token ID | 460 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
Katie | +0.062 |
prise | +0.061 |
install | +0.059 |
Annie | +0.058 |
dining | +0.058 |
Neg logit contributions | |
s | -0.052 |
ebra | -0.051 |
gers | -0.048 |
ite | -0.048 |
opard | -0.047 |
Token | 's |
Token ID | 338 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
prise | +0.090 |
dining | +0.084 |
Ethan | +0.084 |
Katie | +0.084 |
install | +0.083 |
Neg logit contributions | |
s | -0.050 |
ebra | -0.042 |
legs | -0.040 |
opard | -0.039 |
arrows | -0.038 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
dining | +0.013 |
prise | +0.013 |
install | +0.013 |
Nathan | +0.013 |
Katie | +0.013 |
Neg logit contributions | |
tail | -0.012 |
legs | -0.011 |
every | -0.011 |
arrows | -0.011 |
wings | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
prise | +0.226 |
install | +0.221 |
Ethan | +0.215 |
Katie | +0.214 |
dining | +0.214 |
Neg logit contributions | |
s | -0.057 |
ebra | -0.054 |
legs | -0.046 |
opard | -0.043 |
gers | -0.042 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ebra | +0.028 |
legs | +0.027 |
s | +0.027 |
arrows | +0.025 |
opard | +0.025 |
Neg logit contributions | |
prise | -0.028 |
install | -0.026 |
dining | -0.025 |
Ethan | -0.024 |
Katie | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
prise | +0.083 |
install | +0.079 |
Katie | +0.078 |
Ethan | +0.077 |
Baby | +0.076 |
Neg logit contributions | |
ebra | -0.042 |
s | -0.040 |
opard | -0.038 |
gers | -0.037 |
ang | -0.037 |
Token | Acc |
Token ID | 6366 |
Feature activation | -7.28e+00 |
Pos logit contributions | |
prise | +0.021 |
install | +0.019 |
Katie | +0.019 |
Ethan | +0.019 |
Esk | +0.019 |
Neg logit contributions | |
ebra | -0.020 |
s | -0.018 |
opard | -0.018 |
ang | -0.018 |
ite | -0.018 |
Token | idents |
Token ID | 3231 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
prise | +0.292 |
install | +0.272 |
Katie | +0.269 |
Ethan | +0.261 |
Baby | +0.257 |
Neg logit contributions | |
ebra | -0.463 |
s | -0.435 |
opard | -0.432 |
gers | -0.428 |
ang | -0.427 |
Token | happen |
Token ID | 1645 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
prise | +0.036 |
Katie | +0.033 |
Baby | +0.031 |
dining | +0.031 |
Son | +0.031 |
Neg logit contributions | |
s | -0.066 |
ebra | -0.062 |
gers | -0.060 |
opard | -0.060 |
skills | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
prise | +0.242 |
Katie | +0.233 |
install | +0.231 |
Baby | +0.226 |
Ethan | +0.226 |
Neg logit contributions | |
ebra | -0.190 |
ang | -0.169 |
opard | -0.169 |
ites | -0.165 |
gers | -0.163 |
Token | It |
Token ID | 632 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
prise | +0.006 |
install | +0.005 |
Katie | +0.005 |
Ethan | +0.005 |
Baby | +0.005 |
Neg logit contributions | |
ebra | -0.006 |
s | -0.006 |
opard | -0.005 |
gers | -0.005 |
ang | -0.005 |
Token | 's |
Token ID | 338 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
prise | +0.012 |
Katie | +0.012 |
Ethan | +0.011 |
dining | +0.011 |
install | +0.011 |
Neg logit contributions | |
s | -0.008 |
ebra | -0.007 |
opard | -0.006 |
ite | -0.006 |
ites | -0.006 |
Token | 's |
Token ID | 338 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
prise | +0.052 |
install | +0.050 |
Katie | +0.049 |
Ethan | +0.048 |
Baby | +0.048 |
Neg logit contributions | |
ebra | -0.041 |
s | -0.038 |
opard | -0.037 |
gers | -0.036 |
ang | -0.036 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
prise | +0.005 |
install | +0.005 |
dining | +0.005 |
Katie | +0.005 |
Ethan | +0.004 |
Neg logit contributions | |
tail | -0.006 |
legs | -0.006 |
pads | -0.006 |
ebra | -0.006 |
tails | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
prise | +0.188 |
install | +0.184 |
Katie | +0.180 |
Ethan | +0.179 |
dining | +0.176 |
Neg logit contributions | |
ebra | -0.063 |
s | -0.061 |
opard | -0.053 |
gers | -0.052 |
legs | -0.051 |
Token | Lily |
Token ID | 20037 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
ebra | +0.031 |
s | +0.029 |
opard | +0.028 |
legs | +0.028 |
affe | +0.028 |
Neg logit contributions | |
prise | -0.030 |
install | -0.029 |
Ethan | -0.027 |
dining | -0.027 |
Katie | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
prise | +0.064 |
install | +0.061 |
Katie | +0.061 |
Ethan | +0.060 |
Baby | +0.059 |
Neg logit contributions | |
ebra | -0.037 |
s | -0.033 |
opard | -0.033 |
gers | -0.032 |
ang | -0.032 |
Token | Acc |
Token ID | 6366 |
Feature activation | -7.28e+00 |
Pos logit contributions | |
prise | +0.009 |
install | +0.008 |
Katie | +0.008 |
Ethan | +0.008 |
Baby | +0.008 |
Neg logit contributions | |
ebra | -0.009 |
s | -0.009 |
opard | -0.009 |
gers | -0.008 |
ang | -0.008 |
Token | idents |
Token ID | 3231 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
prise | +0.233 |
install | +0.225 |
Katie | +0.223 |
Ethan | +0.218 |
Acc | +0.217 |
Neg logit contributions | |
ebra | -0.497 |
gers | -0.463 |
opard | -0.462 |
ang | -0.460 |
ites | -0.457 |
Token | happen |
Token ID | 1645 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
prise | +0.031 |
Katie | +0.028 |
install | +0.027 |
Baby | +0.027 |
Ethan | +0.026 |
Neg logit contributions | |
s | -0.065 |
ebra | -0.063 |
gers | -0.061 |
opard | -0.060 |
ang | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
prise | +0.229 |
Katie | +0.221 |
install | +0.218 |
Esk | +0.216 |
Baby | +0.214 |
Neg logit contributions | |
ebra | -0.185 |
ang | -0.165 |
opard | -0.165 |
ites | -0.162 |
ite | -0.160 |
Token | I |
Token ID | 314 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ebra | +0.002 |
s | +0.002 |
opard | +0.002 |
gers | +0.002 |
ang | +0.002 |
Neg logit contributions | |
prise | -0.002 |
install | -0.002 |
Katie | -0.002 |
Baby | -0.002 |
Ethan | -0.002 |
Token | 'm |
Token ID | 1101 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
prise | +0.072 |
Katie | +0.069 |
install | +0.067 |
Ethan | +0.067 |
Baby | +0.066 |
Neg logit contributions | |
ebra | -0.080 |
s | -0.079 |
opard | -0.076 |
ang | -0.074 |
gers | -0.074 |
Token | 't |
Token ID | 470 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ebra | +0.006 |
opard | +0.006 |
ang | +0.005 |
s | +0.005 |
gers | +0.005 |
Neg logit contributions | |
prise | -0.007 |
Katie | -0.006 |
install | -0.006 |
Ethan | -0.006 |
Baby | -0.006 |
Token | cry |
Token ID | 3960 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
s | +0.103 |
legs | +0.102 |
ebra | +0.101 |
ite | +0.097 |
arrows | +0.096 |
Neg logit contributions | |
dining | -0.089 |
prise | -0.088 |
agna | -0.082 |
Katie | -0.082 |
install | -0.082 |
Token | , |
Token ID | 11 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ebra | +0.011 |
s | +0.010 |
opard | +0.009 |
gers | +0.009 |
ang | +0.009 |
Neg logit contributions | |
prise | -0.035 |
install | -0.034 |
Katie | -0.033 |
Ethan | -0.033 |
dining | -0.032 |
Token | boys |
Token ID | 6510 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
ebra | +0.054 |
s | +0.051 |
legs | +0.051 |
arrows | +0.051 |
affe | +0.050 |
Neg logit contributions | |
prise | -0.063 |
install | -0.060 |
dining | -0.059 |
Katie | -0.056 |
Ethan | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
prise | +0.012 |
install | +0.011 |
Katie | +0.011 |
dining | +0.011 |
perfection | +0.011 |
Neg logit contributions | |
s | -0.004 |
ebra | -0.004 |
gers | -0.003 |
opard | -0.003 |
ang | -0.003 |
Token | Acc |
Token ID | 6366 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
ebra | +0.008 |
s | +0.008 |
opard | +0.008 |
ang | +0.007 |
ite | +0.007 |
Neg logit contributions | |
prise | -0.009 |
install | -0.009 |
Katie | -0.009 |
dining | -0.008 |
Ethan | -0.008 |
Token | idents |
Token ID | 3231 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
prise | +0.256 |
install | +0.244 |
Katie | +0.240 |
Ethan | +0.237 |
Baby | +0.227 |
Neg logit contributions | |
ebra | -0.484 |
opard | -0.452 |
ang | -0.450 |
gers | -0.448 |
ites | -0.444 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
prise | +0.035 |
Katie | +0.031 |
Baby | +0.030 |
install | +0.030 |
dining | +0.030 |
Neg logit contributions | |
s | -0.061 |
ebra | -0.057 |
gers | -0.055 |
opard | -0.054 |
skills | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
prise | +0.265 |
install | +0.254 |
Katie | +0.251 |
Ethan | +0.247 |
Baby | +0.245 |
Neg logit contributions | |
ebra | -0.149 |
s | -0.136 |
opard | -0.132 |
gers | -0.131 |
ang | -0.129 |
Token | I |
Token ID | 314 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
prise | +0.012 |
install | +0.011 |
Katie | +0.011 |
Ethan | +0.011 |
dining | +0.011 |
Neg logit contributions | |
ebra | -0.010 |
s | -0.009 |
opard | -0.009 |
ang | -0.009 |
ite | -0.009 |
Token | have |
Token ID | 423 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
Katie | +0.079 |
prise | +0.079 |
Ethan | +0.075 |
dining | +0.075 |
Annie | +0.074 |
Neg logit contributions | |
s | -0.081 |
ebra | -0.073 |
opard | -0.072 |
ite | -0.070 |
ang | -0.069 |
Token | 's |
Token ID | 338 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
prise | +0.074 |
Katie | +0.071 |
install | +0.070 |
dining | +0.070 |
Ethan | +0.070 |
Neg logit contributions | |
s | -0.043 |
ebra | -0.038 |
opard | -0.036 |
legs | -0.035 |
affe | -0.034 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
prise | +0.005 |
install | +0.005 |
dining | +0.005 |
Katie | +0.005 |
Ethan | +0.005 |
Neg logit contributions | |
legs | -0.007 |
ebra | -0.007 |
tail | -0.007 |
arrows | -0.007 |
opard | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
install | +0.186 |
prise | +0.182 |
dining | +0.179 |
perfection | +0.175 |
izz | +0.172 |
Neg logit contributions | |
s | -0.067 |
ebra | -0.060 |
legs | -0.059 |
affe | -0.057 |
- | -0.054 |
Token | Sammy |
Token ID | 44067 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
ebra | +0.025 |
legs | +0.024 |
arrows | +0.024 |
affe | +0.023 |
s | +0.023 |
Neg logit contributions | |
prise | -0.031 |
install | -0.029 |
dining | -0.029 |
Katie | -0.027 |
izz | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
prise | +0.023 |
install | +0.022 |
perfection | +0.021 |
dining | +0.021 |
Katie | +0.021 |
Neg logit contributions | |
s | -0.016 |
ebra | -0.015 |
affe | -0.014 |
opard | -0.014 |
legs | -0.013 |
Token | Acc |
Token ID | 6366 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
prise | +0.021 |
install | +0.019 |
Katie | +0.019 |
dining | +0.018 |
dessert | +0.018 |
Neg logit contributions | |
ebra | -0.019 |
s | -0.018 |
opard | -0.018 |
ang | -0.017 |
ite | -0.017 |
Token | idents |
Token ID | 3231 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
prise | +0.269 |
install | +0.256 |
Katie | +0.254 |
Ethan | +0.247 |
Baby | +0.242 |
Neg logit contributions | |
ebra | -0.466 |
opard | -0.434 |
gers | -0.433 |
ang | -0.432 |
s | -0.431 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
prise | +0.030 |
Katie | +0.028 |
dining | +0.028 |
Baby | +0.027 |
Son | +0.027 |
Neg logit contributions | |
s | -0.046 |
gers | -0.041 |
affe | -0.041 |
ebra | -0.041 |
skills | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
prise | +0.212 |
install | +0.201 |
Katie | +0.192 |
dining | +0.190 |
Ethan | +0.190 |
Neg logit contributions | |
s | -0.193 |
ebra | -0.183 |
gers | -0.178 |
opard | -0.172 |
legs | -0.168 |
Token | Let |
Token ID | 3914 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
prise | +0.005 |
install | +0.005 |
Katie | +0.005 |
Ethan | +0.004 |
dining | +0.004 |
Neg logit contributions | |
ebra | -0.005 |
s | -0.005 |
opard | -0.005 |
ang | -0.005 |
gers | -0.005 |
Token | 's |
Token ID | 338 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
prise | +0.082 |
install | +0.078 |
dining | +0.076 |
Katie | +0.076 |
Esk | +0.076 |
Neg logit contributions | |
s | -0.054 |
ebra | -0.051 |
gers | -0.047 |
ite | -0.046 |
ites | -0.046 |
Token | 's |
Token ID | 338 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
prise | +0.087 |
install | +0.083 |
Ethan | +0.083 |
dining | +0.082 |
Katie | +0.082 |
Neg logit contributions | |
s | -0.046 |
ebra | -0.037 |
legs | -0.036 |
opard | -0.035 |
ite | -0.032 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
install | +0.011 |
prise | +0.010 |
Ethan | +0.010 |
dining | +0.010 |
Nathan | +0.010 |
Neg logit contributions | |
tail | -0.012 |
legs | -0.011 |
pads | -0.011 |
tails | -0.011 |
wings | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
install | +0.223 |
prise | +0.221 |
Ethan | +0.215 |
Esk | +0.211 |
dining | +0.210 |
Neg logit contributions | |
s | -0.047 |
ebra | -0.044 |
legs | -0.035 |
gers | -0.033 |
opard | -0.033 |
Token | Anna |
Token ID | 11735 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
ebra | +0.037 |
legs | +0.036 |
s | +0.035 |
affe | +0.033 |
opard | +0.033 |
Neg logit contributions | |
prise | -0.035 |
install | -0.034 |
Ethan | -0.031 |
Esk | -0.031 |
plug | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
prise | +0.061 |
install | +0.059 |
Katie | +0.057 |
Ethan | +0.057 |
dining | +0.056 |
Neg logit contributions | |
ebra | -0.027 |
s | -0.026 |
opard | -0.024 |
gers | -0.023 |
ang | -0.023 |
Token | Acc |
Token ID | 6366 |
Feature activation | -7.14e+00 |
Pos logit contributions | |
prise | +0.012 |
install | +0.011 |
Ethan | +0.011 |
Esk | +0.011 |
Katie | +0.011 |
Neg logit contributions | |
ebra | -0.011 |
s | -0.010 |
opard | -0.010 |
ite | -0.010 |
ang | -0.010 |
Token | idents |
Token ID | 3231 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
prise | +0.294 |
install | +0.273 |
Katie | +0.269 |
Ethan | +0.260 |
Baby | +0.257 |
Neg logit contributions | |
ebra | -0.449 |
s | -0.425 |
opard | -0.419 |
gers | -0.415 |
ang | -0.414 |
Token | happen |
Token ID | 1645 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
prise | +0.031 |
Katie | +0.028 |
Baby | +0.027 |
Son | +0.027 |
install | +0.027 |
Neg logit contributions | |
s | -0.053 |
ebra | -0.048 |
gers | -0.048 |
opard | -0.047 |
skills | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
prise | +0.253 |
install | +0.242 |
Katie | +0.240 |
Ethan | +0.235 |
Baby | +0.233 |
Neg logit contributions | |
ebra | -0.169 |
s | -0.154 |
opard | -0.152 |
gers | -0.150 |
ang | -0.149 |
Token | You |
Token ID | 921 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
ebra | +0.005 |
s | +0.005 |
opard | +0.005 |
gers | +0.005 |
ang | +0.005 |
Neg logit contributions | |
prise | -0.005 |
install | -0.005 |
Katie | -0.005 |
Ethan | -0.005 |
Baby | -0.004 |
Token | don |
Token ID | 836 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
s | +0.005 |
ite | +0.004 |
wings | +0.004 |
arrows | +0.004 |
ites | +0.004 |
Neg logit contributions | |
dining | -0.008 |
Katie | -0.008 |
prise | -0.008 |
Ethan | -0.007 |
las | -0.007 |
Token | is |
Token ID | 318 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
prise | +0.367 |
Katie | +0.350 |
install | +0.344 |
Ethan | +0.342 |
Esk | +0.341 |
Neg logit contributions | |
s | -0.172 |
ebra | -0.165 |
gers | -0.147 |
ite | -0.144 |
opard | -0.143 |
Token | still |
Token ID | 991 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
prise | +0.027 |
Katie | +0.025 |
dining | +0.025 |
Annie | +0.024 |
install | +0.024 |
Neg logit contributions | |
tail | -0.015 |
every | -0.014 |
legs | -0.014 |
arrows | -0.014 |
s | -0.014 |
Token | your |
Token ID | 534 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
tail | +0.014 |
legs | +0.014 |
arrows | +0.014 |
and | +0.013 |
skills | +0.013 |
Neg logit contributions | |
prise | -0.022 |
install | -0.020 |
Katie | -0.019 |
Jamie | -0.019 |
dining | -0.019 |
Token | friend |
Token ID | 1545 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
prise | +0.070 |
Katie | +0.066 |
install | +0.065 |
Ethan | +0.064 |
Esk | +0.063 |
Neg logit contributions | |
ebra | -0.052 |
s | -0.049 |
opard | -0.048 |
gers | -0.047 |
legs | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
ebra | +0.109 |
s | +0.103 |
opard | +0.099 |
gers | +0.097 |
ang | +0.097 |
Neg logit contributions | |
prise | -0.153 |
install | -0.146 |
Katie | -0.144 |
Ethan | -0.141 |
Esk | -0.139 |
Token | Acc |
Token ID | 6366 |
Feature activation | -7.04e+00 |
Pos logit contributions | |
prise | +0.024 |
install | +0.022 |
Katie | +0.022 |
dining | +0.021 |
dessert | +0.021 |
Neg logit contributions | |
ebra | -0.016 |
s | -0.016 |
ang | -0.015 |
opard | -0.015 |
ite | -0.015 |
Token | idents |
Token ID | 3231 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
prise | +0.322 |
install | +0.291 |
Katie | +0.287 |
dining | +0.275 |
Ethan | +0.274 |
Neg logit contributions | |
ebra | -0.420 |
s | -0.407 |
opard | -0.391 |
gers | -0.386 |
ang | -0.385 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
prise | +0.031 |
Katie | +0.029 |
dining | +0.028 |
Baby | +0.027 |
Annie | +0.026 |
Neg logit contributions | |
s | -0.059 |
ebra | -0.055 |
gers | -0.054 |
opard | -0.054 |
affe | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
prise | +0.221 |
install | +0.210 |
Katie | +0.209 |
Ethan | +0.205 |
Baby | +0.203 |
Neg logit contributions | |
ebra | -0.184 |
opard | -0.167 |
s | -0.166 |
ang | -0.165 |
gers | -0.163 |
Token | but |
Token ID | 475 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
ebra | +0.038 |
s | +0.037 |
opard | +0.035 |
gers | +0.035 |
ang | +0.034 |
Neg logit contributions | |
prise | -0.051 |
install | -0.048 |
Katie | -0.047 |
Ethan | -0.046 |
dining | -0.046 |
Token | we |
Token ID | 356 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ebra | +0.024 |
s | +0.024 |
opard | +0.022 |
legs | +0.022 |
arrows | +0.022 |
Neg logit contributions | |
prise | -0.027 |
Katie | -0.026 |
dining | -0.025 |
install | -0.025 |
Ethan | -0.025 |
Token | 's |
Token ID | 338 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
prise | +0.086 |
Katie | +0.080 |
dining | +0.080 |
Ethan | +0.079 |
install | +0.079 |
Neg logit contributions | |
s | -0.053 |
ebra | -0.048 |
opard | -0.044 |
legs | -0.044 |
ite | -0.043 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
prise | +0.011 |
dining | +0.011 |
Katie | +0.011 |
install | +0.010 |
Ethan | +0.010 |
Neg logit contributions | |
legs | -0.013 |
s | -0.013 |
arrows | -0.013 |
tail | -0.013 |
every | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
prise | +0.219 |
install | +0.212 |
Katie | +0.210 |
Ethan | +0.208 |
dining | +0.206 |
Neg logit contributions | |
ebra | -0.061 |
s | -0.056 |
opard | -0.050 |
gers | -0.048 |
ang | -0.047 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ebra | +0.032 |
s | +0.032 |
legs | +0.031 |
arrows | +0.030 |
opard | +0.030 |
Neg logit contributions | |
prise | -0.030 |
install | -0.028 |
dining | -0.027 |
Katie | -0.027 |
Ethan | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
prise | +0.079 |
install | +0.076 |
Katie | +0.075 |
Ethan | +0.074 |
Baby | +0.073 |
Neg logit contributions | |
ebra | -0.043 |
s | -0.040 |
opard | -0.038 |
gers | -0.037 |
ang | -0.037 |
Token | Acc |
Token ID | 6366 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
prise | +0.019 |
install | +0.018 |
Katie | +0.018 |
Ethan | +0.017 |
Baby | +0.017 |
Neg logit contributions | |
ebra | -0.021 |
s | -0.019 |
opard | -0.019 |
ang | -0.019 |
gers | -0.019 |
Token | idents |
Token ID | 3231 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
prise | +0.283 |
install | +0.263 |
Katie | +0.260 |
Ethan | +0.252 |
Baby | +0.248 |
Neg logit contributions | |
ebra | -0.442 |
s | -0.417 |
opard | -0.412 |
gers | -0.409 |
ang | -0.408 |
Token | happen |
Token ID | 1645 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
prise | +0.025 |
Katie | +0.023 |
Baby | +0.022 |
install | +0.021 |
dining | +0.021 |
Neg logit contributions | |
s | -0.056 |
ebra | -0.055 |
opard | -0.053 |
gers | -0.053 |
ang | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
prise | +0.221 |
Katie | +0.212 |
install | +0.210 |
Baby | +0.207 |
Ethan | +0.205 |
Neg logit contributions | |
ebra | -0.194 |
ang | -0.174 |
opard | -0.173 |
ites | -0.169 |
ite | -0.168 |
Token | Let |
Token ID | 3914 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
prise | +0.003 |
install | +0.003 |
Katie | +0.003 |
Baby | +0.003 |
Ethan | +0.003 |
Neg logit contributions | |
ebra | -0.003 |
s | -0.003 |
gers | -0.003 |
opard | -0.003 |
ang | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | -8.41e-03 |
Pos logit contributions | |
prise | +0.084 |
install | +0.080 |
Katie | +0.078 |
Ethan | +0.077 |
Esk | +0.077 |
Neg logit contributions | |
ebra | -0.062 |
s | -0.061 |
gers | -0.056 |
opard | -0.055 |
ites | -0.055 |
Token | 's |
Token ID | 338 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
prise | +0.077 |
Katie | +0.072 |
install | +0.072 |
dining | +0.071 |
Ethan | +0.071 |
Neg logit contributions | |
s | -0.046 |
ebra | -0.042 |
opard | -0.039 |
legs | -0.038 |
ang | -0.037 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
prise | +0.008 |
install | +0.008 |
Katie | +0.008 |
Ethan | +0.008 |
dining | +0.008 |
Neg logit contributions | |
legs | -0.012 |
ebra | -0.012 |
s | -0.012 |
pads | -0.012 |
opard | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
prise | +0.205 |
install | +0.202 |
Ethan | +0.197 |
Katie | +0.197 |
dining | +0.194 |
Neg logit contributions | |
ebra | -0.048 |
s | -0.047 |
opard | -0.038 |
legs | -0.037 |
gers | -0.037 |
Token | Anna |
Token ID | 11735 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
legs | +0.041 |
ebra | +0.039 |
s | +0.039 |
arms | +0.036 |
tail | +0.036 |
Neg logit contributions | |
prise | -0.043 |
install | -0.041 |
Esk | -0.038 |
Ethan | -0.037 |
repair | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
prise | +0.043 |
install | +0.042 |
Katie | +0.041 |
Ethan | +0.040 |
Baby | +0.040 |
Neg logit contributions | |
ebra | -0.026 |
s | -0.023 |
opard | -0.023 |
gers | -0.023 |
ang | -0.023 |
Token | Acc |
Token ID | 6366 |
Feature activation | -6.92e+00 |
Pos logit contributions | |
prise | +0.007 |
install | +0.007 |
Katie | +0.007 |
Ethan | +0.007 |
Esk | +0.007 |
Neg logit contributions | |
ebra | -0.007 |
s | -0.006 |
opard | -0.006 |
ang | -0.006 |
ite | -0.006 |
Token | idents |
Token ID | 3231 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
prise | +0.305 |
install | +0.281 |
Katie | +0.275 |
Ethan | +0.267 |
Baby | +0.262 |
Neg logit contributions | |
ebra | -0.419 |
s | -0.406 |
opard | -0.390 |
gers | -0.386 |
ang | -0.386 |
Token | happen |
Token ID | 1645 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
prise | +0.029 |
Katie | +0.027 |
install | +0.025 |
Baby | +0.025 |
Ethan | +0.025 |
Neg logit contributions | |
s | -0.059 |
ebra | -0.057 |
gers | -0.055 |
opard | -0.055 |
ang | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
prise | +0.250 |
Katie | +0.240 |
install | +0.238 |
Baby | +0.234 |
Annie | +0.232 |
Neg logit contributions | |
ebra | -0.185 |
opard | -0.164 |
ang | -0.163 |
ites | -0.160 |
ite | -0.158 |
Token | I |
Token ID | 314 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ebra | +0.005 |
s | +0.004 |
opard | +0.004 |
gers | +0.004 |
ang | +0.004 |
Neg logit contributions | |
prise | -0.005 |
Katie | -0.005 |
install | -0.004 |
Baby | -0.004 |
Ethan | -0.004 |
Token | 'm |
Token ID | 1101 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
prise | +0.073 |
Katie | +0.072 |
dining | +0.069 |
Ethan | +0.068 |
install | +0.067 |
Neg logit contributions | |
s | -0.092 |
ebra | -0.087 |
opard | -0.085 |
ang | -0.083 |
ite | -0.082 |
Token | of |
Token ID | 286 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ebra | +0.172 |
opard | +0.144 |
ig | +0.141 |
ang | +0.140 |
pads | +0.139 |
Neg logit contributions | |
prise | -0.211 |
Katie | -0.195 |
install | -0.194 |
Santa | -0.188 |
repair | -0.187 |
Token | the |
Token ID | 262 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ebra | +0.006 |
s | +0.006 |
opard | +0.005 |
ang | +0.005 |
gers | +0.005 |
Neg logit contributions | |
prise | -0.007 |
install | -0.006 |
Katie | -0.006 |
Ethan | -0.006 |
Baby | -0.006 |
Token | story |
Token ID | 1621 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
ebra | +0.053 |
s | +0.049 |
gers | +0.048 |
opard | +0.046 |
legs | +0.045 |
Neg logit contributions | |
prise | -0.080 |
install | -0.077 |
Katie | -0.075 |
Ethan | -0.074 |
Baby | -0.073 |
Token | is |
Token ID | 318 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
ebra | +0.045 |
ang | +0.042 |
opard | +0.040 |
pads | +0.040 |
ites | +0.039 |
Neg logit contributions | |
prise | -0.040 |
Katie | -0.037 |
Annie | -0.036 |
dessert | -0.036 |
install | -0.036 |
Token | : |
Token ID | 25 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ebra | +0.004 |
gers | +0.004 |
pads | +0.004 |
ang | +0.003 |
ites | +0.003 |
Neg logit contributions | |
prise | -0.005 |
install | -0.005 |
Katie | -0.005 |
Baby | -0.005 |
Acc | -0.005 |
Token | Acc |
Token ID | 6366 |
Feature activation | -6.88e+00 |
Pos logit contributions | |
prise | +0.068 |
install | +0.065 |
Katie | +0.063 |
Ethan | +0.062 |
Baby | +0.062 |
Neg logit contributions | |
ebra | -0.082 |
gers | -0.076 |
opard | -0.075 |
s | -0.075 |
ang | -0.075 |
Token | idents |
Token ID | 3231 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
prise | +0.262 |
install | +0.249 |
Katie | +0.246 |
Ethan | +0.239 |
Baby | +0.234 |
Neg logit contributions | |
ebra | -0.447 |
opard | -0.417 |
ang | -0.412 |
gers | -0.411 |
s | -0.410 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
prise | +0.018 |
install | +0.016 |
Katie | +0.015 |
Ethan | +0.014 |
Baby | +0.014 |
Neg logit contributions | |
ebra | -0.056 |
s | -0.054 |
opard | -0.053 |
gers | -0.053 |
ang | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
prise | +0.203 |
Katie | +0.200 |
Jimmy | +0.194 |
Annie | +0.194 |
install | +0.193 |
Neg logit contributions | |
ebra | -0.181 |
ang | -0.163 |
opard | -0.161 |
ites | -0.161 |
ite | -0.156 |
Token | but |
Token ID | 475 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
ebra | +0.063 |
opard | +0.056 |
ang | +0.055 |
s | +0.055 |
ites | +0.054 |
Neg logit contributions | |
prise | -0.071 |
Katie | -0.071 |
Baby | -0.068 |
install | -0.068 |
Ethan | -0.068 |
Token | we |
Token ID | 356 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
ebra | +0.051 |
s | +0.048 |
opard | +0.047 |
gers | +0.046 |
ang | +0.046 |
Neg logit contributions | |
prise | -0.050 |
install | -0.047 |
Katie | -0.046 |
Ethan | -0.045 |
Baby | -0.045 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
tail | +0.002 |
every | +0.002 |
legs | +0.002 |
skills | +0.002 |
arrows | +0.002 |
Neg logit contributions | |
prise | -0.002 |
install | -0.002 |
dining | -0.002 |
Ethan | -0.002 |
agna | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
install | +0.185 |
prise | +0.184 |
Ethan | +0.176 |
Esk | +0.174 |
dining | +0.173 |
Neg logit contributions | |
s | -0.058 |
legs | -0.052 |
ebra | -0.052 |
affe | -0.047 |
opard | -0.045 |
Token | sweet |
Token ID | 6029 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
ebra | +0.035 |
s | +0.035 |
legs | +0.035 |
affe | +0.034 |
arrows | +0.033 |
Neg logit contributions | |
prise | -0.033 |
install | -0.031 |
Ethan | -0.030 |
Esk | -0.029 |
dining | -0.029 |
Token | ie |
Token ID | 494 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
prise | +0.118 |
install | +0.114 |
Ethan | +0.110 |
Katie | +0.108 |
Esk | +0.107 |
Neg logit contributions | |
ebra | -0.106 |
s | -0.101 |
opard | -0.097 |
gers | -0.096 |
affe | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
ebra | +0.026 |
s | +0.025 |
opard | +0.024 |
gers | +0.023 |
ang | +0.023 |
Neg logit contributions | |
prise | -0.041 |
install | -0.040 |
Katie | -0.038 |
Ethan | -0.038 |
dining | -0.038 |
Token | Acc |
Token ID | 6366 |
Feature activation | -6.86e+00 |
Pos logit contributions | |
prise | +0.017 |
install | +0.016 |
Katie | +0.015 |
dessert | +0.015 |
dining | +0.015 |
Neg logit contributions | |
ebra | -0.014 |
s | -0.012 |
opard | -0.012 |
ang | -0.012 |
ite | -0.012 |
Token | idents |
Token ID | 3231 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
prise | +0.288 |
install | +0.267 |
Katie | +0.262 |
Ethan | +0.254 |
Baby | +0.250 |
Neg logit contributions | |
ebra | -0.428 |
s | -0.406 |
opard | -0.399 |
gers | -0.395 |
ang | -0.394 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
prise | +0.030 |
dining | +0.027 |
Katie | +0.026 |
install | +0.025 |
Baby | +0.025 |
Neg logit contributions | |
s | -0.048 |
gers | -0.044 |
ebra | -0.044 |
opard | -0.043 |
skills | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
prise | +0.241 |
install | +0.230 |
Katie | +0.221 |
Ethan | +0.220 |
dining | +0.218 |
Neg logit contributions | |
s | -0.152 |
ebra | -0.150 |
gers | -0.141 |
opard | -0.137 |
ang | -0.133 |
Token | Let |
Token ID | 3914 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
prise | +0.002 |
install | +0.002 |
Katie | +0.002 |
Ethan | +0.002 |
dining | +0.002 |
Neg logit contributions | |
ebra | -0.002 |
s | -0.002 |
opard | -0.002 |
ang | -0.002 |
gers | -0.002 |
Token | 's |
Token ID | 338 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
prise | +0.095 |
install | +0.092 |
Esk | +0.091 |
dining | +0.089 |
Ethan | +0.088 |
Neg logit contributions | |
s | -0.056 |
ebra | -0.048 |
gers | -0.045 |
affe | -0.044 |
ites | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
prise | +0.023 |
install | +0.021 |
Esk | +0.021 |
dining | +0.021 |
Ethan | +0.020 |
Neg logit contributions | |
ebra | -0.015 |
s | -0.014 |
arrows | -0.013 |
gers | -0.013 |
legs | -0.013 |
Token | kind |
Token ID | 1611 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
prise | +0.027 |
install | +0.026 |
Ethan | +0.026 |
Katie | +0.026 |
Jimmy | +0.025 |
Neg logit contributions | |
ebra | -0.011 |
opard | -0.011 |
affe | -0.009 |
arrows | -0.009 |
gers | -0.009 |
Token | lady |
Token ID | 10846 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
prise | +0.080 |
Katie | +0.077 |
install | +0.076 |
Ethan | +0.074 |
Baby | +0.074 |
Neg logit contributions | |
ebra | -0.042 |
s | -0.038 |
opard | -0.037 |
ang | -0.037 |
gers | -0.037 |
Token | behind |
Token ID | 2157 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ebra | +0.016 |
s | +0.016 |
ang | +0.014 |
ite | +0.014 |
opard | +0.014 |
Neg logit contributions | |
prise | -0.034 |
install | -0.033 |
Ethan | -0.033 |
Esk | -0.032 |
Katie | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ebra | +0.008 |
s | +0.007 |
opard | +0.007 |
gers | +0.007 |
ang | +0.007 |
Neg logit contributions | |
prise | -0.012 |
install | -0.012 |
Katie | -0.012 |
Ethan | -0.011 |
Baby | -0.011 |
Token | counter |
Token ID | 3753 |
Feature activation | -6.82e+00 |
Pos logit contributions | |
prise | +0.097 |
install | +0.093 |
Ethan | +0.093 |
Katie | +0.093 |
Nathan | +0.092 |
Neg logit contributions | |
opard | -0.038 |
ebra | -0.038 |
s | -0.035 |
affe | -0.035 |
legs | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
prise | +0.465 |
install | +0.443 |
Katie | +0.438 |
Ethan | +0.435 |
Baby | +0.430 |
Neg logit contributions | |
ebra | -0.240 |
s | -0.226 |
opard | -0.213 |
gers | -0.210 |
ang | -0.208 |
Token | |
Token ID | 220 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
prise | +0.012 |
install | +0.011 |
Esk | +0.011 |
dining | +0.011 |
dessert | +0.011 |
Neg logit contributions | |
s | -0.007 |
ebra | -0.006 |
opard | -0.006 |
ang | -0.006 |
ite | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
s | +0.005 |
ebra | +0.004 |
ang | +0.004 |
ites | +0.004 |
opard | +0.004 |
Neg logit contributions | |
prise | -0.009 |
install | -0.008 |
Esk | -0.008 |
dining | -0.008 |
dessert | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
prise | +0.033 |
install | +0.032 |
Esk | +0.031 |
Katie | +0.031 |
dining | +0.030 |
Neg logit contributions | |
s | -0.021 |
ebra | -0.020 |
ang | -0.019 |
opard | -0.018 |
ites | -0.018 |
Token | As |
Token ID | 1722 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
prise | +0.030 |
install | +0.028 |
Katie | +0.028 |
Ethan | +0.028 |
Baby | +0.027 |
Neg logit contributions | |
ebra | -0.022 |
s | -0.021 |
opard | -0.020 |
gers | -0.020 |
ang | -0.020 |
Token | 's |
Token ID | 338 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
prise | +0.081 |
Katie | +0.076 |
dining | +0.076 |
install | +0.075 |
Ethan | +0.075 |
Neg logit contributions | |
s | -0.051 |
ebra | -0.046 |
opard | -0.042 |
legs | -0.042 |
ite | -0.041 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
prise | +0.008 |
dining | +0.007 |
Katie | +0.007 |
install | +0.007 |
Ethan | +0.007 |
Neg logit contributions | |
legs | -0.010 |
ebra | -0.010 |
s | -0.010 |
arrows | -0.010 |
tail | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
prise | +0.203 |
install | +0.196 |
Katie | +0.195 |
Ethan | +0.192 |
Baby | +0.191 |
Neg logit contributions | |
ebra | -0.068 |
s | -0.058 |
opard | -0.056 |
gers | -0.055 |
ang | -0.055 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ebra | +0.037 |
s | +0.037 |
legs | +0.035 |
arrows | +0.035 |
gers | +0.035 |
Neg logit contributions | |
prise | -0.033 |
install | -0.031 |
Katie | -0.029 |
dining | -0.029 |
Ethan | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
prise | +0.069 |
install | +0.066 |
Katie | +0.065 |
Ethan | +0.064 |
Baby | +0.064 |
Neg logit contributions | |
ebra | -0.039 |
s | -0.035 |
opard | -0.034 |
gers | -0.034 |
ang | -0.034 |
Token | Acc |
Token ID | 6366 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
prise | +0.017 |
install | +0.016 |
Katie | +0.016 |
Ethan | +0.016 |
Baby | +0.015 |
Neg logit contributions | |
ebra | -0.018 |
s | -0.017 |
opard | -0.017 |
gers | -0.017 |
ang | -0.017 |
Token | idents |
Token ID | 3231 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
prise | +0.262 |
install | +0.246 |
Katie | +0.243 |
Ethan | +0.236 |
Baby | +0.232 |
Neg logit contributions | |
ebra | -0.443 |
opard | -0.412 |
s | -0.411 |
gers | -0.409 |
ang | -0.408 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
prise | +0.020 |
Katie | +0.017 |
install | +0.017 |
Baby | +0.016 |
dining | +0.016 |
Neg logit contributions | |
ebra | -0.049 |
s | -0.048 |
opard | -0.046 |
gers | -0.046 |
ang | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
prise | +0.210 |
Katie | +0.204 |
install | +0.201 |
Baby | +0.198 |
Annie | +0.197 |
Neg logit contributions | |
ebra | -0.177 |
ang | -0.158 |
opard | -0.157 |
ites | -0.153 |
ite | -0.152 |
Token | Just |
Token ID | 2329 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
ebra | +0.003 |
gers | +0.002 |
s | +0.002 |
opard | +0.002 |
ang | +0.002 |
Neg logit contributions | |
prise | -0.002 |
install | -0.002 |
Katie | -0.002 |
Baby | -0.002 |
Acc | -0.002 |
Token | remember |
Token ID | 3505 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ebra | +0.030 |
legs | +0.028 |
s | +0.028 |
ig | +0.028 |
ang | +0.027 |
Neg logit contributions | |
prise | -0.030 |
Katie | -0.029 |
dining | -0.029 |
install | -0.028 |
Ethan | -0.028 |
Token | 's |
Token ID | 338 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
prise | +0.083 |
Katie | +0.080 |
dining | +0.079 |
Ethan | +0.078 |
perfection | +0.078 |
Neg logit contributions | |
s | -0.047 |
ebra | -0.041 |
opard | -0.039 |
legs | -0.036 |
affe | -0.036 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
prise | +0.015 |
Katie | +0.015 |
dining | +0.014 |
install | +0.014 |
Annie | +0.014 |
Neg logit contributions | |
ebra | -0.023 |
legs | -0.022 |
opard | -0.022 |
s | -0.022 |
pads | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
prise | +0.207 |
install | +0.206 |
Ethan | +0.200 |
dining | +0.200 |
Katie | +0.199 |
Neg logit contributions | |
s | -0.041 |
ebra | -0.040 |
legs | -0.030 |
opard | -0.030 |
gers | -0.029 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ebra | +0.040 |
s | +0.037 |
opard | +0.036 |
ang | +0.036 |
gers | +0.036 |
Neg logit contributions | |
prise | -0.039 |
install | -0.037 |
Katie | -0.036 |
Ethan | -0.035 |
dining | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
prise | +0.090 |
install | +0.085 |
Katie | +0.084 |
perfection | +0.083 |
dining | +0.083 |
Neg logit contributions | |
s | -0.030 |
ebra | -0.029 |
opard | -0.026 |
gers | -0.025 |
ang | -0.025 |
Token | Acc |
Token ID | 6366 |
Feature activation | -6.76e+00 |
Pos logit contributions | |
ebra | +0.003 |
opard | +0.003 |
s | +0.003 |
ang | +0.003 |
ite | +0.003 |
Neg logit contributions | |
prise | -0.004 |
install | -0.003 |
Katie | -0.003 |
Ethan | -0.003 |
Esk | -0.003 |
Token | idents |
Token ID | 3231 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
prise | +0.269 |
install | +0.251 |
Katie | +0.248 |
Ethan | +0.240 |
Baby | +0.237 |
Neg logit contributions | |
ebra | -0.432 |
s | -0.405 |
opard | -0.403 |
gers | -0.399 |
ang | -0.399 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
prise | +0.024 |
Katie | +0.022 |
Baby | +0.021 |
dining | +0.021 |
Son | +0.021 |
Neg logit contributions | |
s | -0.040 |
gers | -0.037 |
ebra | -0.037 |
opard | -0.036 |
affe | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
prise | +0.268 |
install | +0.258 |
Katie | +0.253 |
Ethan | +0.250 |
Baby | +0.247 |
Neg logit contributions | |
ebra | -0.131 |
s | -0.131 |
gers | -0.120 |
opard | -0.118 |
ang | -0.114 |
Token | I |
Token ID | 314 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ebra | +0.023 |
s | +0.021 |
gers | +0.021 |
opard | +0.021 |
ang | +0.021 |
Neg logit contributions | |
prise | -0.019 |
Katie | -0.018 |
install | -0.018 |
Baby | -0.018 |
Ethan | -0.018 |
Token | 'm |
Token ID | 1101 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
prise | +0.070 |
Katie | +0.069 |
dining | +0.066 |
Ethan | +0.065 |
Annie | +0.064 |
Neg logit contributions | |
s | -0.073 |
ebra | -0.071 |
opard | -0.070 |
ang | -0.067 |
ite | -0.067 |
Token | 's |
Token ID | 338 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
prise | +0.083 |
dining | +0.078 |
Katie | +0.077 |
install | +0.076 |
Ethan | +0.075 |
Neg logit contributions | |
s | -0.048 |
ebra | -0.042 |
legs | -0.040 |
arrows | -0.039 |
opard | -0.038 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
prise | +0.007 |
install | +0.007 |
dining | +0.007 |
Katie | +0.006 |
lad | +0.006 |
Neg logit contributions | |
tail | -0.008 |
legs | -0.007 |
pads | -0.007 |
every | -0.007 |
tails | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
prise | +0.203 |
install | +0.199 |
dining | +0.192 |
Katie | +0.192 |
Ethan | +0.191 |
Neg logit contributions | |
s | -0.059 |
ebra | -0.057 |
legs | -0.048 |
opard | -0.048 |
gers | -0.047 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ebra | +0.037 |
s | +0.035 |
legs | +0.035 |
arrows | +0.034 |
gers | +0.034 |
Neg logit contributions | |
prise | -0.038 |
install | -0.035 |
dining | -0.034 |
Katie | -0.032 |
Ethan | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
prise | +0.077 |
install | +0.073 |
Katie | +0.072 |
Ethan | +0.070 |
dining | +0.070 |
Neg logit contributions | |
ebra | -0.036 |
s | -0.035 |
opard | -0.032 |
gers | -0.031 |
ang | -0.031 |
Token | Acc |
Token ID | 6366 |
Feature activation | -6.72e+00 |
Pos logit contributions | |
prise | +0.017 |
install | +0.016 |
Katie | +0.015 |
Ethan | +0.015 |
dining | +0.015 |
Neg logit contributions | |
ebra | -0.015 |
s | -0.014 |
opard | -0.014 |
ang | -0.014 |
gers | -0.014 |
Token | idents |
Token ID | 3231 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
prise | +0.300 |
install | +0.274 |
Katie | +0.268 |
Ethan | +0.259 |
Baby | +0.258 |
Neg logit contributions | |
ebra | -0.404 |
s | -0.391 |
opard | -0.375 |
gers | -0.372 |
ang | -0.370 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
prise | +0.024 |
Katie | +0.022 |
dining | +0.021 |
Baby | +0.021 |
install | +0.020 |
Neg logit contributions | |
s | -0.045 |
ebra | -0.043 |
gers | -0.042 |
opard | -0.042 |
affe | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
prise | +0.220 |
Katie | +0.210 |
install | +0.210 |
Ethan | +0.205 |
Baby | +0.203 |
Neg logit contributions | |
ebra | -0.170 |
opard | -0.153 |
ang | -0.152 |
s | -0.151 |
gers | -0.149 |
Token | Just |
Token ID | 2329 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
ebra | +0.003 |
s | +0.003 |
opard | +0.003 |
gers | +0.003 |
ang | +0.003 |
Neg logit contributions | |
prise | -0.003 |
install | -0.003 |
Katie | -0.003 |
Ethan | -0.003 |
Baby | -0.003 |
Token | be |
Token ID | 307 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
ebra | +0.029 |
legs | +0.027 |
ig | +0.027 |
s | +0.026 |
ang | +0.026 |
Neg logit contributions | |
prise | -0.032 |
dining | -0.031 |
Katie | -0.030 |
install | -0.029 |
Ethan | -0.028 |
Token | 's |
Token ID | 338 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
prise | +0.079 |
dining | +0.074 |
Ethan | +0.073 |
install | +0.073 |
Esk | +0.073 |
Neg logit contributions | |
s | -0.044 |
ebra | -0.036 |
legs | -0.035 |
arrows | -0.034 |
opard | -0.034 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
prise | +0.003 |
install | +0.003 |
dining | +0.003 |
agna | +0.003 |
Ethan | +0.003 |
Neg logit contributions | |
every | -0.003 |
tail | -0.003 |
legs | -0.003 |
wings | -0.003 |
skills | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
prise | +0.205 |
install | +0.202 |
dining | +0.194 |
Ethan | +0.193 |
Katie | +0.192 |
Neg logit contributions | |
s | -0.049 |
ebra | -0.047 |
legs | -0.040 |
opard | -0.038 |
gers | -0.038 |
Token | Fiona |
Token ID | 42207 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ebra | +0.042 |
s | +0.039 |
opard | +0.038 |
gers | +0.038 |
ang | +0.038 |
Neg logit contributions | |
prise | -0.037 |
install | -0.035 |
Katie | -0.035 |
Ethan | -0.034 |
Baby | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
prise | +0.008 |
install | +0.008 |
Katie | +0.008 |
Ethan | +0.007 |
Baby | +0.007 |
Neg logit contributions | |
ebra | -0.004 |
s | -0.004 |
opard | -0.004 |
gers | -0.004 |
ang | -0.004 |
Token | Acc |
Token ID | 6366 |
Feature activation | -6.68e+00 |
Pos logit contributions | |
prise | +0.015 |
install | +0.014 |
Katie | +0.014 |
dessert | +0.014 |
dining | +0.014 |
Neg logit contributions | |
ebra | -0.013 |
s | -0.012 |
opard | -0.012 |
ang | -0.012 |
ite | -0.012 |
Token | idents |
Token ID | 3231 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
prise | +0.282 |
install | +0.261 |
Katie | +0.257 |
Ethan | +0.249 |
Baby | +0.245 |
Neg logit contributions | |
ebra | -0.415 |
s | -0.393 |
opard | -0.386 |
gers | -0.383 |
ang | -0.382 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
prise | +0.024 |
Katie | +0.020 |
dining | +0.020 |
install | +0.020 |
Baby | +0.019 |
Neg logit contributions | |
s | -0.045 |
ebra | -0.044 |
gers | -0.043 |
opard | -0.042 |
affe | -0.041 |
Token | ." |
Token ID | 526 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
prise | +0.230 |
Katie | +0.220 |
install | +0.219 |
Ethan | +0.214 |
Baby | +0.213 |
Neg logit contributions | |
ebra | -0.160 |
opard | -0.142 |
ang | -0.141 |
s | -0.140 |
gers | -0.138 |
Token | Then |
Token ID | 3244 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
Baby | +0.066 |
prise | +0.066 |
Katie | +0.066 |
Ethan | +0.064 |
Annie | +0.064 |
Neg logit contributions | |
ebra | -0.075 |
opard | -0.067 |
gers | -0.067 |
ites | -0.066 |
ite | -0.065 |
Token | they |
Token ID | 484 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
Baby | +0.043 |
Katie | +0.042 |
Annie | +0.041 |
Ethan | +0.040 |
Jimmy | +0.040 |
Neg logit contributions | |
ebra | -0.036 |
opard | -0.033 |
affe | -0.033 |
ites | -0.031 |
ite | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
prise | +0.057 |
install | +0.055 |
Katie | +0.053 |
Ethan | +0.053 |
dining | +0.052 |
Neg logit contributions | |
ebra | -0.024 |
s | -0.023 |
gers | -0.021 |
opard | -0.021 |
ang | -0.020 |
Token | It |
Token ID | 632 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
ebra | +0.013 |
opard | +0.012 |
s | +0.012 |
ang | +0.012 |
gers | +0.012 |
Neg logit contributions | |
prise | -0.013 |
install | -0.012 |
Katie | -0.012 |
Ethan | -0.012 |
Esk | -0.012 |
Token | 's |
Token ID | 338 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
prise | +0.029 |
Katie | +0.028 |
install | +0.027 |
Ethan | +0.027 |
dining | +0.026 |
Neg logit contributions | |
s | -0.016 |
ebra | -0.015 |
opard | -0.014 |
gers | -0.013 |
ang | -0.013 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
prise | +0.064 |
install | +0.062 |
Katie | +0.061 |
dining | +0.059 |
Ethan | +0.058 |
Neg logit contributions | |
tail | -0.048 |
legs | -0.045 |
pads | -0.045 |
tails | -0.044 |
wings | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
prise | +0.199 |
install | +0.197 |
Ethan | +0.191 |
Katie | +0.191 |
dining | +0.187 |
Neg logit contributions | |
s | -0.090 |
ebra | -0.088 |
gers | -0.078 |
opard | -0.077 |
legs | -0.077 |
Token | Acc |
Token ID | 6366 |
Feature activation | -6.68e+00 |
Pos logit contributions | |
ebra | +0.009 |
s | +0.008 |
opard | +0.008 |
gers | +0.008 |
ang | +0.008 |
Neg logit contributions | |
prise | -0.009 |
install | -0.009 |
Katie | -0.008 |
Ethan | -0.008 |
Esk | -0.008 |
Token | idents |
Token ID | 3231 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
prise | +0.257 |
install | +0.241 |
Katie | +0.238 |
Ethan | +0.232 |
Baby | +0.228 |
Neg logit contributions | |
ebra | -0.433 |
opard | -0.404 |
s | -0.402 |
gers | -0.400 |
ang | -0.400 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
prise | +0.032 |
Katie | +0.029 |
Baby | +0.028 |
dining | +0.028 |
Son | +0.027 |
Neg logit contributions | |
s | -0.056 |
gers | -0.052 |
ebra | -0.052 |
opard | -0.050 |
every | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
prise | +0.262 |
install | +0.252 |
Katie | +0.247 |
Ethan | +0.244 |
Baby | +0.241 |
Neg logit contributions | |
ebra | -0.142 |
s | -0.139 |
gers | -0.130 |
opard | -0.127 |
ang | -0.124 |
Token | Just |
Token ID | 2329 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
ebra | +0.025 |
s | +0.024 |
opard | +0.023 |
gers | +0.023 |
ang | +0.023 |
Neg logit contributions | |
prise | -0.023 |
install | -0.021 |
Katie | -0.021 |
Ethan | -0.021 |
Baby | -0.021 |
Token | be |
Token ID | 307 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
ebra | +0.024 |
legs | +0.023 |
ig | +0.023 |
s | +0.022 |
ang | +0.022 |
Neg logit contributions | |
prise | -0.028 |
Katie | -0.027 |
dining | -0.027 |
install | -0.026 |
Ethan | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +8.65e-02 |
Pos logit contributions | |
prise | +0.036 |
install | +0.034 |
Katie | +0.034 |
Ethan | +0.033 |
Baby | +0.033 |
Neg logit contributions | |
ebra | -0.019 |
s | -0.018 |
opard | -0.017 |
gers | -0.016 |
ang | -0.016 |
Token | It |
Token ID | 632 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ebra | +0.004 |
s | +0.004 |
opard | +0.004 |
ite | +0.004 |
legs | +0.004 |
Neg logit contributions | |
prise | -0.005 |
install | -0.005 |
Katie | -0.004 |
dining | -0.004 |
Esk | -0.004 |
Token | is |
Token ID | 318 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
prise | +0.012 |
Katie | +0.012 |
install | +0.011 |
Ethan | +0.011 |
dining | +0.011 |
Neg logit contributions | |
s | -0.008 |
ebra | -0.008 |
opard | -0.007 |
ite | -0.007 |
ang | -0.007 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
prise | +0.017 |
install | +0.016 |
Katie | +0.015 |
dining | +0.015 |
Ethan | +0.015 |
Neg logit contributions | |
tail | -0.015 |
legs | -0.014 |
pads | -0.014 |
arrows | -0.014 |
tails | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
prise | +0.158 |
install | +0.149 |
Katie | +0.149 |
Baby | +0.146 |
Ethan | +0.146 |
Neg logit contributions | |
ebra | -0.097 |
opard | -0.086 |
s | -0.086 |
ang | -0.085 |
gers | -0.085 |
Token | Acc |
Token ID | 6366 |
Feature activation | -6.68e+00 |
Pos logit contributions | |
ebra | +0.002 |
s | +0.001 |
opard | +0.001 |
gers | +0.001 |
ang | +0.001 |
Neg logit contributions | |
prise | -0.002 |
install | -0.002 |
Katie | -0.002 |
Ethan | -0.002 |
Esk | -0.002 |
Token | idents |
Token ID | 3231 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
prise | +0.258 |
install | +0.243 |
Katie | +0.240 |
Ethan | +0.233 |
Baby | +0.229 |
Neg logit contributions | |
ebra | -0.432 |
opard | -0.402 |
s | -0.401 |
gers | -0.398 |
ang | -0.398 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
prise | +0.026 |
Katie | +0.024 |
dining | +0.023 |
Baby | +0.023 |
Son | +0.022 |
Neg logit contributions | |
s | -0.047 |
ebra | -0.044 |
gers | -0.043 |
opard | -0.043 |
affe | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
prise | +0.234 |
Katie | +0.223 |
install | +0.223 |
Ethan | +0.218 |
Baby | +0.217 |
Neg logit contributions | |
ebra | -0.171 |
opard | -0.153 |
ang | -0.152 |
s | -0.149 |
ites | -0.148 |
Token | Let |
Token ID | 3914 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ebra | +0.014 |
s | +0.013 |
opard | +0.013 |
gers | +0.013 |
ang | +0.013 |
Neg logit contributions | |
prise | -0.013 |
install | -0.012 |
Katie | -0.012 |
Ethan | -0.012 |
Baby | -0.012 |
Token | me |
Token ID | 502 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
prise | +0.077 |
install | +0.073 |
Katie | +0.072 |
Esk | +0.071 |
dining | +0.071 |
Neg logit contributions | |
s | -0.054 |
ebra | -0.054 |
gers | -0.049 |
opard | -0.048 |
ites | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
prise | +0.115 |
install | +0.108 |
Katie | +0.104 |
Ethan | +0.101 |
dining | +0.101 |
Neg logit contributions | |
ebra | -0.103 |
s | -0.102 |
legs | -0.097 |
gers | -0.097 |
opard | -0.096 |
Token | stew |
Token ID | 20798 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
s | +0.033 |
ebra | +0.031 |
opard | +0.030 |
legs | +0.030 |
gers | +0.029 |
Neg logit contributions | |
prise | -0.024 |
Acc | -0.023 |
install | -0.022 |
Katie | -0.022 |
Ethan | -0.022 |
Token | all |
Token ID | 477 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
prise | +0.158 |
install | +0.150 |
Katie | +0.148 |
Ethan | +0.147 |
Esk | +0.144 |
Neg logit contributions | |
ebra | -0.090 |
s | -0.087 |
opard | -0.081 |
gers | -0.080 |
ang | -0.079 |
Token | over |
Token ID | 625 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
s | +0.017 |
ebra | +0.017 |
ang | +0.016 |
ites | +0.016 |
gers | +0.015 |
Neg logit contributions | |
prise | -0.023 |
install | -0.022 |
Katie | -0.021 |
Ethan | -0.021 |
dining | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
prise | +0.062 |
install | +0.059 |
Katie | +0.057 |
Ethan | +0.056 |
dining | +0.056 |
Neg logit contributions | |
ebra | -0.048 |
s | -0.046 |
ang | -0.044 |
gers | -0.044 |
opard | -0.043 |
Token | counter |
Token ID | 3753 |
Feature activation | -6.61e+00 |
Pos logit contributions | |
prise | +0.084 |
Katie | +0.078 |
Jason | +0.076 |
Ethan | +0.076 |
install | +0.076 |
Neg logit contributions | |
legs | -0.039 |
s | -0.037 |
ebra | -0.036 |
opard | -0.035 |
trees | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
prise | +0.452 |
install | +0.430 |
Katie | +0.426 |
Ethan | +0.421 |
Baby | +0.416 |
Neg logit contributions | |
ebra | -0.232 |
s | -0.220 |
opard | -0.207 |
gers | -0.203 |
ang | -0.203 |
Token |
|
Token ID | 198 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
prise | +0.012 |
install | +0.011 |
Esk | +0.011 |
dining | +0.011 |
dessert | +0.011 |
Neg logit contributions | |
s | -0.005 |
legs | -0.005 |
opard | -0.005 |
ebra | -0.005 |
gers | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
prise | +0.035 |
install | +0.033 |
dining | +0.032 |
Esk | +0.032 |
Katie | +0.032 |
Neg logit contributions | |
s | -0.022 |
ebra | -0.021 |
ang | -0.019 |
opard | -0.019 |
gers | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
prise | +0.035 |
Katie | +0.033 |
install | +0.033 |
Ethan | +0.033 |
dessert | +0.033 |
Neg logit contributions | |
ebra | -0.017 |
s | -0.016 |
opard | -0.016 |
gers | -0.016 |
ang | -0.015 |
Token | p |
Token ID | 279 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ebra | +0.047 |
opard | +0.042 |
ang | +0.040 |
legs | +0.040 |
gers | +0.040 |
Neg logit contributions | |
Katie | -0.063 |
prise | -0.061 |
Jason | -0.059 |
install | -0.059 |
Ethan | -0.058 |
Token | prince |
Token ID | 19716 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
prise | +0.010 |
install | +0.010 |
Katie | +0.009 |
Ethan | +0.009 |
Esk | +0.009 |
Neg logit contributions | |
ebra | -0.008 |
s | -0.007 |
opard | -0.007 |
gers | -0.007 |
ang | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ebra | +0.069 |
opard | +0.062 |
s | +0.061 |
ang | +0.060 |
gers | +0.060 |
Neg logit contributions | |
prise | -0.115 |
Katie | -0.110 |
install | -0.109 |
Annie | -0.106 |
dessert | -0.106 |
Token |
|
Token ID | 198 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
ebra | +0.004 |
s | +0.004 |
opard | +0.004 |
ang | +0.004 |
gers | +0.004 |
Neg logit contributions | |
prise | -0.006 |
install | -0.006 |
Katie | -0.006 |
Esk | -0.006 |
Ethan | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
prise | +0.011 |
install | +0.010 |
Katie | +0.010 |
Ethan | +0.010 |
Baby | +0.010 |
Neg logit contributions | |
ebra | -0.008 |
s | -0.008 |
opard | -0.008 |
ang | -0.008 |
gers | -0.008 |
Token | So |
Token ID | 2396 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
prise | +0.012 |
install | +0.011 |
Katie | +0.011 |
Ethan | +0.010 |
Baby | +0.010 |
Neg logit contributions | |
ebra | -0.009 |
s | -0.008 |
opard | -0.008 |
gers | -0.008 |
legs | -0.008 |
Token | one |
Token ID | 530 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
ebra | +0.011 |
opard | +0.010 |
ang | +0.010 |
ites | +0.009 |
gers | +0.009 |
Neg logit contributions | |
Katie | -0.016 |
prise | -0.016 |
Baby | -0.016 |
Annie | -0.016 |
Ethan | -0.015 |
Token | day |
Token ID | 1110 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ebra | +0.143 |
s | +0.127 |
opard | +0.124 |
gers | +0.122 |
ang | +0.121 |
Neg logit contributions | |
prise | -0.316 |
install | -0.305 |
Katie | -0.302 |
Ethan | -0.298 |
Baby | -0.295 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ebra | +0.079 |
s | +0.069 |
opard | +0.067 |
gers | +0.066 |
ang | +0.066 |
Neg logit contributions | |
prise | -0.198 |
install | -0.190 |
Katie | -0.189 |
Ethan | -0.186 |
Baby | -0.185 |
Token | she |
Token ID | 673 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
ebra | +0.048 |
s | +0.045 |
opard | +0.044 |
gers | +0.043 |
ang | +0.043 |
Neg logit contributions | |
prise | -0.071 |
install | -0.068 |
Katie | -0.066 |
Ethan | -0.065 |
Esk | -0.065 |
Token | asked |
Token ID | 1965 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ebra | +0.038 |
s | +0.038 |
gers | +0.036 |
opard | +0.035 |
ang | +0.034 |
Neg logit contributions | |
prise | -0.044 |
install | -0.041 |
Katie | -0.040 |
Ethan | -0.039 |
dessert | -0.039 |
Token | her |
Token ID | 607 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
prise | +0.123 |
install | +0.117 |
Katie | +0.112 |
Ethan | +0.112 |
Esk | +0.111 |
Neg logit contributions | |
ebra | -0.095 |
s | -0.088 |
opard | -0.086 |
gers | -0.085 |
ang | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ebra | +0.047 |
s | +0.041 |
opard | +0.040 |
affe | +0.040 |
ang | +0.040 |
Neg logit contributions | |
prise | -0.057 |
install | -0.056 |
dessert | -0.054 |
Katie | -0.054 |
dining | -0.054 |
Token | The |
Token ID | 383 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ebra | +0.008 |
s | +0.007 |
opard | +0.007 |
gers | +0.007 |
ang | +0.007 |
Neg logit contributions | |
prise | -0.013 |
install | -0.012 |
Katie | -0.012 |
Ethan | -0.012 |
Baby | -0.011 |
Token | duck |
Token ID | 22045 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
ebra | +0.027 |
s | +0.024 |
ang | +0.023 |
opard | +0.023 |
ites | +0.023 |
Neg logit contributions | |
prise | -0.038 |
install | -0.037 |
Baby | -0.036 |
Esk | -0.036 |
dessert | -0.036 |
Token | had |
Token ID | 550 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
ebra | +0.039 |
gers | +0.035 |
opard | +0.035 |
ang | +0.034 |
ites | +0.034 |
Neg logit contributions | |
prise | -0.039 |
install | -0.037 |
Katie | -0.037 |
Baby | -0.036 |
Ethan | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
ebra | +0.046 |
s | +0.042 |
ang | +0.042 |
opard | +0.041 |
gers | +0.041 |
Neg logit contributions | |
prise | -0.038 |
install | -0.036 |
Katie | -0.036 |
Baby | -0.035 |
Esk | -0.035 |
Token | friend |
Token ID | 1545 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
prise | +0.014 |
install | +0.013 |
Baby | +0.013 |
Katie | +0.013 |
dessert | +0.013 |
Neg logit contributions | |
ebra | -0.013 |
s | -0.012 |
ites | -0.012 |
ang | -0.012 |
gers | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ebra | +0.173 |
opard | +0.153 |
gers | +0.151 |
s | +0.151 |
ang | +0.149 |
Neg logit contributions | |
prise | -0.292 |
Katie | -0.278 |
install | -0.277 |
Baby | -0.274 |
Ethan | -0.271 |
Token | a |
Token ID | 257 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
ebra | +0.056 |
opard | +0.055 |
s | +0.054 |
arrows | +0.053 |
legs | +0.052 |
Neg logit contributions | |
prise | -0.079 |
install | -0.074 |
dining | -0.072 |
agna | -0.069 |
Katie | -0.068 |
Token | little |
Token ID | 1310 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
prise | +0.053 |
install | +0.051 |
Katie | +0.051 |
Ethan | +0.050 |
Esk | +0.049 |
Neg logit contributions | |
ebra | -0.031 |
opard | -0.029 |
s | -0.029 |
gers | -0.028 |
ang | -0.028 |
Token | girl |
Token ID | 2576 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
prise | +0.073 |
Baby | +0.070 |
Katie | +0.069 |
install | +0.069 |
dessert | +0.068 |
Neg logit contributions | |
ebra | -0.056 |
ites | -0.049 |
gers | -0.049 |
s | -0.049 |
ang | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ebra | +0.037 |
gers | +0.034 |
opard | +0.033 |
s | +0.033 |
affe | +0.033 |
Neg logit contributions | |
prise | -0.046 |
Katie | -0.043 |
Baby | -0.042 |
install | -0.042 |
Annie | -0.041 |
Token | white |
Token ID | 2330 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Annie | +0.027 |
Ethan | +0.027 |
Katie | +0.027 |
Jimmy | +0.027 |
James | +0.027 |
Neg logit contributions | |
ebra | -0.025 |
opard | -0.022 |
ites | -0.022 |
gers | -0.022 |
ang | -0.022 |
Token | stripes |
Token ID | 28806 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ang | +0.058 |
ites | +0.054 |
opard | +0.054 |
ebra | +0.054 |
ite | +0.053 |
Neg logit contributions | |
dessert | -0.078 |
Ethan | -0.078 |
frost | -0.077 |
candle | -0.076 |
Esk | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
ebra | +0.163 |
opard | +0.147 |
ang | +0.143 |
gers | +0.141 |
ites | +0.138 |
Neg logit contributions | |
install | -0.136 |
Katie | -0.135 |
Jimmy | -0.135 |
Ethan | -0.134 |
dessert | -0.134 |
Token | a |
Token ID | 257 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
Annie | +0.003 |
Ethan | +0.003 |
Katie | +0.003 |
Esk | +0.003 |
prise | +0.003 |
Neg logit contributions | |
ebra | -0.005 |
ang | -0.005 |
opard | -0.005 |
ites | -0.004 |
ite | -0.004 |
Token | long |
Token ID | 890 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
prise | +0.040 |
install | +0.038 |
Ethan | +0.037 |
Katie | +0.037 |
dessert | +0.037 |
Neg logit contributions | |
ebra | -0.031 |
ites | -0.028 |
ang | -0.028 |
gers | -0.028 |
s | -0.027 |
Token | tail |
Token ID | 7894 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
ites | +0.048 |
ang | +0.046 |
s | +0.043 |
ite | +0.043 |
ebra | +0.043 |
Neg logit contributions | |
shave | -0.075 |
Ethan | -0.074 |
dessert | -0.073 |
candle | -0.072 |
Katie | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
ebra | +0.249 |
ites | +0.226 |
ang | +0.225 |
opard | +0.225 |
gers | +0.222 |
Neg logit contributions | |
prise | -0.232 |
install | -0.230 |
Esk | -0.229 |
repair | -0.226 |
bake | -0.222 |
Token | It |
Token ID | 632 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
prise | +0.004 |
install | +0.004 |
Katie | +0.004 |
dining | +0.004 |
Ethan | +0.004 |
Neg logit contributions | |
ebra | -0.003 |
s | -0.003 |
opard | -0.003 |
gers | -0.003 |
ang | -0.003 |
Token | has |
Token ID | 468 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
prise | +0.004 |
install | +0.004 |
Annie | +0.004 |
Ethan | +0.004 |
Esk | +0.004 |
Neg logit contributions | |
ebra | -0.004 |
opard | -0.004 |
ang | -0.004 |
gers | -0.004 |
ites | -0.003 |
Token | wheels |
Token ID | 13666 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ebra | +0.052 |
ang | +0.048 |
opard | +0.048 |
s | +0.048 |
gers | +0.047 |
Neg logit contributions | |
prise | -0.039 |
Katie | -0.038 |
Ethan | -0.037 |
install | -0.037 |
Esk | -0.037 |
Token | on |
Token ID | 319 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ebra | +0.065 |
opard | +0.061 |
gers | +0.059 |
ang | +0.056 |
affe | +0.053 |
Neg logit contributions | |
Ethan | -0.082 |
install | -0.081 |
repair | -0.080 |
Jimmy | -0.079 |
plugged | -0.078 |
Token | that |
Token ID | 326 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Katie | +0.000 |
prise | +0.000 |
Jimmy | +0.000 |
install | +0.000 |
dessert | +0.000 |
Neg logit contributions | |
ebra | -0.000 |
opard | -0.000 |
ang | -0.000 |
ites | -0.000 |
gers | -0.000 |
Token | she |
Token ID | 673 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
prise | +0.082 |
install | +0.078 |
Katie | +0.077 |
Ethan | +0.076 |
Baby | +0.075 |
Neg logit contributions | |
ebra | -0.050 |
s | -0.046 |
opard | -0.044 |
gers | -0.044 |
ang | -0.044 |
Token | could |
Token ID | 714 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
ebra | +0.028 |
s | +0.026 |
opard | +0.025 |
gers | +0.025 |
ang | +0.025 |
Neg logit contributions | |
prise | -0.035 |
install | -0.034 |
Katie | -0.033 |
Baby | -0.033 |
Ethan | -0.033 |
Token | teach |
Token ID | 4545 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
prise | +0.029 |
Katie | +0.026 |
install | +0.026 |
Ethan | +0.026 |
Baby | +0.026 |
Neg logit contributions | |
ebra | -0.038 |
s | -0.036 |
opard | -0.035 |
gers | -0.035 |
ang | -0.035 |
Token | her |
Token ID | 607 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
ebra | +0.092 |
opard | +0.085 |
s | +0.084 |
ang | +0.084 |
gers | +0.083 |
Neg logit contributions | |
prise | -0.093 |
Katie | -0.088 |
install | -0.088 |
Ethan | -0.085 |
Baby | -0.085 |
Token | friend |
Token ID | 1545 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
ebra | +0.047 |
s | +0.043 |
opard | +0.042 |
gers | +0.042 |
ang | +0.042 |
Neg logit contributions | |
prise | -0.056 |
install | -0.053 |
Katie | -0.053 |
Ethan | -0.052 |
Baby | -0.051 |
Token | something |
Token ID | 1223 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ebra | +0.183 |
opard | +0.166 |
s | +0.165 |
ang | +0.164 |
gers | +0.163 |
Neg logit contributions | |
prise | -0.225 |
Katie | -0.215 |
install | -0.215 |
Ethan | -0.208 |
Baby | -0.207 |
Token | unique |
Token ID | 3748 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
prise | +0.116 |
install | +0.110 |
Katie | +0.107 |
Ethan | +0.106 |
Esk | +0.106 |
Neg logit contributions | |
ebra | -0.085 |
s | -0.084 |
gers | -0.078 |
opard | -0.077 |
ang | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
ebra | +0.056 |
opard | +0.051 |
ang | +0.051 |
ites | +0.049 |
gers | +0.047 |
Neg logit contributions | |
prise | -0.062 |
Katie | -0.061 |
install | -0.060 |
Annie | -0.059 |
Jimmy | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
prise | +0.011 |
Katie | +0.011 |
install | +0.011 |
Ethan | +0.011 |
Baby | +0.011 |
Neg logit contributions | |
ebra | -0.010 |
opard | -0.009 |
s | -0.009 |
gers | -0.009 |
ang | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
prise | +0.026 |
install | +0.025 |
Katie | +0.024 |
Ethan | +0.024 |
Esk | +0.024 |
Neg logit contributions | |
ebra | -0.024 |
s | -0.023 |
opard | -0.022 |
ang | -0.022 |
gers | -0.022 |
Token | something |
Token ID | 1223 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ebra | +0.032 |
opard | +0.029 |
s | +0.029 |
ang | +0.029 |
gers | +0.029 |
Neg logit contributions | |
prise | -0.026 |
install | -0.025 |
Katie | -0.025 |
Ethan | -0.024 |
Baby | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
prise | +0.086 |
install | +0.081 |
Katie | +0.080 |
Ethan | +0.079 |
Baby | +0.078 |
Neg logit contributions | |
ebra | -0.077 |
s | -0.074 |
gers | -0.071 |
opard | -0.071 |
ang | -0.070 |
Token | She |
Token ID | 1375 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
prise | +0.003 |
install | +0.003 |
Katie | +0.003 |
Ethan | +0.003 |
Baby | +0.003 |
Neg logit contributions | |
ebra | -0.003 |
s | -0.002 |
opard | -0.002 |
gers | -0.002 |
ang | -0.002 |
Token | boldly |
Token ID | 42831 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
ebra | +0.009 |
opard | +0.008 |
gers | +0.008 |
ites | +0.008 |
s | +0.008 |
Neg logit contributions | |
prise | -0.008 |
install | -0.007 |
Katie | -0.007 |
Baby | -0.007 |
Ethan | -0.007 |
Token | stepped |
Token ID | 10764 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
ebra | +0.004 |
opard | +0.004 |
s | +0.004 |
gers | +0.004 |
ang | +0.004 |
Neg logit contributions | |
prise | -0.004 |
install | -0.004 |
Katie | -0.004 |
Ethan | -0.004 |
Baby | -0.004 |
Token | forward |
Token ID | 2651 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
prise | +0.031 |
Katie | +0.029 |
install | +0.029 |
Baby | +0.029 |
Ethan | +0.028 |
Neg logit contributions | |
ebra | -0.035 |
opard | -0.033 |
affe | -0.032 |
s | -0.031 |
ites | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
ebra | +0.125 |
opard | +0.108 |
gers | +0.105 |
ites | +0.103 |
ang | +0.103 |
Neg logit contributions | |
prise | -0.305 |
Katie | -0.301 |
install | -0.300 |
Annie | -0.292 |
Ethan | -0.292 |
Token | said |
Token ID | 531 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
prise | +0.023 |
install | +0.022 |
Katie | +0.021 |
Ethan | +0.021 |
Esk | +0.021 |
Neg logit contributions | |
ebra | -0.021 |
s | -0.020 |
gers | -0.019 |
ang | -0.019 |
opard | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
ebra | +0.007 |
ang | +0.006 |
ites | +0.006 |
ite | +0.006 |
opard | +0.005 |
Neg logit contributions | |
prise | -0.010 |
Katie | -0.010 |
Baby | -0.010 |
Ethan | -0.010 |
Annie | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
ebra | +0.006 |
opard | +0.005 |
s | +0.005 |
ites | +0.005 |
ite | +0.005 |
Neg logit contributions | |
prise | -0.005 |
Katie | -0.004 |
install | -0.004 |
Ethan | -0.004 |
Baby | -0.004 |
Token | calm |
Token ID | 9480 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
prise | +0.044 |
install | +0.042 |
Katie | +0.041 |
Ethan | +0.040 |
Baby | +0.040 |
Neg logit contributions | |
ebra | -0.047 |
s | -0.044 |
opard | -0.044 |
gers | -0.043 |
ang | -0.043 |
Token | find |
Token ID | 1064 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
ebra | +0.024 |
legs | +0.023 |
s | +0.023 |
arrows | +0.022 |
skills | +0.022 |
Neg logit contributions | |
prise | -0.032 |
dining | -0.032 |
Katie | -0.030 |
agna | -0.030 |
Ethan | -0.029 |
Token | her |
Token ID | 607 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
ebra | +0.018 |
s | +0.017 |
arrows | +0.017 |
legs | +0.016 |
ang | +0.016 |
Neg logit contributions | |
prise | -0.025 |
install | -0.024 |
Esk | -0.023 |
dining | -0.023 |
Ethan | -0.023 |
Token | red |
Token ID | 2266 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ebra | +0.031 |
gers | +0.029 |
opard | +0.029 |
ang | +0.029 |
s | +0.028 |
Neg logit contributions | |
prise | -0.031 |
install | -0.030 |
Katie | -0.030 |
dessert | -0.029 |
Baby | -0.029 |
Token | brick |
Token ID | 17214 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
ebra | +0.089 |
gers | +0.089 |
ang | +0.088 |
opard | +0.084 |
ites | +0.081 |
Neg logit contributions | |
dessert | -0.061 |
repair | -0.058 |
prise | -0.058 |
install | -0.057 |
Daddy | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
prise | +0.039 |
install | +0.037 |
dessert | +0.037 |
Katie | +0.037 |
repair | +0.036 |
Neg logit contributions | |
ebra | -0.029 |
opard | -0.026 |
ang | -0.026 |
gers | -0.026 |
ites | -0.025 |
Token | but |
Token ID | 475 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ebra | +0.014 |
opard | +0.012 |
gers | +0.012 |
ang | +0.012 |
s | +0.012 |
Neg logit contributions | |
prise | -0.013 |
Katie | -0.013 |
install | -0.012 |
Baby | -0.012 |
Ethan | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
ebra | +0.012 |
ites | +0.011 |
opard | +0.011 |
gers | +0.011 |
ang | +0.011 |
Neg logit contributions | |
Katie | -0.011 |
Baby | -0.011 |
prise | -0.011 |
Annie | -0.011 |
Jimmy | -0.011 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
ebra | +0.001 |
s | +0.001 |
gers | +0.001 |
ang | +0.001 |
opard | +0.001 |
Neg logit contributions | |
prise | -0.001 |
install | -0.001 |
Katie | -0.001 |
dessert | -0.001 |
Baby | -0.001 |
Token | my |
Token ID | 1820 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
prise | +0.035 |
install | +0.033 |
Katie | +0.032 |
Ethan | +0.032 |
Baby | +0.031 |
Neg logit contributions | |
ebra | -0.041 |
s | -0.038 |
opard | -0.038 |
gers | -0.038 |
ang | -0.037 |
Token | told |
Token ID | 1297 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
prise | +0.129 |
install | +0.121 |
Katie | +0.120 |
Ethan | +0.117 |
dining | +0.116 |
Neg logit contributions | |
ebra | -0.135 |
s | -0.128 |
opard | -0.124 |
ang | -0.123 |
gers | -0.122 |
Token | her |
Token ID | 607 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
s | +0.004 |
ebra | +0.004 |
ted | +0.004 |
legs | +0.004 |
gers | +0.004 |
Neg logit contributions | |
prise | -0.011 |
install | -0.010 |
Esk | -0.010 |
dining | -0.010 |
agna | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
ebra | +0.030 |
opard | +0.026 |
ites | +0.025 |
affe | +0.025 |
gers | +0.025 |
Neg logit contributions | |
Katie | -0.054 |
prise | -0.054 |
install | -0.054 |
Ethan | -0.052 |
Baby | -0.052 |
Token | tried |
Token ID | 3088 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
prise | +0.023 |
install | +0.021 |
Esk | +0.020 |
Katie | +0.020 |
dessert | +0.020 |
Neg logit contributions | |
s | -0.018 |
ebra | -0.017 |
ang | -0.016 |
legs | -0.016 |
gers | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ebra | +0.021 |
opard | +0.019 |
gers | +0.019 |
ang | +0.019 |
affe | +0.018 |
Neg logit contributions | |
Katie | -0.026 |
install | -0.026 |
prise | -0.026 |
dessert | -0.025 |
Jimmy | -0.025 |
Token | snap |
Token ID | 11495 |
Feature activation | +9.03e-03 |
Pos logit contributions | |
ebra | +0.011 |
legs | +0.010 |
arrows | +0.010 |
s | +0.010 |
ang | +0.010 |
Neg logit contributions | |
prise | -0.012 |
Katie | -0.011 |
dining | -0.011 |
Ethan | -0.011 |
Baby | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
ebra | +0.000 |
opard | +0.000 |
ang | +0.000 |
ite | +0.000 |
ites | +0.000 |
Neg logit contributions | |
Katie | -0.000 |
prise | -0.000 |
Ethan | -0.000 |
Baby | -0.000 |
install | -0.000 |
Token | fingers |
Token ID | 9353 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ebra | +0.042 |
ites | +0.040 |
opard | +0.040 |
gers | +0.039 |
ang | +0.038 |
Neg logit contributions | |
Daddy | -0.054 |
prise | -0.054 |
install | -0.054 |
Katie | -0.053 |
dessert | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ebra | +0.096 |
opard | +0.087 |
gers | +0.083 |
ang | +0.081 |
ites | +0.080 |
Neg logit contributions | |
prise | -0.111 |
install | -0.109 |
Katie | -0.108 |
Ethan | -0.105 |
Jimmy | -0.104 |
Token | same |
Token ID | 976 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ebra | +0.013 |
s | +0.012 |
opard | +0.012 |
ang | +0.012 |
gers | +0.012 |
Neg logit contributions | |
prise | -0.013 |
install | -0.013 |
Katie | -0.012 |
Ethan | -0.012 |
Baby | -0.012 |
Token | way |
Token ID | 835 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
prise | +0.062 |
install | +0.061 |
Katie | +0.060 |
dessert | +0.059 |
Ethan | +0.058 |
Neg logit contributions | |
ebra | -0.054 |
opard | -0.049 |
ites | -0.049 |
ang | -0.048 |
gers | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
Katie | +0.009 |
Ethan | +0.009 |
Baby | +0.009 |
install | +0.009 |
Jimmy | +0.009 |
Neg logit contributions | |
ebra | -0.010 |
opard | -0.009 |
gers | -0.008 |
ang | -0.008 |
ites | -0.008 |
Token | frog |
Token ID | 21264 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
prise | +0.022 |
install | +0.021 |
Katie | +0.021 |
Ethan | +0.021 |
Baby | +0.020 |
Neg logit contributions | |
ebra | -0.016 |
s | -0.015 |
opard | -0.015 |
gers | -0.014 |
ang | -0.014 |
Token | for |
Token ID | 329 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ebra | +0.015 |
opard | +0.013 |
ang | +0.013 |
s | +0.013 |
ites | +0.013 |
Neg logit contributions | |
prise | -0.026 |
install | -0.025 |
Katie | -0.025 |
Baby | -0.024 |
Ethan | -0.024 |
Token | her |
Token ID | 607 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
ebra | +0.063 |
s | +0.058 |
gers | +0.058 |
opard | +0.057 |
legs | +0.057 |
Neg logit contributions | |
prise | -0.064 |
install | -0.061 |
Katie | -0.060 |
Ethan | -0.059 |
dining | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
ebra | +0.004 |
s | +0.003 |
opard | +0.003 |
ang | +0.003 |
gers | +0.003 |
Neg logit contributions | |
prise | -0.005 |
install | -0.005 |
Katie | -0.005 |
Ethan | -0.005 |
Baby | -0.005 |
Token | Brown |
Token ID | 4373 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ebra | +0.002 |
s | +0.002 |
opard | +0.002 |
legs | +0.002 |
ang | +0.002 |
Neg logit contributions | |
prise | -0.002 |
install | -0.002 |
Esk | -0.002 |
dining | -0.002 |
dessert | -0.002 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
prise | +0.108 |
install | +0.102 |
Katie | +0.101 |
Ethan | +0.099 |
Esk | +0.098 |
Neg logit contributions | |
ebra | -0.089 |
s | -0.083 |
opard | -0.081 |
ang | -0.080 |
gers | -0.079 |
Token | up |
Token ID | 510 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
prise | +0.074 |
install | +0.071 |
Katie | +0.069 |
Ethan | +0.068 |
Esk | +0.068 |
Neg logit contributions | |
ebra | -0.037 |
s | -0.036 |
gers | -0.033 |
ang | -0.033 |
opard | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
ebra | +0.059 |
opard | +0.054 |
ites | +0.050 |
affe | +0.049 |
ang | +0.047 |
Neg logit contributions | |
Katie | -0.088 |
Jimmy | -0.083 |
Baby | -0.082 |
Sus | -0.081 |
Daddy | -0.081 |
Token | wondering |
Token ID | 11263 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ebra | +0.022 |
s | +0.020 |
opard | +0.020 |
gers | +0.019 |
ang | +0.019 |
Neg logit contributions | |
prise | -0.044 |
install | -0.042 |
Katie | -0.042 |
Ethan | -0.041 |
Baby | -0.041 |
Token | what |
Token ID | 644 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
prise | +0.059 |
install | +0.055 |
Katie | +0.054 |
Ethan | +0.052 |
Baby | +0.051 |
Neg logit contributions | |
ebra | -0.124 |
s | -0.117 |
opard | -0.116 |
gers | -0.115 |
ang | -0.115 |
Token | it |
Token ID | 340 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
prise | +0.155 |
install | +0.148 |
Katie | +0.147 |
Ethan | +0.143 |
Baby | +0.142 |
Neg logit contributions | |
ebra | -0.119 |
s | -0.109 |
opard | -0.108 |
gers | -0.106 |
ang | -0.106 |
Token | was |
Token ID | 373 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
ebra | +0.017 |
s | +0.016 |
opard | +0.016 |
gers | +0.016 |
ang | +0.015 |
Neg logit contributions | |
prise | -0.026 |
install | -0.025 |
Katie | -0.025 |
Ethan | -0.024 |
Baby | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ebra | +0.099 |
ites | +0.089 |
ang | +0.089 |
gers | +0.089 |
opard | +0.088 |
Neg logit contributions | |
prise | -0.133 |
install | -0.129 |
Katie | -0.128 |
Esk | -0.127 |
dessert | -0.126 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
ebra | +0.006 |
s | +0.006 |
ang | +0.006 |
opard | +0.006 |
gers | +0.005 |
Neg logit contributions | |
prise | -0.010 |
install | -0.009 |
Esk | -0.009 |
Katie | -0.009 |
dining | -0.009 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ebra | +0.038 |
s | +0.037 |
ang | +0.034 |
gers | +0.034 |
ite | +0.034 |
Neg logit contributions | |
prise | -0.061 |
install | -0.059 |
Katie | -0.056 |
dining | -0.055 |
Ethan | -0.055 |
Token | upon |
Token ID | 2402 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
prise | +0.006 |
Katie | +0.006 |
install | +0.006 |
Ethan | +0.005 |
Baby | +0.005 |
Neg logit contributions | |
ebra | -0.006 |
opard | -0.006 |
gers | -0.006 |
s | -0.006 |
ang | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
ebra | +0.038 |
s | +0.037 |
gers | +0.036 |
arrows | +0.036 |
legs | +0.036 |
Neg logit contributions | |
prise | -0.053 |
install | -0.052 |
Katie | -0.049 |
Ethan | -0.049 |
Acc | -0.049 |
Token | time |
Token ID | 640 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
prise | +0.014 |
Katie | +0.013 |
install | +0.013 |
Baby | +0.013 |
dessert | +0.013 |
Neg logit contributions | |
ebra | -0.015 |
s | -0.014 |
opard | -0.014 |
gers | -0.014 |
ites | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
ebra | +0.014 |
opard | +0.012 |
gers | +0.012 |
s | +0.012 |
ang | +0.011 |
Neg logit contributions | |
prise | -0.040 |
Katie | -0.039 |
install | -0.039 |
Ethan | -0.038 |
Baby | -0.038 |
Token | in |
Token ID | 287 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ebra | +0.038 |
s | +0.036 |
ang | +0.036 |
opard | +0.036 |
ite | +0.034 |
Neg logit contributions | |
prise | -0.046 |
install | -0.045 |
Katie | -0.043 |
Ethan | -0.043 |
dining | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
prise | +0.027 |
install | +0.025 |
Katie | +0.025 |
Ethan | +0.024 |
Baby | +0.024 |
Neg logit contributions | |
ebra | -0.034 |
s | -0.031 |
opard | -0.031 |
gers | -0.031 |
ang | -0.031 |
Token | small |
Token ID | 1402 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
prise | +0.068 |
install | +0.065 |
Katie | +0.063 |
Ethan | +0.062 |
Sus | +0.060 |
Neg logit contributions | |
ebra | -0.049 |
s | -0.045 |
ang | -0.044 |
opard | -0.044 |
gers | -0.042 |
Token | village |
Token ID | 7404 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
prise | +0.034 |
install | +0.032 |
Katie | +0.032 |
Ethan | +0.031 |
Baby | +0.031 |
Neg logit contributions | |
ebra | -0.033 |
s | -0.031 |
opard | -0.030 |
gers | -0.030 |
ang | -0.030 |
Token | so |
Token ID | 523 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ebra | +0.046 |
s | +0.045 |
legs | +0.043 |
opard | +0.042 |
gers | +0.042 |
Neg logit contributions | |
prise | -0.048 |
install | -0.045 |
Katie | -0.044 |
Ethan | -0.044 |
Esk | -0.043 |
Token | happy |
Token ID | 3772 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
prise | +0.093 |
install | +0.087 |
Katie | +0.086 |
Ethan | +0.084 |
Esk | +0.081 |
Neg logit contributions | |
s | -0.098 |
ebra | -0.097 |
ang | -0.092 |
legs | -0.092 |
gers | -0.091 |
Token | ! |
Token ID | 0 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
prise | +0.071 |
install | +0.068 |
Katie | +0.067 |
Ethan | +0.066 |
Baby | +0.065 |
Neg logit contributions | |
ebra | -0.033 |
s | -0.030 |
opard | -0.028 |
gers | -0.028 |
ang | -0.028 |
Token | Every |
Token ID | 3887 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ebra | +0.030 |
s | +0.029 |
ang | +0.027 |
opard | +0.027 |
ite | +0.027 |
Neg logit contributions | |
prise | -0.045 |
install | -0.043 |
Esk | -0.041 |
dining | -0.040 |
dessert | -0.040 |
Token | day |
Token ID | 1110 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
ebra | +0.056 |
s | +0.050 |
opard | +0.050 |
ang | +0.049 |
gers | +0.048 |
Neg logit contributions | |
prise | -0.088 |
Katie | -0.084 |
install | -0.083 |
Baby | -0.082 |
Ethan | -0.082 |
Token | she |
Token ID | 673 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ebra | +0.090 |
s | +0.087 |
gers | +0.082 |
opard | +0.076 |
ang | +0.076 |
Neg logit contributions | |
prise | -0.212 |
install | -0.203 |
Esk | -0.197 |
dining | -0.195 |
Katie | -0.193 |
Token | carried |
Token ID | 5281 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
ebra | +0.051 |
s | +0.049 |
gers | +0.044 |
legs | +0.043 |
ang | +0.043 |
Neg logit contributions | |
prise | -0.091 |
install | -0.085 |
Katie | -0.084 |
dessert | -0.082 |
Esk | -0.082 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ebra | +0.025 |
opard | +0.023 |
s | +0.023 |
ang | +0.022 |
gers | +0.022 |
Neg logit contributions | |
prise | -0.027 |
Katie | -0.026 |
install | -0.025 |
Ethan | -0.025 |
Baby | -0.025 |
Token | bear |
Token ID | 6842 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
ebra | +0.046 |
opard | +0.042 |
s | +0.041 |
gers | +0.041 |
legs | +0.040 |
Neg logit contributions | |
prise | -0.061 |
install | -0.058 |
Katie | -0.057 |
Esk | -0.056 |
Ethan | -0.056 |
Token | with |
Token ID | 351 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
ebra | +0.105 |
opard | +0.094 |
ang | +0.093 |
gers | +0.093 |
affe | +0.089 |
Neg logit contributions | |
prise | -0.124 |
install | -0.118 |
Katie | -0.116 |
dessert | -0.113 |
Baby | -0.113 |
Token | her |
Token ID | 607 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
ebra | +0.046 |
opard | +0.042 |
s | +0.042 |
ang | +0.041 |
gers | +0.041 |
Neg logit contributions | |
prise | -0.051 |
Katie | -0.049 |
install | -0.048 |
Ethan | -0.047 |
Baby | -0.047 |
Token | dog |
Token ID | 3290 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ebra | +0.026 |
s | +0.023 |
ang | +0.022 |
opard | +0.022 |
gers | +0.022 |
Neg logit contributions | |
prise | -0.050 |
install | -0.048 |
Katie | -0.047 |
Ethan | -0.046 |
Baby | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
ebra | +0.073 |
opard | +0.065 |
gers | +0.065 |
ites | +0.064 |
ang | +0.063 |
Neg logit contributions | |
prise | -0.117 |
install | -0.114 |
Katie | -0.110 |
Baby | -0.109 |
dessert | -0.109 |
Token | the |
Token ID | 262 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
prise | +0.014 |
install | +0.014 |
Katie | +0.014 |
Baby | +0.013 |
Ethan | +0.013 |
Neg logit contributions | |
ebra | -0.019 |
opard | -0.017 |
s | -0.017 |
ang | -0.017 |
gers | -0.017 |
Token | vest |
Token ID | 19750 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
prise | +0.001 |
install | +0.001 |
Katie | +0.001 |
Ethan | +0.001 |
Baby | +0.001 |
Neg logit contributions | |
ebra | -0.000 |
s | -0.000 |
ang | -0.000 |
opard | -0.000 |
gers | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
install | +0.026 |
prise | +0.025 |
Esk | +0.025 |
repair | +0.025 |
dessert | +0.025 |
Neg logit contributions | |
ebra | -0.033 |
ites | -0.029 |
opard | -0.029 |
ang | -0.029 |
ite | -0.027 |
Token | They |
Token ID | 1119 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
prise | +0.008 |
Katie | +0.008 |
install | +0.008 |
Baby | +0.008 |
Ethan | +0.008 |
Neg logit contributions | |
ebra | -0.007 |
opard | -0.006 |
ang | -0.006 |
s | -0.006 |
gers | -0.006 |
Token | feel |
Token ID | 1254 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
ebra | +0.002 |
s | +0.002 |
legs | +0.002 |
arrows | +0.002 |
opard | +0.002 |
Neg logit contributions | |
prise | -0.002 |
Katie | -0.001 |
install | -0.001 |
dining | -0.001 |
dessert | -0.001 |
Token | sorry |
Token ID | 7926 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ebra | +0.011 |
s | +0.010 |
gers | +0.010 |
legs | +0.010 |
ang | +0.010 |
Neg logit contributions | |
prise | -0.010 |
install | -0.010 |
Katie | -0.009 |
dining | -0.009 |
Ethan | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
prise | +0.116 |
install | +0.116 |
dessert | +0.114 |
Baby | +0.114 |
Esk | +0.114 |
Neg logit contributions | |
ebra | -0.111 |
ites | -0.098 |
opard | -0.098 |
ang | -0.097 |
ite | -0.095 |
Token | They |
Token ID | 1119 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
ebra | +0.010 |
opard | +0.009 |
s | +0.009 |
ang | +0.009 |
gers | +0.008 |
Neg logit contributions | |
prise | -0.012 |
Katie | -0.011 |
install | -0.011 |
Baby | -0.011 |
Ethan | -0.011 |
Token | miss |
Token ID | 2051 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
s | +0.007 |
ebra | +0.007 |
arrows | +0.007 |
affe | +0.007 |
legs | +0.006 |
Neg logit contributions | |
prise | -0.006 |
Katie | -0.006 |
dining | -0.006 |
install | -0.006 |
dessert | -0.006 |
Token | so |
Token ID | 523 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ebra | +0.061 |
opard | +0.055 |
gers | +0.055 |
s | +0.055 |
ang | +0.054 |
Neg logit contributions | |
prise | -0.076 |
Katie | -0.075 |
install | -0.074 |
Baby | -0.073 |
Ethan | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
Katie | +0.087 |
prise | +0.085 |
Annie | +0.084 |
Baby | +0.084 |
install | +0.081 |
Neg logit contributions | |
ebra | -0.074 |
opard | -0.066 |
gers | -0.065 |
pads | -0.065 |
ites | -0.064 |
Token | lady |
Token ID | 10846 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
ebra | +0.027 |
s | +0.024 |
opard | +0.024 |
ang | +0.024 |
gers | +0.023 |
Neg logit contributions | |
prise | -0.045 |
install | -0.043 |
Katie | -0.043 |
Baby | -0.042 |
Ethan | -0.041 |
Token | opened |
Token ID | 4721 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ebra | +0.052 |
s | +0.050 |
opard | +0.048 |
ang | +0.047 |
gers | +0.047 |
Neg logit contributions | |
prise | -0.051 |
install | -0.048 |
Katie | -0.048 |
Ethan | -0.047 |
Esk | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
prise | +0.093 |
Katie | +0.089 |
install | +0.089 |
Ethan | +0.086 |
Baby | +0.086 |
Neg logit contributions | |
ebra | -0.092 |
opard | -0.084 |
s | -0.084 |
gers | -0.083 |
ang | -0.083 |
Token | bag |
Token ID | 6131 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
ebra | +0.020 |
s | +0.018 |
opard | +0.017 |
ang | +0.017 |
gers | +0.017 |
Neg logit contributions | |
prise | -0.031 |
install | -0.030 |
Katie | -0.030 |
Ethan | -0.029 |
Baby | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ebra | +0.001 |
opard | +0.001 |
ang | +0.001 |
ites | +0.001 |
gers | +0.001 |
Neg logit contributions | |
Katie | -0.001 |
install | -0.001 |
prise | -0.001 |
dining | -0.001 |
Annie | -0.001 |
Token | showed |
Token ID | 3751 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
s | +0.010 |
ted | +0.009 |
arrows | +0.009 |
ebra | +0.009 |
legs | +0.009 |
Neg logit contributions | |
prise | -0.012 |
Esk | -0.012 |
Acc | -0.012 |
dessert | -0.011 |
install | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
ebra | +0.008 |
s | +0.008 |
opard | +0.007 |
gers | +0.007 |
ang | +0.007 |
Neg logit contributions | |
prise | -0.010 |
install | -0.010 |
Ethan | -0.009 |
dining | -0.009 |
Katie | -0.009 |
Token | what |
Token ID | 644 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
s | +0.018 |
ebra | +0.017 |
legs | +0.017 |
gers | +0.016 |
arrows | +0.016 |
Neg logit contributions | |
prise | -0.025 |
install | -0.023 |
Ethan | -0.023 |
Acc | -0.022 |
Esk | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
prise | +0.214 |
install | +0.207 |
Esk | +0.198 |
Ethan | +0.198 |
Katie | +0.194 |
Neg logit contributions | |
s | -0.115 |
ebra | -0.114 |
gers | -0.108 |
opard | -0.106 |
legs | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
install | +0.051 |
prise | +0.051 |
Katie | +0.049 |
Ethan | +0.049 |
dining | +0.048 |
Neg logit contributions | |
ebra | -0.041 |
opard | -0.037 |
ang | -0.036 |
affe | -0.035 |
ites | -0.035 |
Token | He |
Token ID | 679 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
prise | +0.011 |
Katie | +0.011 |
install | +0.011 |
Ethan | +0.011 |
Baby | +0.011 |
Neg logit contributions | |
ebra | -0.008 |
opard | -0.008 |
s | -0.008 |
ang | -0.008 |
ites | -0.007 |
Token | heard |
Token ID | 2982 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
prise | +0.002 |
install | +0.002 |
Katie | +0.002 |
Ethan | +0.002 |
Baby | +0.002 |
Neg logit contributions | |
ebra | -0.002 |
s | -0.002 |
gers | -0.002 |
opard | -0.002 |
ang | -0.002 |
Token | his |
Token ID | 465 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
s | +0.048 |
arrows | +0.048 |
legs | +0.046 |
ebra | +0.045 |
ted | +0.045 |
Neg logit contributions | |
prise | -0.080 |
install | -0.072 |
Acc | -0.070 |
agna | -0.070 |
dining | -0.070 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
ebra | +0.056 |
opard | +0.052 |
ites | +0.052 |
s | +0.052 |
ang | +0.052 |
Neg logit contributions | |
prise | -0.054 |
Katie | -0.051 |
install | -0.051 |
Ethan | -0.050 |
Baby | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
s | +0.023 |
ebra | +0.021 |
ang | +0.020 |
legs | +0.020 |
ted | +0.019 |
Neg logit contributions | |
prise | -0.019 |
perfection | -0.018 |
agna | -0.017 |
dessert | -0.017 |
Katie | -0.017 |
Token | dad |
Token ID | 9955 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
prise | +0.021 |
install | +0.019 |
dining | +0.019 |
perfection | +0.019 |
dessert | +0.019 |
Neg logit contributions | |
s | -0.014 |
ebra | -0.013 |
legs | -0.013 |
arrows | -0.012 |
gers | -0.012 |
Token | arguing |
Token ID | 11810 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
prise | +0.103 |
perfection | +0.098 |
agna | +0.094 |
Esk | +0.094 |
dessert | +0.092 |
Neg logit contributions | |
s | -0.108 |
legs | -0.093 |
ebra | -0.091 |
ang | -0.089 |
ted | -0.087 |
Token | downstairs |
Token ID | 34624 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
prise | +0.143 |
install | +0.132 |
Katie | +0.132 |
Baby | +0.130 |
Ethan | +0.130 |
Neg logit contributions | |
ebra | -0.086 |
s | -0.085 |
gers | -0.080 |
legs | -0.077 |
opard | -0.076 |
Token | . |
Token ID | 13 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
prise | +0.243 |
install | +0.231 |
Katie | +0.229 |
Ethan | +0.225 |
Baby | +0.224 |
Neg logit contributions | |
ebra | -0.133 |
s | -0.122 |
opard | -0.117 |
gers | -0.117 |
ang | -0.116 |
Token | He |
Token ID | 679 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
Katie | +0.009 |
prise | +0.009 |
install | +0.009 |
Ethan | +0.009 |
Baby | +0.009 |
Neg logit contributions | |
ebra | -0.009 |
opard | -0.008 |
ang | -0.008 |
gers | -0.007 |
ites | -0.007 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
prise | +0.019 |
dessert | +0.018 |
install | +0.017 |
Esk | +0.017 |
Acc | +0.017 |
Neg logit contributions | |
s | -0.014 |
ebra | -0.013 |
ted | -0.013 |
legs | -0.012 |
arrows | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
prise | +0.065 |
install | +0.062 |
Katie | +0.059 |
dining | +0.058 |
Ethan | +0.058 |
Neg logit contributions | |
ebra | -0.057 |
s | -0.054 |
arrows | -0.052 |
gers | -0.052 |
opard | -0.051 |
Token | small |
Token ID | 1402 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
prise | +0.040 |
install | +0.039 |
Katie | +0.038 |
Ethan | +0.038 |
Esk | +0.037 |
Neg logit contributions | |
ebra | -0.026 |
s | -0.025 |
opard | -0.025 |
gers | -0.023 |
legs | -0.023 |
Token | fairy |
Token ID | 25607 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
prise | +0.004 |
install | +0.004 |
Katie | +0.004 |
Ethan | +0.004 |
Baby | +0.004 |
Neg logit contributions | |
ebra | -0.003 |
s | -0.002 |
opard | -0.002 |
gers | -0.002 |
ang | -0.002 |
Token | standing |
Token ID | 5055 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ebra | +0.095 |
s | +0.087 |
opard | +0.084 |
ang | +0.084 |
gers | +0.083 |
Neg logit contributions | |
prise | -0.146 |
install | -0.141 |
Katie | -0.139 |
Ethan | -0.137 |
Baby | -0.136 |
Token | there |
Token ID | 612 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
prise | +0.120 |
install | +0.114 |
Katie | +0.114 |
Ethan | +0.111 |
Baby | +0.110 |
Neg logit contributions | |
ebra | -0.094 |
s | -0.087 |
opard | -0.086 |
gers | -0.084 |
ang | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
prise | +0.067 |
install | +0.064 |
Katie | +0.064 |
Ethan | +0.063 |
Baby | +0.062 |
Neg logit contributions | |
ebra | -0.037 |
s | -0.034 |
opard | -0.033 |
gers | -0.032 |
ang | -0.032 |
Token | Maxwell |
Token ID | 28276 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
prise | +0.009 |
install | +0.008 |
Esk | +0.008 |
dessert | +0.008 |
dining | +0.008 |
Neg logit contributions | |
s | -0.006 |
ebra | -0.006 |
gers | -0.005 |
opard | -0.005 |
legs | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
s | +0.033 |
ebra | +0.030 |
legs | +0.029 |
arrows | +0.028 |
opard | +0.027 |
Neg logit contributions | |
prise | -0.049 |
install | -0.045 |
dessert | -0.045 |
Esk | -0.044 |
dining | -0.044 |
Token | very |
Token ID | 845 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
legs | +0.016 |
tail | +0.015 |
wings | +0.014 |
ang | +0.014 |
arms | +0.013 |
Neg logit contributions | |
prise | -0.025 |
install | -0.023 |
agna | -0.023 |
Ethan | -0.022 |
perfection | -0.022 |
Token | happy |
Token ID | 3772 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
prise | +0.075 |
agna | +0.073 |
install | +0.072 |
Ethan | +0.072 |
dining | +0.071 |
Neg logit contributions | |
s | -0.056 |
legs | -0.054 |
ang | -0.054 |
ebra | -0.048 |
arrows | -0.048 |
Token | big |
Token ID | 1263 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ebra | +0.046 |
s | +0.045 |
opard | +0.044 |
gers | +0.043 |
legs | +0.043 |
Neg logit contributions | |
prise | -0.052 |
install | -0.049 |
Ethan | -0.048 |
Katie | -0.047 |
Esk | -0.047 |
Token | bou |
Token ID | 35833 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
prise | +0.073 |
install | +0.070 |
Katie | +0.068 |
Ethan | +0.068 |
Esk | +0.067 |
Neg logit contributions | |
ebra | -0.038 |
s | -0.035 |
gers | -0.033 |
opard | -0.033 |
legs | -0.032 |
Token | quet |
Token ID | 21108 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
ebra | +0.003 |
opard | +0.003 |
legs | +0.003 |
gers | +0.003 |
ang | +0.003 |
Neg logit contributions | |
prise | -0.003 |
install | -0.002 |
Katie | -0.002 |
bake | -0.002 |
dining | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Katie | +0.041 |
Annie | +0.039 |
Daddy | +0.038 |
Sus | +0.037 |
Jimmy | +0.037 |
Neg logit contributions | |
ebra | -0.039 |
opard | -0.034 |
ang | -0.032 |
gers | -0.032 |
affe | -0.032 |
Token | flowers |
Token ID | 12734 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
prise | +0.009 |
install | +0.009 |
Ethan | +0.008 |
Katie | +0.008 |
Esk | +0.008 |
Neg logit contributions | |
ebra | -0.006 |
s | -0.006 |
gers | -0.006 |
opard | -0.006 |
ites | -0.006 |
Token | back |
Token ID | 736 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
ebra | +0.048 |
opard | +0.042 |
gers | +0.039 |
affe | +0.039 |
ang | +0.039 |
Neg logit contributions | |
Katie | -0.069 |
prise | -0.068 |
Annie | -0.066 |
install | -0.066 |
Baby | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
prise | +0.045 |
Katie | +0.045 |
install | +0.043 |
Baby | +0.043 |
Annie | +0.043 |
Neg logit contributions | |
ebra | -0.024 |
opard | -0.021 |
gers | -0.020 |
affe | -0.020 |
ang | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
prise | +0.118 |
install | +0.111 |
Esk | +0.109 |
Ethan | +0.108 |
plug | +0.103 |
Neg logit contributions | |
ebra | -0.075 |
s | -0.071 |
every | -0.067 |
legs | -0.067 |
gers | -0.067 |
Token | kitchen |
Token ID | 9592 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
prise | +0.077 |
install | +0.071 |
Ethan | +0.070 |
izz | +0.069 |
Esk | +0.067 |
Neg logit contributions | |
opard | -0.050 |
s | -0.050 |
legs | -0.049 |
gers | -0.048 |
tail | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
prise | +0.371 |
install | +0.352 |
Ethan | +0.345 |
Katie | +0.343 |
Esk | +0.341 |
Neg logit contributions | |
ebra | -0.169 |
s | -0.163 |
gers | -0.150 |
opard | -0.149 |
legs | -0.147 |
Token | carefully |
Token ID | 7773 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
prise | +0.051 |
Esk | +0.047 |
install | +0.046 |
Ethan | +0.046 |
Acc | +0.043 |
Neg logit contributions | |
s | -0.041 |
legs | -0.039 |
ebra | -0.038 |
ted | -0.037 |
pads | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ebra | +0.070 |
ites | +0.063 |
opard | +0.062 |
ang | +0.062 |
arrows | +0.062 |
Neg logit contributions | |
Katie | -0.111 |
install | -0.111 |
bake | -0.110 |
dining | -0.109 |
dessert | -0.108 |
Token | a |
Token ID | 257 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
s | +0.014 |
legs | +0.013 |
gers | +0.013 |
arrows | +0.012 |
ebra | +0.012 |
Neg logit contributions | |
prise | -0.013 |
Esk | -0.012 |
install | -0.011 |
Acc | -0.011 |
erupt | -0.011 |
Token | shiny |
Token ID | 22441 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
prise | +0.023 |
install | +0.023 |
Katie | +0.022 |
Esk | +0.022 |
Ethan | +0.022 |
Neg logit contributions | |
ebra | -0.018 |
s | -0.018 |
legs | -0.017 |
opard | -0.017 |
gers | -0.016 |
Token | chain |
Token ID | 6333 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
ebra | +0.018 |
s | +0.017 |
ang | +0.017 |
ites | +0.017 |
opard | +0.017 |
Neg logit contributions | |
prise | -0.019 |
dessert | -0.018 |
Katie | -0.017 |
install | -0.017 |
Ethan | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ebra | +0.118 |
opard | +0.104 |
ang | +0.104 |
ites | +0.103 |
gers | +0.099 |
Neg logit contributions | |
prise | -0.131 |
install | -0.131 |
Katie | -0.129 |
Ethan | -0.126 |
dining | -0.124 |
Token | Baby |
Token ID | 14801 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
prise | +0.009 |
install | +0.008 |
Esk | +0.007 |
believe | +0.007 |
gen | +0.007 |
Neg logit contributions | |
s | -0.005 |
legs | -0.004 |
ted | -0.004 |
pads | -0.004 |
gers | -0.004 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
prise | +0.298 |
install | +0.273 |
perfection | +0.266 |
dessert | +0.262 |
dining | +0.259 |
Neg logit contributions | |
s | -0.161 |
ebra | -0.153 |
legs | -0.140 |
opard | -0.138 |
ang | -0.134 |
Token | and |
Token ID | 290 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
prise | +0.121 |
dining | +0.106 |
install | +0.105 |
bluff | +0.104 |
Acc | +0.104 |
Neg logit contributions | |
every | -0.030 |
s | -0.028 |
and | -0.026 |
legs | -0.026 |
ted | -0.024 |
Token | smiled |
Token ID | 13541 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
prise | +0.014 |
install | +0.013 |
Esk | +0.012 |
punish | +0.012 |
agna | +0.012 |
Neg logit contributions | |
legs | -0.009 |
s | -0.009 |
ebra | -0.008 |
every | -0.008 |
ang | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
ebra | +0.016 |
s | +0.014 |
opard | +0.014 |
gers | +0.014 |
ang | +0.014 |
Neg logit contributions | |
prise | -0.029 |
install | -0.027 |
Katie | -0.027 |
Ethan | -0.027 |
Baby | -0.027 |
Token | She |
Token ID | 1375 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
prise | +0.003 |
install | +0.002 |
believe | +0.002 |
punished | +0.002 |
Esk | +0.002 |
Neg logit contributions | |
s | -0.001 |
legs | -0.001 |
ebra | -0.001 |
pads | -0.001 |
gers | -0.001 |
Token | Thank |
Token ID | 10449 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
prise | +0.001 |
install | +0.001 |
Esk | +0.001 |
Katie | +0.001 |
Ethan | +0.001 |
Neg logit contributions | |
ebra | -0.001 |
s | -0.001 |
opard | -0.001 |
gers | -0.001 |
ang | -0.001 |
Token | you |
Token ID | 345 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
prise | +0.029 |
Katie | +0.026 |
install | +0.025 |
Baby | +0.025 |
Annie | +0.024 |
Neg logit contributions | |
ebra | -0.050 |
opard | -0.047 |
s | -0.047 |
gers | -0.046 |
ang | -0.046 |
Token | for |
Token ID | 329 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
ebra | +0.004 |
s | +0.004 |
opard | +0.003 |
gers | +0.003 |
ang | +0.003 |
Neg logit contributions | |
prise | -0.010 |
install | -0.010 |
Katie | -0.009 |
Ethan | -0.009 |
Esk | -0.009 |
Token | helping |
Token ID | 5742 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ebra | +0.090 |
legs | +0.087 |
skills | +0.085 |
ang | +0.083 |
tail | +0.083 |
Neg logit contributions | |
Katie | -0.106 |
prise | -0.104 |
Ethan | -0.103 |
install | -0.100 |
Nathan | -0.098 |
Token | to |
Token ID | 284 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
prise | +0.108 |
Esk | +0.105 |
install | +0.102 |
dining | +0.100 |
Ethan | +0.099 |
Neg logit contributions | |
s | -0.060 |
ebra | -0.057 |
legs | -0.057 |
skills | -0.052 |
every | -0.051 |
Token | clean |
Token ID | 3424 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
prise | +0.034 |
Katie | +0.032 |
Claus | +0.030 |
agna | +0.029 |
Son | +0.029 |
Neg logit contributions | |
legs | -0.055 |
every | -0.054 |
skills | -0.053 |
s | -0.053 |
ebra | -0.053 |
Token | Ruby |
Token ID | 10888 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
prise | +0.231 |
install | +0.216 |
Katie | +0.211 |
Ethan | +0.207 |
Esk | +0.205 |
Neg logit contributions | |
ebra | -0.230 |
s | -0.217 |
gers | -0.210 |
opard | -0.208 |
ang | -0.208 |
Token | , |
Token ID | 11 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
s | +0.002 |
legs | +0.001 |
every | +0.001 |
ebra | +0.001 |
skills | +0.001 |
Neg logit contributions | |
prise | -0.003 |
Ethan | -0.003 |
Katie | -0.003 |
install | -0.003 |
Esk | -0.003 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
prise | +0.011 |
install | +0.010 |
Katie | +0.010 |
Ethan | +0.010 |
Esk | +0.009 |
Neg logit contributions | |
ebra | -0.012 |
s | -0.011 |
opard | -0.011 |
gers | -0.011 |
ang | -0.011 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
prise | +0.145 |
install | +0.138 |
Katie | +0.132 |
Ethan | +0.131 |
Nathan | +0.129 |
Neg logit contributions | |
s | -0.096 |
ebra | -0.086 |
ite | -0.082 |
every | -0.081 |
pads | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
prise | +0.073 |
Katie | +0.073 |
Baby | +0.071 |
install | +0.070 |
Annie | +0.070 |
Neg logit contributions | |
ebra | -0.077 |
gers | -0.071 |
opard | -0.070 |
ang | -0.069 |
ites | -0.067 |
Token | show |
Token ID | 905 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
prise | +0.052 |
agna | +0.049 |
Esk | +0.048 |
igor | +0.047 |
Baby | +0.047 |
Neg logit contributions | |
every | -0.035 |
skills | -0.034 |
legs | -0.034 |
ebra | -0.032 |
arrows | -0.031 |
Token | Daddy |
Token ID | 26926 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
ebra | +0.047 |
s | +0.045 |
gers | +0.043 |
legs | +0.043 |
ang | +0.042 |
Neg logit contributions | |
prise | -0.070 |
install | -0.066 |
Esk | -0.064 |
dining | -0.063 |
Katie | -0.062 |
Token | her |
Token ID | 607 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
prise | +0.189 |
install | +0.178 |
Esk | +0.175 |
Ethan | +0.172 |
Katie | +0.169 |
Neg logit contributions | |
s | -0.138 |
ebra | -0.132 |
gers | -0.123 |
ites | -0.117 |
ang | -0.117 |
Token | new |
Token ID | 649 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
prise | +0.008 |
install | +0.007 |
Ethan | +0.007 |
Katie | +0.007 |
Esk | +0.007 |
Neg logit contributions | |
ebra | -0.007 |
s | -0.007 |
skills | -0.006 |
legs | -0.006 |
gers | -0.006 |
Token | f |
Token ID | 277 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
prise | +0.023 |
install | +0.022 |
Katie | +0.022 |
Ethan | +0.022 |
Baby | +0.021 |
Neg logit contributions | |
ebra | -0.018 |
s | -0.017 |
opard | -0.017 |
gers | -0.016 |
skills | -0.016 |
Token | auc |
Token ID | 14272 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
prise | +0.096 |
Katie | +0.088 |
install | +0.087 |
Baby | +0.085 |
Ethan | +0.084 |
Neg logit contributions | |
ebra | -0.198 |
s | -0.187 |
ang | -0.186 |
opard | -0.185 |
gers | -0.183 |
Token | et |
Token ID | 316 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
prise | +0.342 |
install | +0.328 |
Katie | +0.324 |
Ethan | +0.318 |
Baby | +0.315 |
Neg logit contributions | |
ebra | -0.183 |
s | -0.167 |
opard | -0.163 |
ang | -0.161 |
ites | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
ebra | +0.094 |
opard | +0.084 |
gers | +0.083 |
ang | +0.083 |
s | +0.082 |
Neg logit contributions | |
prise | -0.144 |
install | -0.140 |
Katie | -0.139 |
Ethan | -0.136 |
Baby | -0.134 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
prise | +0.028 |
install | +0.026 |
Esk | +0.025 |
punished | +0.025 |
dessert | +0.025 |
Neg logit contributions | |
s | -0.013 |
ebra | -0.011 |
ang | -0.010 |
ite | -0.010 |
legs | -0.009 |
Token | B |
Token ID | 33 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
prise | +0.004 |
install | +0.003 |
perfection | +0.003 |
Katie | +0.003 |
dining | +0.003 |
Neg logit contributions | |
s | -0.002 |
ebra | -0.002 |
gers | -0.002 |
ang | -0.002 |
ite | -0.002 |
Token | eth |
Token ID | 2788 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
prise | +0.015 |
install | +0.014 |
Katie | +0.014 |
dessert | +0.014 |
Esk | +0.014 |
Neg logit contributions | |
ebra | -0.014 |
s | -0.014 |
ang | -0.013 |
ite | -0.013 |
opard | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
ebra | +0.008 |
s | +0.007 |
opard | +0.007 |
gers | +0.007 |
ang | +0.007 |
Neg logit contributions | |
prise | -0.028 |
install | -0.027 |
Katie | -0.027 |
Ethan | -0.026 |
Baby | -0.026 |
Token | it |
Token ID | 340 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ebra | +0.034 |
dog | +0.033 |
s | +0.033 |
legs | +0.032 |
every | +0.031 |
Neg logit contributions | |
prise | -0.055 |
install | -0.055 |
plug | -0.054 |
handed | -0.052 |
Esk | -0.052 |
Token | is |
Token ID | 318 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
s | +0.009 |
ebra | +0.008 |
gers | +0.007 |
opard | +0.007 |
legs | +0.007 |
Neg logit contributions | |
prise | -0.016 |
install | -0.015 |
Katie | -0.015 |
Ethan | -0.015 |
Esk | -0.015 |
Token | time |
Token ID | 640 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
prise | +0.031 |
install | +0.030 |
Esk | +0.027 |
Ethan | +0.027 |
Acc | +0.027 |
Neg logit contributions | |
gers | -0.015 |
legs | -0.015 |
pads | -0.015 |
s | -0.015 |
ebra | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
prise | +0.039 |
install | +0.037 |
Katie | +0.037 |
Ethan | +0.037 |
Baby | +0.036 |
Neg logit contributions | |
ebra | -0.015 |
s | -0.014 |
opard | -0.013 |
gers | -0.013 |
ang | -0.013 |
Token | tidy |
Token ID | 43044 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
prise | +0.065 |
plug | +0.062 |
Acc | +0.062 |
bluff | +0.060 |
Katie | +0.060 |
Neg logit contributions | |
skills | -0.035 |
every | -0.035 |
ebra | -0.034 |
gers | -0.034 |
legs | -0.033 |
Token | up |
Token ID | 510 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
prise | +0.262 |
install | +0.244 |
Esk | +0.234 |
Acc | +0.230 |
Ethan | +0.228 |
Neg logit contributions | |
ebra | -0.177 |
s | -0.175 |
gers | -0.166 |
legs | -0.158 |
ang | -0.153 |
Token | your |
Token ID | 534 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
prise | +0.028 |
install | +0.026 |
Esk | +0.026 |
Ethan | +0.026 |
Acc | +0.025 |
Neg logit contributions | |
s | -0.017 |
ebra | -0.016 |
gers | -0.015 |
legs | -0.015 |
ites | -0.014 |
Token | room |
Token ID | 2119 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
prise | +0.037 |
Katie | +0.035 |
install | +0.035 |
Ethan | +0.034 |
Baby | +0.033 |
Neg logit contributions | |
ebra | -0.050 |
s | -0.047 |
gers | -0.046 |
opard | -0.046 |
ang | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
prise | +0.195 |
install | +0.187 |
Katie | +0.183 |
Ethan | +0.183 |
Baby | +0.181 |
Neg logit contributions | |
ebra | -0.095 |
s | -0.091 |
gers | -0.086 |
opard | -0.082 |
ang | -0.082 |
Token | You |
Token ID | 921 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
ebra | +0.001 |
gers | +0.001 |
legs | +0.001 |
ite | +0.001 |
opard | +0.001 |
Neg logit contributions | |
prise | -0.002 |
install | -0.002 |
Esk | -0.002 |
dessert | -0.002 |
dining | -0.002 |
Token | helped |
Token ID | 4193 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
s | +0.075 |
ebra | +0.073 |
gers | +0.066 |
legs | +0.066 |
ite | +0.065 |
Neg logit contributions | |
prise | -0.109 |
install | -0.099 |
Esk | -0.097 |
dining | -0.097 |
Katie | -0.097 |
Token | him |
Token ID | 683 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
prise | +0.077 |
dining | +0.070 |
Esk | +0.068 |
install | +0.068 |
Katie | +0.067 |
Neg logit contributions | |
s | -0.060 |
ebra | -0.057 |
legs | -0.055 |
gers | -0.054 |
arrows | -0.053 |
Token | clean |
Token ID | 3424 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
prise | +0.030 |
Katie | +0.028 |
Ethan | +0.027 |
dining | +0.027 |
Esk | +0.027 |
Neg logit contributions | |
s | -0.025 |
ebra | -0.023 |
legs | -0.022 |
skills | -0.022 |
arrows | -0.022 |
Token | up |
Token ID | 510 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
prise | +0.238 |
install | +0.225 |
Katie | +0.223 |
Ethan | +0.218 |
Baby | +0.216 |
Neg logit contributions | |
ebra | -0.217 |
s | -0.201 |
opard | -0.198 |
gers | -0.196 |
ang | -0.195 |
Token | the |
Token ID | 262 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
prise | +0.015 |
install | +0.014 |
Katie | +0.014 |
Ethan | +0.014 |
Esk | +0.014 |
Neg logit contributions | |
ebra | -0.011 |
s | -0.010 |
gers | -0.010 |
ang | -0.009 |
opard | -0.009 |
Token | mess |
Token ID | 2085 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
prise | +0.017 |
Katie | +0.016 |
install | +0.016 |
Ethan | +0.015 |
Esk | +0.015 |
Neg logit contributions | |
ebra | -0.015 |
legs | -0.014 |
s | -0.014 |
gers | -0.014 |
opard | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
prise | +0.276 |
install | +0.263 |
Katie | +0.261 |
Ethan | +0.256 |
Baby | +0.255 |
Neg logit contributions | |
ebra | -0.115 |
s | -0.109 |
gers | -0.100 |
opard | -0.098 |
ang | -0.098 |
Token | They |
Token ID | 1119 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
prise | +0.015 |
install | +0.014 |
Katie | +0.013 |
Esk | +0.013 |
dining | +0.013 |
Neg logit contributions | |
ebra | -0.010 |
s | -0.010 |
opard | -0.009 |
ang | -0.009 |
ites | -0.009 |
Token | used |
Token ID | 973 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
s | +0.008 |
ebra | +0.007 |
ite | +0.007 |
every | +0.007 |
legs | +0.007 |
Neg logit contributions | |
prise | -0.011 |
Katie | -0.010 |
Esk | -0.010 |
install | -0.010 |
dessert | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
s | +0.042 |
legs | +0.041 |
arrows | +0.041 |
clubs | +0.040 |
skills | +0.040 |
Neg logit contributions | |
prise | -0.063 |
install | -0.056 |
Katie | -0.056 |
dining | -0.055 |
Esk | -0.055 |
Token | bucket |
Token ID | 19236 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
s | +0.012 |
legs | +0.010 |
ebra | +0.010 |
ite | +0.010 |
opard | +0.010 |
Neg logit contributions | |
prise | -0.017 |
Esk | -0.017 |
Katie | -0.017 |
Ethan | -0.017 |
install | -0.017 |