Token | that |
Token ID | 326 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
icol | +0.040 |
opl | +0.038 |
former | +0.038 |
destination | +0.038 |
destinations | +0.036 |
Neg logit contributions | |
do | -0.014 |
I | -0.010 |
ily | -0.010 |
there | -0.010 |
did | -0.010 |
Token | they |
Token ID | 484 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
icol | +0.066 |
opl | +0.065 |
former | +0.063 |
destination | +0.062 |
destinations | +0.061 |
Neg logit contributions | |
do | -0.028 |
ily | -0.022 |
I | -0.021 |
there | -0.020 |
did | -0.020 |
Token | had |
Token ID | 550 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
icol | +0.117 |
former | +0.113 |
opl | +0.112 |
destination | +0.111 |
destinations | +0.107 |
Neg logit contributions | |
do | -0.054 |
I | -0.045 |
Tom | -0.044 |
ily | -0.043 |
kids | -0.043 |
Token | more |
Token ID | 517 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
icol | +0.179 |
opl | +0.173 |
achers | +0.168 |
former | +0.164 |
destination | +0.160 |
Neg logit contributions | |
do | -0.066 |
did | -0.055 |
Tom | -0.054 |
kids | -0.053 |
there | -0.052 |
Token | in |
Token ID | 287 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
do | +0.025 |
there | +0.022 |
kids | +0.021 |
did | +0.020 |
curious | +0.019 |
Neg logit contributions | |
icol | -0.054 |
achers | -0.051 |
destination | -0.050 |
opl | -0.049 |
ric | -0.049 |
Token | common |
Token ID | 2219 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
do | +0.036 |
there | +0.033 |
Tom | +0.032 |
kids | +0.030 |
did | +0.029 |
Neg logit contributions | |
icol | -0.053 |
opl | -0.048 |
achers | -0.046 |
former | -0.045 |
destination | -0.044 |
Token | than |
Token ID | 621 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
icol | +0.720 |
opl | +0.685 |
former | +0.681 |
destination | +0.672 |
achers | +0.652 |
Neg logit contributions | |
do | -0.238 |
I | -0.172 |
there | -0.171 |
did | -0.170 |
Tom | -0.170 |
Token | they |
Token ID | 484 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
icol | +0.183 |
opl | +0.173 |
former | +0.169 |
destination | +0.166 |
achers | +0.164 |
Neg logit contributions | |
do | -0.084 |
Tom | -0.068 |
there | -0.068 |
I | -0.067 |
did | -0.066 |
Token | thought |
Token ID | 1807 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
icol | +0.109 |
opl | +0.107 |
destination | +0.106 |
former | +0.106 |
destinations | +0.102 |
Neg logit contributions | |
do | -0.054 |
I | -0.046 |
ily | -0.045 |
Tom | -0.044 |
kids | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
do | +0.029 |
did | +0.021 |
kids | +0.021 |
I | +0.021 |
curious | +0.021 |
Neg logit contributions | |
icol | -0.073 |
opl | -0.071 |
destination | -0.069 |
former | -0.069 |
destinations | -0.066 |
Token | They |
Token ID | 1119 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
icol | +0.052 |
opl | +0.050 |
destination | +0.049 |
former | +0.049 |
achers | +0.049 |
Neg logit contributions | |
do | -0.023 |
Tom | -0.021 |
I | -0.020 |
there | -0.019 |
ily | -0.019 |
Token | They |
Token ID | 1119 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
icol | +0.021 |
opl | +0.019 |
former | +0.019 |
destination | +0.019 |
achers | +0.018 |
Neg logit contributions | |
do | -0.010 |
there | -0.008 |
I | -0.008 |
did | -0.008 |
Tom | -0.008 |
Token | have |
Token ID | 423 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
icol | +0.095 |
opl | +0.093 |
former | +0.092 |
destination | +0.092 |
destinations | +0.088 |
Neg logit contributions | |
do | -0.029 |
oh | -0.026 |
there | -0.026 |
I | -0.025 |
ily | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
icol | +0.035 |
opl | +0.034 |
former | +0.033 |
achers | +0.032 |
destination | +0.032 |
Neg logit contributions | |
do | -0.020 |
did | -0.016 |
Tom | -0.016 |
there | -0.016 |
kids | -0.016 |
Token | lot |
Token ID | 1256 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
icol | +0.029 |
opl | +0.029 |
achers | +0.029 |
en | +0.028 |
former | +0.028 |
Neg logit contributions | |
do | -0.018 |
did | -0.014 |
kids | -0.014 |
Tom | -0.014 |
there | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
icol | +0.309 |
former | +0.288 |
destination | +0.287 |
opl | +0.282 |
ric | +0.276 |
Neg logit contributions | |
do | -0.089 |
ily | -0.069 |
Tom | -0.067 |
there | -0.066 |
kids | -0.064 |
Token | common |
Token ID | 2219 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
do | +0.036 |
Tom | +0.029 |
there | +0.029 |
kids | +0.028 |
I | +0.028 |
Neg logit contributions | |
icol | -0.076 |
opl | -0.071 |
former | -0.071 |
destination | -0.069 |
achers | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
icol | +0.645 |
opl | +0.627 |
destination | +0.622 |
former | +0.621 |
destinations | +0.599 |
Neg logit contributions | |
do | -0.270 |
I | -0.222 |
ily | -0.210 |
Tom | -0.205 |
oh | -0.204 |
Token | They |
Token ID | 1119 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
icol | +0.011 |
opl | +0.011 |
former | +0.010 |
destination | +0.010 |
destinations | +0.010 |
Neg logit contributions | |
do | -0.006 |
did | -0.005 |
there | -0.005 |
kids | -0.005 |
I | -0.005 |
Token | become |
Token ID | 1716 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
icol | +0.084 |
opl | +0.082 |
former | +0.081 |
destination | +0.081 |
destinations | +0.078 |
Neg logit contributions | |
do | -0.026 |
oh | -0.025 |
there | -0.023 |
ily | -0.022 |
I | -0.022 |
Token | friends |
Token ID | 2460 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
icol | +0.107 |
opl | +0.102 |
former | +0.099 |
destination | +0.098 |
achers | +0.097 |
Neg logit contributions | |
do | -0.046 |
there | -0.037 |
kids | -0.037 |
Tom | -0.036 |
did | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
opl | +0.047 |
icol | +0.046 |
destination | +0.045 |
en | +0.044 |
former | +0.044 |
Neg logit contributions | |
do | -0.024 |
oh | -0.020 |
ily | -0.019 |
did | -0.018 |
don | -0.018 |
Token | that |
Token ID | 326 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
do | +0.006 |
there | +0.005 |
Tom | +0.004 |
I | +0.004 |
did | +0.004 |
Neg logit contributions | |
icol | -0.029 |
opl | -0.027 |
former | -0.027 |
destination | -0.027 |
achers | -0.027 |
Token | they |
Token ID | 484 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
icol | +0.064 |
former | +0.063 |
opl | +0.063 |
destination | +0.061 |
conflicts | +0.060 |
Neg logit contributions | |
do | -0.026 |
ily | -0.021 |
did | -0.020 |
I | -0.019 |
kids | -0.019 |
Token | had |
Token ID | 550 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
icol | +0.104 |
opl | +0.101 |
destination | +0.101 |
former | +0.101 |
destinations | +0.097 |
Neg logit contributions | |
do | -0.055 |
Tom | -0.048 |
I | -0.047 |
ily | -0.046 |
kids | -0.046 |
Token | more |
Token ID | 517 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
icol | +0.153 |
opl | +0.144 |
former | +0.138 |
achers | +0.136 |
destination | +0.135 |
Neg logit contributions | |
do | -0.081 |
did | -0.070 |
there | -0.066 |
Tom | -0.066 |
kids | -0.065 |
Token | in |
Token ID | 287 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
do | +0.026 |
there | +0.022 |
did | +0.021 |
kids | +0.021 |
curious | +0.021 |
Neg logit contributions | |
icol | -0.045 |
destination | -0.041 |
achers | -0.040 |
opl | -0.040 |
former | -0.039 |
Token | common |
Token ID | 2219 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
do | +0.032 |
there | +0.027 |
Tom | +0.026 |
kids | +0.026 |
did | +0.026 |
Neg logit contributions | |
icol | -0.046 |
opl | -0.042 |
achers | -0.041 |
former | -0.040 |
destination | -0.040 |
Token | than |
Token ID | 621 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
icol | +0.723 |
opl | +0.680 |
former | +0.673 |
destination | +0.664 |
achers | +0.651 |
Neg logit contributions | |
do | -0.253 |
there | -0.192 |
did | -0.188 |
kids | -0.183 |
Tom | -0.182 |
Token | they |
Token ID | 484 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
icol | +0.179 |
former | +0.169 |
opl | +0.169 |
destination | +0.166 |
destinations | +0.159 |
Neg logit contributions | |
do | -0.094 |
I | -0.075 |
there | -0.075 |
did | -0.074 |
ily | -0.074 |
Token | thought |
Token ID | 1807 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
icol | +0.109 |
opl | +0.107 |
former | +0.105 |
destination | +0.105 |
achers | +0.101 |
Neg logit contributions | |
do | -0.053 |
I | -0.044 |
ily | -0.044 |
Tom | -0.044 |
kids | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
do | +0.028 |
did | +0.021 |
kids | +0.021 |
Tom | +0.021 |
I | +0.021 |
Neg logit contributions | |
icol | -0.072 |
opl | -0.070 |
destination | -0.068 |
former | -0.068 |
achers | -0.065 |
Token | They |
Token ID | 1119 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
icol | +0.054 |
opl | +0.052 |
former | +0.051 |
destination | +0.051 |
achers | +0.050 |
Neg logit contributions | |
do | -0.028 |
Tom | -0.024 |
I | -0.024 |
there | -0.023 |
ily | -0.023 |
Token | they |
Token ID | 484 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
icol | +0.054 |
former | +0.053 |
destination | +0.053 |
opl | +0.052 |
destinations | +0.051 |
Neg logit contributions | |
do | -0.024 |
ily | -0.019 |
I | -0.018 |
did | -0.018 |
curious | -0.017 |
Token | had |
Token ID | 550 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
icol | +0.106 |
opl | +0.100 |
former | +0.100 |
destination | +0.099 |
achers | +0.096 |
Neg logit contributions | |
do | -0.046 |
I | -0.036 |
Tom | -0.036 |
there | -0.036 |
kids | -0.035 |
Token | many |
Token ID | 867 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
icol | +0.139 |
opl | +0.133 |
former | +0.127 |
achers | +0.126 |
destination | +0.123 |
Neg logit contributions | |
do | -0.055 |
Tom | -0.045 |
there | -0.044 |
did | -0.044 |
kids | -0.044 |
Token | things |
Token ID | 1243 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
do | +0.071 |
kids | +0.061 |
there | +0.055 |
did | +0.054 |
children | +0.052 |
Neg logit contributions | |
icol | -0.169 |
opl | -0.152 |
former | -0.151 |
destination | -0.149 |
ric | -0.149 |
Token | in |
Token ID | 287 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
icol | +0.059 |
opl | +0.056 |
former | +0.056 |
destination | +0.055 |
achers | +0.054 |
Neg logit contributions | |
do | -0.023 |
there | -0.018 |
I | -0.017 |
did | -0.017 |
Tom | -0.017 |
Token | common |
Token ID | 2219 |
Feature activation | +5.90e+00 |
Pos logit contributions | |
do | +0.069 |
Tom | +0.065 |
there | +0.065 |
kids | +0.062 |
I | +0.061 |
Neg logit contributions | |
icol | -0.048 |
opl | -0.041 |
former | -0.040 |
achers | -0.038 |
ric | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
icol | +0.711 |
opl | +0.676 |
former | +0.671 |
destination | +0.663 |
achers | +0.643 |
Neg logit contributions | |
do | -0.232 |
there | -0.167 |
I | -0.167 |
did | -0.166 |
Tom | -0.165 |
Token | They |
Token ID | 1119 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
icol | +0.023 |
opl | +0.022 |
former | +0.022 |
destination | +0.022 |
achers | +0.021 |
Neg logit contributions | |
do | -0.011 |
Tom | -0.010 |
I | -0.009 |
there | -0.009 |
kids | -0.009 |
Token | started |
Token ID | 2067 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
icol | +0.077 |
former | +0.074 |
destination | +0.073 |
opl | +0.072 |
destinations | +0.070 |
Neg logit contributions | |
do | -0.040 |
I | -0.034 |
you | -0.033 |
ily | -0.032 |
there | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
icol | +0.030 |
opl | +0.029 |
former | +0.028 |
achers | +0.027 |
destination | +0.027 |
Neg logit contributions | |
do | -0.011 |
there | -0.009 |
Tom | -0.008 |
curious | -0.008 |
kids | -0.008 |
Token | have |
Token ID | 423 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
icol | +0.066 |
former | +0.063 |
opl | +0.063 |
destination | +0.062 |
destinations | +0.060 |
Neg logit contributions | |
do | -0.034 |
I | -0.028 |
there | -0.028 |
ily | -0.028 |
Tom | -0.028 |
Token | No |
Token ID | 2949 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
icol | +0.027 |
opl | +0.026 |
former | +0.026 |
destination | +0.024 |
destinations | +0.024 |
Neg logit contributions | |
do | -0.020 |
there | -0.017 |
kids | -0.017 |
Tom | -0.016 |
did | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
do | +0.014 |
there | +0.011 |
ily | +0.011 |
I | +0.010 |
did | +0.010 |
Neg logit contributions | |
icol | -0.046 |
opl | -0.044 |
destination | -0.044 |
former | -0.043 |
achers | -0.042 |
Token | that |
Token ID | 326 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
icol | +0.002 |
destination | +0.002 |
opl | +0.002 |
brand | +0.002 |
Wed | +0.002 |
Neg logit contributions | |
do | -0.001 |
he | -0.001 |
ily | -0.001 |
curious | -0.001 |
lock | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
icol | +0.027 |
opl | +0.025 |
former | +0.025 |
destination | +0.024 |
achers | +0.024 |
Neg logit contributions | |
do | -0.013 |
ily | -0.011 |
there | -0.011 |
Tom | -0.011 |
I | -0.011 |
Token | too |
Token ID | 1165 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
icol | +0.099 |
former | +0.093 |
opl | +0.093 |
destination | +0.091 |
achers | +0.091 |
Neg logit contributions | |
do | -0.035 |
Tom | -0.029 |
I | -0.028 |
there | -0.027 |
you | -0.027 |
Token | common |
Token ID | 2219 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
do | +0.029 |
there | +0.023 |
I | +0.023 |
did | +0.023 |
Tom | +0.023 |
Neg logit contributions | |
icol | -0.062 |
opl | -0.058 |
former | -0.058 |
destination | -0.057 |
achers | -0.055 |
Token | ," |
Token ID | 553 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
icol | +0.557 |
opl | +0.553 |
destination | +0.531 |
en | +0.529 |
conflicts | +0.515 |
Neg logit contributions | |
do | -0.290 |
oh | -0.255 |
curious | -0.229 |
kids | -0.227 |
ily | -0.226 |
Token | Anna |
Token ID | 11735 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
do | +0.042 |
did | +0.025 |
there | +0.025 |
don | +0.024 |
oh | +0.024 |
Neg logit contributions | |
icol | -0.173 |
former | -0.167 |
destination | -0.164 |
opl | -0.161 |
lifelong | -0.158 |
Token | says |
Token ID | 1139 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
icol | +0.003 |
opl | +0.003 |
former | +0.003 |
destination | +0.003 |
achers | +0.003 |
Neg logit contributions | |
do | -0.002 |
there | -0.001 |
I | -0.001 |
did | -0.001 |
Tom | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
do | +0.059 |
oh | +0.051 |
kids | +0.050 |
did | +0.050 |
I | +0.048 |
Neg logit contributions | |
icol | -0.085 |
destination | -0.080 |
en | -0.078 |
fault | -0.078 |
alks | -0.077 |
Token | " |
Token ID | 366 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
icol | +0.036 |
opl | +0.034 |
former | +0.033 |
destination | +0.033 |
achers | +0.032 |
Neg logit contributions | |
do | -0.016 |
did | -0.012 |
kids | -0.012 |
there | -0.012 |
I | -0.012 |
Token | meant |
Token ID | 4001 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
do | +0.058 |
did | +0.048 |
Tom | +0.043 |
there | +0.043 |
ily | +0.041 |
Neg logit contributions | |
icol | -0.156 |
opl | -0.146 |
former | -0.144 |
destination | -0.142 |
achers | -0.140 |
Token | something |
Token ID | 1223 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
do | +0.013 |
Tom | +0.010 |
there | +0.010 |
I | +0.010 |
did | +0.009 |
Neg logit contributions | |
icol | -0.042 |
opl | -0.040 |
former | -0.039 |
destination | -0.038 |
achers | -0.038 |
Token | that |
Token ID | 326 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
icol | +0.100 |
opl | +0.095 |
former | +0.095 |
destination | +0.092 |
achers | +0.091 |
Neg logit contributions | |
do | -0.041 |
there | -0.032 |
did | -0.032 |
I | -0.032 |
Tom | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
icol | +0.041 |
opl | +0.039 |
former | +0.039 |
destination | +0.038 |
achers | +0.037 |
Neg logit contributions | |
do | -0.021 |
there | -0.017 |
I | -0.017 |
did | -0.016 |
Tom | -0.016 |
Token | not |
Token ID | 407 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
icol | +0.150 |
opl | +0.140 |
achers | +0.138 |
former | +0.136 |
destination | +0.133 |
Neg logit contributions | |
do | -0.059 |
there | -0.050 |
Tom | -0.050 |
did | -0.047 |
curious | -0.045 |
Token | common |
Token ID | 2219 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
do | +0.042 |
there | +0.032 |
I | +0.031 |
did | +0.031 |
Tom | +0.031 |
Neg logit contributions | |
icol | -0.116 |
opl | -0.111 |
former | -0.110 |
destination | -0.108 |
achers | -0.105 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
icol | +0.672 |
opl | +0.649 |
former | +0.639 |
destination | +0.634 |
achers | +0.613 |
Neg logit contributions | |
do | -0.241 |
I | -0.178 |
did | -0.176 |
Tom | -0.174 |
there | -0.174 |
Token | something |
Token ID | 1223 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
icol | +0.014 |
opl | +0.013 |
former | +0.013 |
destination | +0.013 |
achers | +0.012 |
Neg logit contributions | |
do | -0.005 |
there | -0.004 |
I | -0.004 |
did | -0.004 |
ily | -0.004 |
Token | that |
Token ID | 326 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
icol | +0.101 |
former | +0.095 |
opl | +0.095 |
destination | +0.093 |
achers | +0.092 |
Neg logit contributions | |
do | -0.037 |
did | -0.028 |
there | -0.028 |
I | -0.027 |
Tom | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
icol | +0.041 |
opl | +0.039 |
former | +0.038 |
destination | +0.038 |
achers | +0.037 |
Neg logit contributions | |
do | -0.020 |
did | -0.016 |
there | -0.016 |
Tom | -0.016 |
I | -0.016 |
Token | special |
Token ID | 2041 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
icol | +0.141 |
opl | +0.131 |
achers | +0.129 |
former | +0.126 |
destination | +0.124 |
Neg logit contributions | |
do | -0.063 |
there | -0.054 |
Tom | -0.053 |
did | -0.051 |
curious | -0.049 |
Token | they |
Token ID | 484 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
icol | +0.132 |
opl | +0.126 |
former | +0.125 |
destination | +0.122 |
achers | +0.120 |
Neg logit contributions | |
do | -0.037 |
there | -0.026 |
Tom | -0.025 |
did | -0.025 |
I | -0.024 |
Token | had |
Token ID | 550 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
icol | +0.098 |
opl | +0.092 |
former | +0.092 |
destination | +0.091 |
achers | +0.087 |
Neg logit contributions | |
do | -0.055 |
I | -0.045 |
there | -0.044 |
Tom | -0.044 |
kids | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
icol | +0.154 |
opl | +0.150 |
achers | +0.143 |
former | +0.140 |
acking | +0.133 |
Neg logit contributions | |
do | -0.061 |
there | -0.055 |
did | -0.054 |
Tom | -0.053 |
kids | -0.050 |
Token | lot |
Token ID | 1256 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
opl | +0.029 |
ays | +0.028 |
alled | +0.028 |
achers | +0.027 |
icol | +0.027 |
Neg logit contributions | |
do | -0.016 |
happy | -0.013 |
there | -0.013 |
did | -0.012 |
little | -0.012 |
Token | in |
Token ID | 287 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
icol | +0.326 |
former | +0.303 |
destination | +0.294 |
opl | +0.292 |
achers | +0.289 |
Neg logit contributions | |
do | -0.057 |
there | -0.046 |
ily | -0.045 |
Tom | -0.038 |
kids | -0.033 |
Token | common |
Token ID | 2219 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
do | +0.029 |
Tom | +0.026 |
there | +0.026 |
kids | +0.022 |
Anna | +0.020 |
Neg logit contributions | |
icol | -0.085 |
opl | -0.080 |
former | -0.079 |
achers | -0.077 |
ric | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
icol | +0.674 |
opl | +0.641 |
former | +0.639 |
destination | +0.638 |
destinations | +0.613 |
Neg logit contributions | |
do | -0.240 |
I | -0.187 |
Tom | -0.177 |
ily | -0.177 |
did | -0.176 |
Token | They |
Token ID | 1119 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
icol | +0.044 |
opl | +0.043 |
former | +0.041 |
destination | +0.041 |
achers | +0.041 |
Neg logit contributions | |
do | -0.021 |
Tom | -0.019 |
there | -0.017 |
ily | -0.017 |
I | -0.017 |
Token | liked |
Token ID | 8288 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
icol | +0.085 |
former | +0.080 |
destination | +0.079 |
opl | +0.078 |
destinations | +0.075 |
Neg logit contributions | |
do | -0.051 |
I | -0.044 |
there | -0.042 |
you | -0.042 |
ily | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +1.20e-03 |
Pos logit contributions | |
do | +0.038 |
Tom | +0.035 |
there | +0.033 |
kids | +0.031 |
you | +0.029 |
Neg logit contributions | |
icol | -0.094 |
opl | -0.092 |
achers | -0.090 |
former | -0.090 |
destination | -0.087 |
Token | same |
Token ID | 976 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
icol | +0.000 |
opl | +0.000 |
achers | +0.000 |
former | +0.000 |
irs | +0.000 |
Neg logit contributions | |
do | -0.000 |
kids | -0.000 |
there | -0.000 |
did | -0.000 |
curious | -0.000 |
Token | you |
Token ID | 345 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ily | +0.002 |
do | +0.002 |
Tom | +0.001 |
did | +0.001 |
oh | +0.001 |
Neg logit contributions | |
former | -0.007 |
destination | -0.007 |
icol | -0.007 |
destinations | -0.007 |
opl | -0.007 |
Token | may |
Token ID | 743 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
do | +0.065 |
Tom | +0.058 |
ily | +0.057 |
kids | +0.056 |
there | +0.056 |
Neg logit contributions | |
icol | -0.095 |
destination | -0.092 |
former | -0.092 |
opl | -0.091 |
destinations | -0.087 |
Token | find |
Token ID | 1064 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
icol | +0.100 |
opl | +0.094 |
former | +0.094 |
destination | +0.092 |
achers | +0.090 |
Neg logit contributions | |
do | -0.036 |
I | -0.027 |
there | -0.027 |
did | -0.026 |
Tom | -0.026 |
Token | something |
Token ID | 1223 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
do | +0.033 |
there | +0.027 |
I | +0.027 |
you | +0.026 |
kids | +0.026 |
Neg logit contributions | |
icol | -0.073 |
opl | -0.068 |
former | -0.067 |
destination | -0.066 |
achers | -0.065 |
Token | in |
Token ID | 287 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
icol | +0.087 |
opl | +0.082 |
former | +0.080 |
destination | +0.078 |
achers | +0.078 |
Neg logit contributions | |
do | -0.044 |
there | -0.036 |
I | -0.036 |
you | -0.035 |
did | -0.034 |
Token | common |
Token ID | 2219 |
Feature activation | +5.80e+00 |
Pos logit contributions | |
do | +0.037 |
there | +0.029 |
I | +0.028 |
Tom | +0.028 |
kids | +0.028 |
Neg logit contributions | |
icol | -0.086 |
opl | -0.080 |
former | -0.079 |
destination | -0.078 |
achers | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
icol | +0.691 |
opl | +0.655 |
former | +0.650 |
destination | +0.641 |
achers | +0.623 |
Neg logit contributions | |
do | -0.239 |
there | -0.177 |
I | -0.175 |
did | -0.174 |
Tom | -0.173 |
Token | This |
Token ID | 770 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
do | +0.015 |
did | +0.013 |
there | +0.012 |
kids | +0.012 |
ily | +0.012 |
Neg logit contributions | |
icol | -0.024 |
opl | -0.024 |
former | -0.023 |
destination | -0.023 |
ric | -0.022 |
Token | can |
Token ID | 460 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
icol | +0.048 |
opl | +0.045 |
former | +0.045 |
destination | +0.044 |
achers | +0.042 |
Neg logit contributions | |
do | -0.035 |
there | -0.029 |
I | -0.029 |
did | -0.029 |
Tom | -0.029 |
Token | make |
Token ID | 787 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
destination | +0.099 |
former | +0.099 |
opl | +0.097 |
icol | +0.094 |
en | +0.092 |
Neg logit contributions | |
do | -0.032 |
ily | -0.032 |
Tom | -0.031 |
curious | -0.030 |
did | -0.029 |
Token | even |
Token ID | 772 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
icol | +0.061 |
former | +0.060 |
opl | +0.060 |
destination | +0.059 |
destinations | +0.057 |
Neg logit contributions | |
do | -0.028 |
did | -0.023 |
ily | -0.023 |
I | -0.022 |
Tom | -0.022 |
Token | They |
Token ID | 1119 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
icol | +0.011 |
opl | +0.010 |
former | +0.010 |
destination | +0.010 |
achers | +0.010 |
Neg logit contributions | |
do | -0.006 |
Tom | -0.005 |
there | -0.005 |
I | -0.005 |
did | -0.005 |
Token | have |
Token ID | 423 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
icol | +0.079 |
destination | +0.078 |
former | +0.078 |
opl | +0.076 |
destinations | +0.074 |
Neg logit contributions | |
do | -0.030 |
oh | -0.028 |
ily | -0.027 |
there | -0.026 |
I | -0.026 |
Token | many |
Token ID | 867 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
icol | +0.019 |
opl | +0.018 |
achers | +0.017 |
former | +0.017 |
destination | +0.017 |
Neg logit contributions | |
do | -0.008 |
there | -0.007 |
did | -0.007 |
Tom | -0.007 |
kids | -0.007 |
Token | things |
Token ID | 1243 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
do | +0.093 |
kids | +0.080 |
there | +0.076 |
did | +0.075 |
curious | +0.074 |
Neg logit contributions | |
icol | -0.160 |
opl | -0.145 |
former | -0.144 |
destination | -0.141 |
achers | -0.140 |
Token | in |
Token ID | 287 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
icol | +0.048 |
opl | +0.046 |
former | +0.046 |
destination | +0.044 |
achers | +0.044 |
Neg logit contributions | |
do | -0.018 |
there | -0.014 |
I | -0.014 |
Tom | -0.014 |
did | -0.013 |
Token | common |
Token ID | 2219 |
Feature activation | +5.80e+00 |
Pos logit contributions | |
do | +0.067 |
there | +0.060 |
Tom | +0.060 |
kids | +0.058 |
I | +0.058 |
Neg logit contributions | |
icol | -0.057 |
opl | -0.051 |
former | -0.050 |
achers | -0.048 |
destination | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
icol | +0.689 |
opl | +0.656 |
former | +0.651 |
destination | +0.644 |
achers | +0.623 |
Neg logit contributions | |
do | -0.234 |
I | -0.173 |
there | -0.171 |
did | -0.169 |
Tom | -0.169 |
Token | They |
Token ID | 1119 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
icol | +0.005 |
opl | +0.005 |
former | +0.005 |
destination | +0.005 |
achers | +0.005 |
Neg logit contributions | |
do | -0.003 |
there | -0.003 |
Tom | -0.003 |
I | -0.003 |
did | -0.003 |
Token | like |
Token ID | 588 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
icol | +0.072 |
former | +0.070 |
destination | +0.070 |
opl | +0.069 |
destinations | +0.067 |
Neg logit contributions | |
do | -0.026 |
oh | -0.025 |
ily | -0.024 |
there | -0.023 |
I | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
icol | +0.115 |
opl | +0.108 |
former | +0.107 |
destination | +0.105 |
achers | +0.102 |
Neg logit contributions | |
do | -0.067 |
Tom | -0.055 |
there | -0.055 |
kids | -0.054 |
I | -0.054 |
Token | same |
Token ID | 976 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
do | +0.004 |
there | +0.004 |
I | +0.004 |
did | +0.004 |
Tom | +0.004 |
Neg logit contributions | |
icol | -0.007 |
opl | -0.006 |
former | -0.006 |
destination | -0.006 |
achers | -0.006 |
Token | in |
Token ID | 259 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
opl | +0.145 |
icol | +0.135 |
ric | +0.135 |
achers | +0.135 |
former | +0.134 |
Neg logit contributions | |
do | -0.156 |
Tom | -0.142 |
I | -0.133 |
did | -0.132 |
kids | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
do | +0.086 |
Tom | +0.068 |
there | +0.067 |
did | +0.067 |
I | +0.067 |
Neg logit contributions | |
icol | -0.195 |
opl | -0.188 |
former | -0.185 |
destination | -0.182 |
achers | -0.177 |
Token | They |
Token ID | 1119 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
do | +0.005 |
there | +0.004 |
did | +0.004 |
Tom | +0.004 |
kids | +0.004 |
Neg logit contributions | |
icol | -0.010 |
opl | -0.009 |
former | -0.009 |
destination | -0.009 |
achers | -0.009 |
Token | are |
Token ID | 389 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
icol | +0.073 |
former | +0.070 |
opl | +0.070 |
destination | +0.069 |
destinations | +0.066 |
Neg logit contributions | |
do | -0.034 |
Tom | -0.028 |
ily | -0.028 |
there | -0.028 |
kids | -0.027 |
Token | very |
Token ID | 845 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
do | +0.081 |
there | +0.068 |
curious | +0.066 |
you | +0.064 |
I | +0.064 |
Neg logit contributions | |
icol | -0.211 |
achers | -0.193 |
opl | -0.193 |
destination | -0.191 |
former | -0.191 |
Token | common |
Token ID | 2219 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
icol | +0.105 |
opl | +0.099 |
former | +0.098 |
destination | +0.097 |
achers | +0.094 |
Neg logit contributions | |
do | -0.044 |
there | -0.034 |
I | -0.034 |
did | -0.034 |
Tom | -0.034 |
Token | in |
Token ID | 287 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
icol | +0.646 |
opl | +0.619 |
former | +0.614 |
destination | +0.607 |
destinations | +0.587 |
Neg logit contributions | |
do | -0.252 |
ily | -0.185 |
Tom | -0.185 |
did | -0.183 |
I | -0.178 |
Token | this |
Token ID | 428 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
do | +0.038 |
there | +0.030 |
I | +0.030 |
you | +0.029 |
Tom | +0.029 |
Neg logit contributions | |
icol | -0.088 |
opl | -0.080 |
former | -0.080 |
destination | -0.079 |
achers | -0.078 |
Token | area |
Token ID | 1989 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
icol | +0.026 |
opl | +0.024 |
achers | +0.023 |
irs | +0.023 |
former | +0.023 |
Neg logit contributions | |
do | -0.018 |
there | -0.016 |
did | -0.015 |
I | -0.015 |
you | -0.015 |
Token | ." |
Token ID | 526 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
do | +0.066 |
Tom | +0.050 |
did | +0.049 |
kids | +0.049 |
ily | +0.049 |
Neg logit contributions | |
icol | -0.163 |
opl | -0.159 |
former | -0.158 |
destination | -0.157 |
destinations | -0.151 |
Token | The |
Token ID | 383 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
do | +0.025 |
did | +0.020 |
there | +0.019 |
curious | +0.019 |
ily | +0.019 |
Neg logit contributions | |
icol | -0.046 |
opl | -0.043 |
former | -0.043 |
destination | -0.042 |
alks | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
icol | +0.370 |
opl | +0.349 |
former | +0.339 |
destination | +0.333 |
achers | +0.332 |
Neg logit contributions | |
do | -0.102 |
I | -0.078 |
you | -0.072 |
there | -0.070 |
kids | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | -9.17e-02 |
Pos logit contributions | |
do | +0.001 |
ily | +0.001 |
did | +0.001 |
kids | +0.001 |
Tom | +0.001 |
Neg logit contributions | |
icol | -0.003 |
former | -0.002 |
opl | -0.002 |
destination | -0.002 |
destinations | -0.002 |
Token | some |
Token ID | 617 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
do | +0.003 |
ily | +0.003 |
kids | +0.003 |
Tom | +0.003 |
did | +0.003 |
Neg logit contributions | |
icol | -0.010 |
former | -0.010 |
destination | -0.010 |
opl | -0.009 |
destinations | -0.009 |
Token | are |
Token ID | 389 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
do | +0.012 |
I | +0.009 |
there | +0.009 |
did | +0.009 |
Tom | +0.009 |
Neg logit contributions | |
icol | -0.027 |
opl | -0.026 |
former | -0.026 |
destination | -0.025 |
achers | -0.025 |
Token | very |
Token ID | 845 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
do | +0.086 |
there | +0.072 |
I | +0.068 |
did | +0.066 |
you | +0.066 |
Neg logit contributions | |
icol | -0.203 |
opl | -0.188 |
achers | -0.181 |
destination | -0.177 |
former | -0.176 |
Token | common |
Token ID | 2219 |
Feature activation | +5.77e+00 |
Pos logit contributions | |
icol | +0.099 |
opl | +0.094 |
former | +0.090 |
destination | +0.090 |
achers | +0.089 |
Neg logit contributions | |
do | -0.058 |
there | -0.048 |
I | -0.048 |
did | -0.047 |
you | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
icol | +0.654 |
former | +0.624 |
opl | +0.622 |
destination | +0.616 |
destinations | +0.594 |
Neg logit contributions | |
do | -0.246 |
Tom | -0.184 |
did | -0.182 |
ily | -0.181 |
I | -0.176 |
Token | useful |
Token ID | 4465 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
do | +0.003 |
ily | +0.003 |
Tom | +0.003 |
there | +0.003 |
did | +0.002 |
Neg logit contributions | |
icol | -0.008 |
former | -0.007 |
opl | -0.007 |
destination | -0.007 |
destinations | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
icol | +0.347 |
opl | +0.328 |
former | +0.321 |
achers | +0.314 |
destination | +0.314 |
Neg logit contributions | |
do | -0.094 |
I | -0.069 |
there | -0.066 |
kids | -0.065 |
you | -0.064 |
Token | This |
Token ID | 770 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
do | +0.011 |
did | +0.009 |
there | +0.009 |
kids | +0.009 |
ily | +0.009 |
Neg logit contributions | |
icol | -0.016 |
opl | -0.015 |
former | -0.014 |
destination | -0.014 |
ric | -0.014 |
Token | one |
Token ID | 530 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
icol | +0.040 |
opl | +0.038 |
former | +0.037 |
destination | +0.036 |
achers | +0.035 |
Neg logit contributions | |
do | -0.027 |
there | -0.023 |
I | -0.023 |
did | -0.023 |
kids | -0.022 |
Token | but |
Token ID | 475 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
do | +0.004 |
ily | +0.004 |
did | +0.003 |
there | +0.003 |
kids | +0.003 |
Neg logit contributions | |
icol | -0.011 |
destination | -0.011 |
former | -0.011 |
opl | -0.010 |
en | -0.010 |
Token | now |
Token ID | 783 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
destination | +0.084 |
former | +0.082 |
icol | +0.082 |
en | +0.079 |
ric | +0.078 |
Neg logit contributions | |
ily | -0.023 |
do | -0.020 |
kids | -0.017 |
curious | -0.017 |
Tom | -0.016 |
Token | you |
Token ID | 345 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
do | +0.053 |
ily | +0.051 |
curious | +0.038 |
did | +0.036 |
kids | +0.035 |
Neg logit contributions | |
icol | -0.227 |
destination | -0.221 |
former | -0.214 |
en | -0.210 |
opl | -0.209 |
Token | need |
Token ID | 761 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
do | +0.063 |
Tom | +0.054 |
ily | +0.053 |
there | +0.053 |
kids | +0.053 |
Neg logit contributions | |
icol | -0.104 |
former | -0.100 |
destination | -0.099 |
opl | -0.099 |
achers | -0.094 |
Token | to |
Token ID | 284 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
icol | +0.151 |
opl | +0.145 |
former | +0.139 |
destination | +0.136 |
achers | +0.134 |
Neg logit contributions | |
do | -0.070 |
I | -0.059 |
you | -0.058 |
there | -0.058 |
Tom | -0.054 |
Token | common |
Token ID | 2219 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
icol | +0.051 |
former | +0.051 |
destination | +0.050 |
opl | +0.049 |
en | +0.048 |
Neg logit contributions | |
do | -0.020 |
ily | -0.020 |
there | -0.019 |
Tom | -0.019 |
I | -0.018 |
Token | down |
Token ID | 866 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
icol | +0.650 |
opl | +0.616 |
former | +0.607 |
destination | +0.593 |
achers | +0.582 |
Neg logit contributions | |
do | -0.287 |
there | -0.231 |
I | -0.227 |
Tom | -0.224 |
kids | -0.222 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
do | +0.012 |
there | +0.009 |
I | +0.009 |
Tom | +0.009 |
did | +0.009 |
Neg logit contributions | |
icol | -0.033 |
opl | -0.031 |
former | -0.031 |
destination | -0.030 |
achers | -0.029 |
Token | It |
Token ID | 632 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
do | +0.011 |
did | +0.009 |
there | +0.009 |
kids | +0.009 |
ily | +0.008 |
Neg logit contributions | |
icol | -0.019 |
opl | -0.018 |
former | -0.018 |
destination | -0.017 |
achers | -0.016 |
Token | looks |
Token ID | 3073 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
do | +0.068 |
there | +0.054 |
Tom | +0.054 |
I | +0.054 |
did | +0.054 |
Neg logit contributions | |
icol | -0.130 |
opl | -0.123 |
former | -0.122 |
destination | -0.120 |
achers | -0.116 |
Token | to |
Token ID | 284 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
icol | +0.089 |
opl | +0.089 |
achers | +0.086 |
ric | +0.084 |
alks | +0.083 |
Neg logit contributions | |
do | -0.034 |
there | -0.029 |
curious | -0.027 |
did | -0.027 |
you | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
icol | +0.386 |
opl | +0.364 |
former | +0.352 |
achers | +0.349 |
destination | +0.344 |
Neg logit contributions | |
do | -0.077 |
there | -0.047 |
I | -0.047 |
kids | -0.044 |
did | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
do | +0.006 |
I | +0.004 |
there | +0.004 |
did | +0.004 |
Tom | +0.004 |
Neg logit contributions | |
icol | -0.014 |
opl | -0.013 |
former | -0.013 |
destination | -0.013 |
achers | -0.012 |
Token | some |
Token ID | 617 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
do | +0.008 |
ily | +0.007 |
there | +0.007 |
did | +0.007 |
kids | +0.007 |
Neg logit contributions | |
icol | -0.019 |
former | -0.019 |
opl | -0.018 |
destination | -0.018 |
destinations | -0.018 |
Token | are |
Token ID | 389 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
do | +0.018 |
there | +0.014 |
I | +0.014 |
did | +0.014 |
kids | +0.013 |
Neg logit contributions | |
icol | -0.044 |
opl | -0.041 |
former | -0.041 |
destination | -0.040 |
achers | -0.039 |
Token | very |
Token ID | 845 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
do | +0.092 |
there | +0.077 |
did | +0.072 |
curious | +0.072 |
Tom | +0.070 |
Neg logit contributions | |
icol | -0.216 |
opl | -0.201 |
achers | -0.195 |
destination | -0.188 |
former | -0.187 |
Token | common |
Token ID | 2219 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
icol | +0.092 |
opl | +0.087 |
former | +0.083 |
destination | +0.083 |
achers | +0.083 |
Neg logit contributions | |
do | -0.050 |
there | -0.041 |
I | -0.041 |
did | -0.040 |
curious | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
icol | +0.682 |
opl | +0.650 |
former | +0.646 |
destination | +0.639 |
achers | +0.617 |
Neg logit contributions | |
do | -0.230 |
I | -0.166 |
did | -0.165 |
Tom | -0.165 |
there | -0.163 |
Token | useful |
Token ID | 4465 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
do | +0.009 |
there | +0.007 |
I | +0.007 |
did | +0.007 |
Tom | +0.007 |
Neg logit contributions | |
icol | -0.018 |
opl | -0.017 |
former | -0.016 |
destination | -0.016 |
achers | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
icol | +0.360 |
opl | +0.341 |
former | +0.332 |
achers | +0.329 |
destination | +0.323 |
Neg logit contributions | |
do | -0.078 |
there | -0.050 |
kids | -0.050 |
I | -0.050 |
you | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
do | +0.002 |
did | +0.002 |
there | +0.002 |
kids | +0.002 |
I | +0.002 |
Neg logit contributions | |
icol | -0.005 |
opl | -0.004 |
former | -0.004 |
destination | -0.004 |
destinations | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
icol | +0.006 |
opl | +0.006 |
former | +0.006 |
destination | +0.006 |
achers | +0.006 |
Neg logit contributions | |
do | -0.003 |
I | -0.003 |
did | -0.003 |
kids | -0.002 |
oh | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
do | +0.076 |
Tom | +0.059 |
did | +0.058 |
kids | +0.057 |
ily | +0.057 |
Neg logit contributions | |
icol | -0.203 |
opl | -0.200 |
former | -0.194 |
destination | -0.192 |
achers | -0.187 |
Token | It |
Token ID | 632 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
icol | +0.003 |
opl | +0.002 |
former | +0.002 |
destination | +0.002 |
achers | +0.002 |
Neg logit contributions | |
do | -0.001 |
I | -0.001 |
Tom | -0.001 |
there | -0.001 |
did | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
do | +0.071 |
did | +0.059 |
I | +0.058 |
you | +0.056 |
there | +0.055 |
Neg logit contributions | |
icol | -0.146 |
former | -0.135 |
opl | -0.133 |
destination | -0.133 |
achers | -0.130 |
Token | a |
Token ID | 257 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
icol | +0.101 |
achers | +0.095 |
opl | +0.094 |
destination | +0.093 |
former | +0.091 |
Neg logit contributions | |
do | -0.029 |
there | -0.022 |
curious | -0.021 |
Tom | -0.021 |
did | -0.020 |
Token | very |
Token ID | 845 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
icol | +0.021 |
opl | +0.020 |
achers | +0.020 |
former | +0.019 |
aters | +0.019 |
Neg logit contributions | |
do | -0.013 |
I | -0.010 |
you | -0.010 |
there | -0.010 |
curious | -0.010 |
Token | common |
Token ID | 2219 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
icol | +0.104 |
opl | +0.098 |
former | +0.095 |
destination | +0.095 |
achers | +0.094 |
Neg logit contributions | |
do | -0.051 |
there | -0.040 |
I | -0.040 |
did | -0.040 |
you | -0.039 |
Token | bird |
Token ID | 6512 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
icol | +0.632 |
opl | +0.597 |
former | +0.593 |
destination | +0.584 |
achers | +0.566 |
Neg logit contributions | |
do | -0.292 |
there | -0.230 |
I | -0.229 |
did | -0.227 |
Tom | -0.226 |
Token | . |
Token ID | 13 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
do | +0.050 |
Tom | +0.038 |
kids | +0.037 |
did | +0.037 |
I | +0.037 |
Neg logit contributions | |
icol | -0.135 |
opl | -0.133 |
former | -0.128 |
destination | -0.126 |
achers | -0.124 |
Token | It |
Token ID | 632 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
do | +0.002 |
I | +0.001 |
there | +0.001 |
Tom | +0.001 |
did | +0.001 |
Neg logit contributions | |
icol | -0.003 |
opl | -0.003 |
former | -0.003 |
destination | -0.003 |
achers | -0.003 |
Token | likes |
Token ID | 7832 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
do | +0.076 |
did | +0.064 |
I | +0.062 |
you | +0.060 |
there | +0.058 |
Neg logit contributions | |
icol | -0.155 |
former | -0.144 |
destination | -0.142 |
opl | -0.142 |
achers | -0.138 |
Token | to |
Token ID | 284 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
do | +0.023 |
you | +0.019 |
I | +0.018 |
there | +0.018 |
kids | +0.018 |
Neg logit contributions | |
icol | -0.047 |
opl | -0.044 |
former | -0.044 |
destination | -0.044 |
achers | -0.043 |
Token | had |
Token ID | 550 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
icol | +0.027 |
opl | +0.025 |
former | +0.025 |
destination | +0.024 |
achers | +0.024 |
Neg logit contributions | |
do | -0.012 |
did | -0.010 |
there | -0.010 |
I | -0.010 |
Tom | -0.009 |
Token | lots |
Token ID | 6041 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
icol | +0.140 |
opl | +0.134 |
former | +0.129 |
destination | +0.127 |
achers | +0.126 |
Neg logit contributions | |
do | -0.063 |
there | -0.053 |
did | -0.052 |
Tom | -0.050 |
I | -0.050 |
Token | of |
Token ID | 286 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
icol | +0.058 |
former | +0.054 |
ric | +0.054 |
destination | +0.054 |
opl | +0.054 |
Neg logit contributions | |
do | -0.014 |
there | -0.010 |
kids | -0.009 |
I | -0.009 |
you | -0.009 |
Token | things |
Token ID | 1243 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
do | +0.063 |
kids | +0.053 |
there | +0.050 |
did | +0.050 |
you | +0.049 |
Neg logit contributions | |
icol | -0.102 |
opl | -0.093 |
destination | -0.093 |
achers | -0.092 |
former | -0.092 |
Token | in |
Token ID | 287 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
icol | +0.057 |
former | +0.054 |
opl | +0.054 |
destination | +0.052 |
achers | +0.052 |
Neg logit contributions | |
do | -0.020 |
there | -0.016 |
I | -0.015 |
did | -0.015 |
you | -0.014 |
Token | common |
Token ID | 2219 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
do | +0.036 |
there | +0.032 |
Tom | +0.031 |
kids | +0.028 |
I | +0.028 |
Neg logit contributions | |
icol | -0.085 |
opl | -0.078 |
former | -0.078 |
achers | -0.076 |
ric | -0.075 |
Token | , |
Token ID | 11 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
icol | +0.711 |
opl | +0.673 |
former | +0.669 |
destination | +0.656 |
achers | +0.641 |
Neg logit contributions | |
do | -0.219 |
there | -0.160 |
did | -0.154 |
Tom | -0.153 |
kids | -0.152 |
Token | like |
Token ID | 588 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
icol | +0.000 |
opl | +0.000 |
former | +0.000 |
destination | +0.000 |
achers | +0.000 |
Neg logit contributions | |
do | -0.000 |
there | -0.000 |
I | -0.000 |
did | -0.000 |
Tom | -0.000 |
Token | his |
Token ID | 465 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
icol | +0.112 |
opl | +0.105 |
former | +0.105 |
destination | +0.103 |
achers | +0.101 |
Neg logit contributions | |
do | -0.056 |
there | -0.046 |
Tom | -0.045 |
I | -0.045 |
kids | -0.045 |
Token | love |
Token ID | 1842 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
icol | +0.060 |
opl | +0.057 |
achers | +0.056 |
former | +0.054 |
ilts | +0.054 |
Neg logit contributions | |
do | -0.033 |
kids | -0.027 |
there | -0.026 |
Tom | -0.025 |
did | -0.025 |
Token | for |
Token ID | 329 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
do | +0.031 |
there | +0.023 |
did | +0.022 |
I | +0.022 |
Tom | +0.022 |
Neg logit contributions | |
icol | -0.091 |
former | -0.086 |
opl | -0.085 |
destination | -0.083 |
achers | -0.082 |
Token | had |
Token ID | 550 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
icol | +0.011 |
opl | +0.010 |
former | +0.010 |
destination | +0.010 |
achers | +0.010 |
Neg logit contributions | |
do | -0.005 |
did | -0.004 |
there | -0.004 |
I | -0.004 |
Tom | -0.004 |
Token | lots |
Token ID | 6041 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
icol | +0.135 |
opl | +0.129 |
former | +0.124 |
achers | +0.121 |
destination | +0.121 |
Neg logit contributions | |
do | -0.060 |
there | -0.050 |
did | -0.049 |
Tom | -0.048 |
I | -0.047 |
Token | of |
Token ID | 286 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
icol | +0.052 |
former | +0.049 |
ric | +0.049 |
destination | +0.049 |
opl | +0.048 |
Neg logit contributions | |
do | -0.013 |
there | -0.009 |
kids | -0.009 |
I | -0.008 |
you | -0.008 |
Token | things |
Token ID | 1243 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
do | +0.058 |
kids | +0.050 |
there | +0.046 |
did | +0.046 |
you | +0.045 |
Neg logit contributions | |
icol | -0.094 |
opl | -0.087 |
destination | -0.085 |
achers | -0.085 |
former | -0.085 |
Token | in |
Token ID | 287 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
icol | +0.060 |
former | +0.057 |
opl | +0.056 |
destination | +0.054 |
achers | +0.054 |
Neg logit contributions | |
do | -0.020 |
there | -0.016 |
I | -0.015 |
did | -0.015 |
Tom | -0.015 |
Token | common |
Token ID | 2219 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
do | +0.032 |
there | +0.028 |
Tom | +0.027 |
kids | +0.025 |
I | +0.024 |
Neg logit contributions | |
icol | -0.075 |
former | -0.069 |
opl | -0.068 |
achers | -0.067 |
ric | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
icol | +0.709 |
opl | +0.673 |
former | +0.668 |
destination | +0.654 |
achers | +0.640 |
Neg logit contributions | |
do | -0.219 |
there | -0.159 |
did | -0.154 |
Tom | -0.153 |
kids | -0.152 |
Token | like |
Token ID | 588 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
icol | +0.003 |
opl | +0.003 |
former | +0.003 |
destination | +0.003 |
achers | +0.003 |
Neg logit contributions | |
do | -0.001 |
there | -0.001 |
I | -0.001 |
did | -0.001 |
Tom | -0.001 |
Token | his |
Token ID | 465 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
icol | +0.126 |
opl | +0.118 |
former | +0.117 |
destination | +0.116 |
achers | +0.113 |
Neg logit contributions | |
do | -0.062 |
there | -0.049 |
I | -0.049 |
Tom | -0.049 |
kids | -0.049 |
Token | love |
Token ID | 1842 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
icol | +0.063 |
opl | +0.059 |
achers | +0.058 |
former | +0.057 |
ilts | +0.056 |
Neg logit contributions | |
do | -0.034 |
kids | -0.027 |
Tom | -0.026 |
there | -0.026 |
did | -0.026 |
Token | for |
Token ID | 329 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
do | +0.025 |
there | +0.019 |
did | +0.018 |
I | +0.018 |
Tom | +0.018 |
Neg logit contributions | |
icol | -0.074 |
former | -0.070 |
opl | -0.070 |
destination | -0.068 |
achers | -0.067 |
Token | two |
Token ID | 734 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
do | +0.001 |
ily | +0.001 |
did | +0.001 |
I | +0.001 |
Tom | +0.001 |
Neg logit contributions | |
icol | -0.002 |
former | -0.002 |
destination | -0.002 |
opl | -0.002 |
destinations | -0.002 |
Token | kids |
Token ID | 3988 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
do | +0.007 |
I | +0.005 |
ily | +0.005 |
did | +0.005 |
there | +0.004 |
Neg logit contributions | |
destination | -0.027 |
icol | -0.027 |
opl | -0.027 |
destinations | -0.026 |
former | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
do | +0.116 |
I | +0.091 |
ily | +0.090 |
did | +0.089 |
Tom | +0.089 |
Neg logit contributions | |
icol | -0.255 |
opl | -0.242 |
destination | -0.240 |
former | -0.239 |
destinations | -0.231 |
Token | find |
Token ID | 1064 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
icol | +0.068 |
former | +0.065 |
opl | +0.065 |
destination | +0.065 |
achers | +0.061 |
Neg logit contributions | |
do | -0.032 |
I | -0.027 |
there | -0.027 |
ily | -0.026 |
did | -0.026 |
Token | some |
Token ID | 617 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
do | +0.031 |
I | +0.024 |
did | +0.024 |
there | +0.024 |
Tom | +0.024 |
Neg logit contributions | |
icol | -0.069 |
opl | -0.065 |
former | -0.064 |
destination | -0.064 |
achers | -0.061 |
Token | common |
Token ID | 2219 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
do | +0.010 |
kids | +0.008 |
there | +0.008 |
Tom | +0.008 |
did | +0.008 |
Neg logit contributions | |
icol | -0.019 |
opl | -0.018 |
former | -0.017 |
destination | -0.017 |
achers | -0.017 |
Token | ground |
Token ID | 2323 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
icol | +0.649 |
opl | +0.616 |
former | +0.609 |
destination | +0.599 |
achers | +0.583 |
Neg logit contributions | |
do | -0.259 |
there | -0.200 |
did | -0.196 |
I | -0.195 |
Tom | -0.195 |
Token | . |
Token ID | 13 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
do | +0.061 |
there | +0.047 |
Tom | +0.043 |
did | +0.043 |
kids | +0.042 |
Neg logit contributions | |
icol | -0.195 |
opl | -0.184 |
former | -0.180 |
destination | -0.177 |
achers | -0.176 |
Token | He |
Token ID | 679 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
do | +0.016 |
there | +0.013 |
I | +0.013 |
did | +0.013 |
Tom | +0.013 |
Neg logit contributions | |
icol | -0.024 |
opl | -0.023 |
former | -0.023 |
destination | -0.022 |
achers | -0.021 |
Token | said |
Token ID | 531 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
icol | +0.031 |
opl | +0.030 |
former | +0.029 |
destination | +0.028 |
achers | +0.028 |
Neg logit contributions | |
do | -0.016 |
did | -0.013 |
there | -0.013 |
Tom | -0.012 |
kids | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
do | +0.015 |
kids | +0.012 |
I | +0.012 |
ily | +0.012 |
Tom | +0.011 |
Neg logit contributions | |
icol | -0.026 |
destination | -0.024 |
former | -0.024 |
brand | -0.023 |
lifelong | -0.023 |
Token | they |
Token ID | 484 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
icol | +0.067 |
opl | +0.064 |
former | +0.063 |
destination | +0.063 |
ric | +0.060 |
Neg logit contributions | |
do | -0.034 |
ily | -0.028 |
kids | -0.027 |
I | -0.027 |
did | -0.026 |
Token | had |
Token ID | 550 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
icol | +0.074 |
former | +0.072 |
destination | +0.071 |
opl | +0.071 |
destinations | +0.068 |
Neg logit contributions | |
do | -0.035 |
I | -0.029 |
kids | -0.028 |
ily | -0.028 |
Tom | -0.028 |
Token | one |
Token ID | 530 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
icol | +0.102 |
opl | +0.097 |
achers | +0.092 |
former | +0.092 |
destination | +0.090 |
Neg logit contributions | |
do | -0.039 |
there | -0.031 |
did | -0.031 |
Tom | -0.030 |
kids | -0.029 |
Token | thing |
Token ID | 1517 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
icol | +0.157 |
opl | +0.143 |
achers | +0.142 |
former | +0.142 |
ilts | +0.138 |
Neg logit contributions | |
do | -0.067 |
there | -0.053 |
I | -0.050 |
did | -0.048 |
curious | -0.048 |
Token | in |
Token ID | 287 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
icol | +0.083 |
opl | +0.080 |
former | +0.079 |
destination | +0.075 |
achers | +0.075 |
Neg logit contributions | |
do | -0.031 |
there | -0.025 |
I | -0.024 |
Tom | -0.024 |
you | -0.023 |
Token | common |
Token ID | 2219 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
do | +0.054 |
there | +0.049 |
Tom | +0.048 |
I | +0.044 |
kids | +0.042 |
Neg logit contributions | |
icol | -0.101 |
opl | -0.092 |
former | -0.091 |
achers | -0.089 |
sym | -0.086 |
Token | : |
Token ID | 25 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
icol | +0.700 |
opl | +0.662 |
former | +0.658 |
destination | +0.643 |
achers | +0.630 |
Neg logit contributions | |
do | -0.216 |
there | -0.159 |
Tom | -0.153 |
did | -0.152 |
I | -0.151 |
Token | a |
Token ID | 257 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
icol | +0.122 |
opl | +0.115 |
former | +0.115 |
destination | +0.113 |
achers | +0.109 |
Neg logit contributions | |
do | -0.053 |
there | -0.041 |
I | -0.041 |
did | -0.041 |
Tom | -0.041 |
Token | love |
Token ID | 1842 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
do | +0.006 |
I | +0.005 |
curious | +0.004 |
there | +0.004 |
kids | +0.004 |
Neg logit contributions | |
icol | -0.010 |
opl | -0.010 |
achers | -0.010 |
former | -0.010 |
irs | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
do | +0.037 |
I | +0.028 |
there | +0.028 |
Tom | +0.027 |
kids | +0.026 |
Neg logit contributions | |
icol | -0.110 |
former | -0.105 |
opl | -0.104 |
destination | -0.101 |
achers | -0.100 |
Token | bright |
Token ID | 6016 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
do | +0.066 |
there | +0.053 |
did | +0.053 |
I | +0.053 |
Tom | +0.052 |
Neg logit contributions | |
icol | -0.125 |
opl | -0.118 |
former | -0.117 |
destination | -0.116 |
achers | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
icol | +0.035 |
opl | +0.033 |
former | +0.033 |
destination | +0.032 |
achers | +0.032 |
Neg logit contributions | |
do | -0.013 |
there | -0.010 |
I | -0.010 |
did | -0.009 |
Tom | -0.009 |
Token | They |
Token ID | 1119 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
do | +0.015 |
there | +0.012 |
did | +0.012 |
I | +0.012 |
Tom | +0.012 |
Neg logit contributions | |
icol | -0.023 |
opl | -0.022 |
former | -0.022 |
destination | -0.021 |
achers | -0.020 |
Token | all |
Token ID | 477 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
icol | +0.038 |
destination | +0.037 |
former | +0.036 |
opl | +0.036 |
destinations | +0.036 |
Neg logit contributions | |
do | -0.022 |
I | -0.020 |
ily | -0.019 |
you | -0.019 |
oh | -0.019 |
Token | shared |
Token ID | 4888 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
do | +0.029 |
I | +0.026 |
you | +0.025 |
oh | +0.025 |
Tom | +0.025 |
Neg logit contributions | |
icol | -0.044 |
opl | -0.042 |
former | -0.041 |
destination | -0.041 |
en | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
icol | +0.113 |
opl | +0.107 |
destination | +0.106 |
former | +0.106 |
destinations | +0.103 |
Neg logit contributions | |
do | -0.064 |
I | -0.056 |
ily | -0.053 |
did | -0.052 |
oh | -0.050 |
Token | common |
Token ID | 2219 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
do | +0.012 |
there | +0.010 |
did | +0.010 |
kids | +0.010 |
I | +0.010 |
Neg logit contributions | |
icol | -0.015 |
opl | -0.014 |
former | -0.014 |
destination | -0.014 |
achers | -0.013 |
Token | goal |
Token ID | 3061 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
icol | +0.541 |
opl | +0.503 |
former | +0.501 |
destination | +0.490 |
achers | +0.472 |
Neg logit contributions | |
do | -0.368 |
there | -0.313 |
kids | -0.306 |
did | -0.304 |
Tom | -0.298 |
Token | � |
Token ID | 6184 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
icol | +0.083 |
opl | +0.079 |
former | +0.078 |
destination | +0.078 |
achers | +0.075 |
Neg logit contributions | |
do | -0.031 |
did | -0.023 |
I | -0.023 |
Tom | -0.023 |
kids | -0.022 |
Token | � |
Token ID | 95 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
icol | +0.015 |
opl | +0.014 |
former | +0.014 |
destination | +0.013 |
achers | +0.013 |
Neg logit contributions | |
do | -0.018 |
I | -0.016 |
there | -0.016 |
did | -0.016 |
Tom | -0.016 |
Token | € |
Token ID | 26391 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
icol | +0.058 |
former | +0.053 |
opl | +0.053 |
destination | +0.052 |
achers | +0.049 |
Neg logit contributions | |
do | -0.071 |
I | -0.062 |
Tom | -0.061 |
did | -0.061 |
ily | -0.061 |
Token | � |
Token ID | 447 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
do | +0.054 |
ily | +0.050 |
kids | +0.047 |
oh | +0.046 |
Tom | +0.044 |
Neg logit contributions | |
icol | -0.062 |
opl | -0.058 |
destination | -0.056 |
ilts | -0.054 |
achers | -0.053 |
Token | simple |
Token ID | 2829 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
opl | +0.000 |
icol | +0.000 |
ays | +0.000 |
achers | +0.000 |
irs | +0.000 |
Neg logit contributions | |
do | -0.000 |
curious | -0.000 |
I | -0.000 |
did | -0.000 |
there | -0.000 |
Token | rubber |
Token ID | 14239 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
icol | +0.123 |
opl | +0.117 |
former | +0.115 |
destination | +0.112 |
achers | +0.110 |
Neg logit contributions | |
do | -0.085 |
there | -0.069 |
kids | -0.068 |
I | -0.067 |
did | -0.067 |
Token | ball |
Token ID | 2613 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
icol | +0.389 |
former | +0.371 |
opl | +0.370 |
destination | +0.357 |
destinations | +0.351 |
Neg logit contributions | |
do | -0.197 |
I | -0.158 |
there | -0.153 |
kids | -0.152 |
did | -0.152 |
Token | , |
Token ID | 11 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
do | +0.006 |
I | +0.004 |
there | +0.004 |
Tom | +0.004 |
did | +0.004 |
Neg logit contributions | |
icol | -0.017 |
former | -0.017 |
opl | -0.016 |
destination | -0.016 |
achers | -0.016 |
Token | very |
Token ID | 845 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
do | +0.008 |
there | +0.006 |
Tom | +0.005 |
did | +0.005 |
I | +0.005 |
Neg logit contributions | |
icol | -0.023 |
opl | -0.022 |
former | -0.022 |
destination | -0.022 |
achers | -0.021 |
Token | common |
Token ID | 2219 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
icol | +0.086 |
opl | +0.084 |
achers | +0.081 |
destination | +0.079 |
former | +0.079 |
Neg logit contributions | |
do | -0.046 |
did | -0.037 |
there | -0.037 |
I | -0.036 |
Tom | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
icol | +0.581 |
destination | +0.539 |
former | +0.536 |
opl | +0.536 |
achers | +0.512 |
Neg logit contributions | |
do | -0.295 |
I | -0.237 |
ily | -0.233 |
kids | -0.231 |
did | -0.231 |
Token | nothing |
Token ID | 2147 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
do | +0.007 |
ily | +0.006 |
kids | +0.005 |
Tom | +0.005 |
did | +0.005 |
Neg logit contributions | |
icol | -0.022 |
former | -0.021 |
destination | -0.020 |
opl | -0.020 |
destinations | -0.020 |
Token | special |
Token ID | 2041 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
icol | +0.084 |
opl | +0.080 |
former | +0.079 |
destination | +0.078 |
achers | +0.076 |
Neg logit contributions | |
do | -0.035 |
did | -0.028 |
there | -0.028 |
I | -0.027 |
ily | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
icol | +0.270 |
opl | +0.253 |
former | +0.253 |
destination | +0.245 |
achers | +0.239 |
Neg logit contributions | |
do | -0.157 |
did | -0.131 |
there | -0.129 |
I | -0.128 |
Tom | -0.127 |
Token | |
Token ID | 220 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
do | +0.021 |
did | +0.017 |
kids | +0.016 |
there | +0.016 |
don | +0.016 |
Neg logit contributions | |
icol | -0.033 |
former | -0.032 |
opl | -0.031 |
destination | -0.031 |
destinations | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
icol | +0.162 |
opl | +0.152 |
former | +0.151 |
destination | +0.148 |
achers | +0.143 |
Neg logit contributions | |
do | -0.097 |
there | -0.079 |
I | -0.079 |
did | -0.078 |
Tom | -0.078 |
Token | bumped |
Token ID | 38034 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
do | +0.011 |
ily | +0.009 |
kids | +0.009 |
I | +0.009 |
there | +0.009 |
Neg logit contributions | |
icol | -0.016 |
opl | -0.015 |
destination | -0.015 |
former | -0.015 |
achers | -0.014 |
Token | against |
Token ID | 1028 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
icol | +0.158 |
opl | +0.150 |
former | +0.148 |
destination | +0.145 |
achers | +0.139 |
Neg logit contributions | |
do | -0.118 |
Tom | -0.101 |
there | -0.101 |
kids | -0.099 |
did | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
icol | +0.111 |
destination | +0.106 |
opl | +0.105 |
former | +0.104 |
destinations | +0.101 |
Neg logit contributions | |
do | -0.032 |
I | -0.023 |
did | -0.023 |
ily | -0.022 |
there | -0.022 |
Token | books |
Token ID | 3835 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
do | +0.025 |
there | +0.024 |
did | +0.023 |
don | +0.023 |
ily | +0.022 |
Neg logit contributions | |
icol | -0.035 |
destination | -0.034 |
opl | -0.033 |
former | -0.032 |
brand | -0.031 |
Token | hel |
Token ID | 2978 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
do | +0.060 |
kids | +0.054 |
oh | +0.052 |
ily | +0.050 |
don | +0.049 |
Neg logit contributions | |
destination | -0.131 |
opl | -0.130 |
icol | -0.127 |
en | -0.121 |
former | -0.119 |
Token | ves |
Token ID | 1158 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
do | +0.488 |
there | +0.426 |
Tom | +0.422 |
did | +0.418 |
ily | +0.417 |
Neg logit contributions | |
icol | -0.493 |
former | -0.452 |
opl | -0.447 |
destination | -0.430 |
achers | -0.414 |
Token | . |
Token ID | 13 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
icol | +0.031 |
opl | +0.029 |
former | +0.029 |
destination | +0.029 |
achers | +0.028 |
Neg logit contributions | |
do | -0.013 |
I | -0.010 |
kids | -0.010 |
did | -0.010 |
there | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
do | +0.029 |
there | +0.024 |
did | +0.024 |
you | +0.024 |
kids | +0.024 |
Neg logit contributions | |
icol | -0.033 |
opl | -0.030 |
former | -0.030 |
destination | -0.030 |
destinations | -0.029 |
Token | smiled |
Token ID | 13541 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
icol | +0.011 |
opl | +0.010 |
former | +0.010 |
destination | +0.010 |
achers | +0.010 |
Neg logit contributions | |
do | -0.006 |
I | -0.005 |
there | -0.005 |
Tom | -0.005 |
kids | -0.005 |
Token | as |
Token ID | 355 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
do | +0.011 |
there | +0.008 |
Tom | +0.008 |
did | +0.008 |
I | +0.008 |
Neg logit contributions | |
icol | -0.035 |
opl | -0.034 |
former | -0.034 |
destination | -0.033 |
achers | -0.033 |
Token | her |
Token ID | 607 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
icol | +0.009 |
destination | +0.009 |
en | +0.009 |
opl | +0.009 |
former | +0.009 |
Neg logit contributions | |
do | -0.005 |
I | -0.004 |
did | -0.004 |
there | -0.004 |
curious | -0.004 |
Token | not |
Token ID | 407 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
do | +0.057 |
ily | +0.051 |
kids | +0.050 |
I | +0.050 |
Tom | +0.050 |
Neg logit contributions | |
icol | -0.094 |
destination | -0.092 |
former | -0.090 |
fault | -0.087 |
opl | -0.087 |
Token | to |
Token ID | 284 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
do | +0.098 |
ily | +0.084 |
I | +0.083 |
did | +0.083 |
kids | +0.082 |
Neg logit contributions | |
icol | -0.130 |
former | -0.122 |
opl | -0.122 |
destination | -0.121 |
destinations | -0.115 |
Token | investigate |
Token ID | 9161 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
destination | +0.035 |
former | +0.031 |
en | +0.031 |
destinations | +0.029 |
icol | +0.029 |
Neg logit contributions | |
ily | -0.020 |
oh | -0.017 |
kids | -0.017 |
I | -0.017 |
Anna | -0.016 |
Token | books |
Token ID | 3835 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
do | +0.027 |
I | +0.020 |
did | +0.020 |
ily | +0.020 |
Tom | +0.020 |
Neg logit contributions | |
icol | -0.074 |
opl | -0.071 |
former | -0.071 |
destination | -0.070 |
destinations | -0.068 |
Token | hel |
Token ID | 2978 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
do | +0.061 |
kids | +0.058 |
oh | +0.055 |
curious | +0.055 |
I | +0.053 |
Neg logit contributions | |
destination | -0.129 |
opl | -0.123 |
icol | -0.120 |
en | -0.118 |
former | -0.116 |
Token | ves |
Token ID | 1158 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
do | +0.535 |
I | +0.485 |
kids | +0.473 |
curious | +0.471 |
did | +0.469 |
Neg logit contributions | |
opl | -0.388 |
icol | -0.382 |
destination | -0.367 |
en | -0.361 |
achers | -0.356 |
Token | alone |
Token ID | 3436 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
icol | +0.031 |
opl | +0.030 |
destination | +0.030 |
former | +0.029 |
achers | +0.028 |
Neg logit contributions | |
do | -0.012 |
I | -0.009 |
kids | -0.009 |
ily | -0.009 |
did | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
do | +0.100 |
I | +0.079 |
did | +0.077 |
ily | +0.075 |
Tom | +0.074 |
Neg logit contributions | |
icol | -0.218 |
destination | -0.214 |
former | -0.210 |
opl | -0.207 |
en | -0.205 |
Token | but |
Token ID | 475 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
do | +0.016 |
ily | +0.012 |
did | +0.011 |
I | +0.011 |
kids | +0.011 |
Neg logit contributions | |
icol | -0.042 |
former | -0.040 |
destination | -0.040 |
opl | -0.040 |
destinations | -0.039 |
Token | she |
Token ID | 673 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
icol | +0.067 |
destination | +0.065 |
former | +0.065 |
opl | +0.063 |
destinations | +0.062 |
Neg logit contributions | |
do | -0.023 |
ily | -0.016 |
kids | -0.016 |
I | -0.016 |
did | -0.014 |
Token | walked |
Token ID | 6807 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
do | +0.007 |
I | +0.005 |
there | +0.005 |
Tom | +0.005 |
kids | +0.005 |
Neg logit contributions | |
icol | -0.013 |
opl | -0.012 |
former | -0.012 |
destination | -0.012 |
achers | -0.012 |
Token | over |
Token ID | 625 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
do | +0.064 |
I | +0.053 |
did | +0.053 |
there | +0.053 |
Tom | +0.053 |
Neg logit contributions | |
icol | -0.097 |
opl | -0.090 |
former | -0.090 |
destination | -0.089 |
achers | -0.085 |
Token | to |
Token ID | 284 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
icol | +0.110 |
destination | +0.103 |
former | +0.100 |
opl | +0.098 |
destinations | +0.097 |
Neg logit contributions | |
do | -0.077 |
I | -0.066 |
ily | -0.064 |
did | -0.064 |
kids | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
destination | +0.050 |
icol | +0.049 |
en | +0.047 |
former | +0.046 |
irs | +0.046 |
Neg logit contributions | |
ily | -0.023 |
do | -0.023 |
did | -0.023 |
I | -0.021 |
oh | -0.021 |
Token | books |
Token ID | 3835 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
do | +0.016 |
ily | +0.015 |
I | +0.015 |
there | +0.015 |
don | +0.015 |
Neg logit contributions | |
destination | -0.018 |
icol | -0.018 |
opl | -0.016 |
destinations | -0.016 |
former | -0.016 |
Token | hel |
Token ID | 2978 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
oh | +0.066 |
do | +0.062 |
kids | +0.061 |
ily | +0.059 |
don | +0.058 |
Neg logit contributions | |
destination | -0.108 |
opl | -0.102 |
en | -0.099 |
icol | -0.098 |
brand | -0.094 |
Token | ves |
Token ID | 1158 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
do | +0.499 |
I | +0.437 |
did | +0.432 |
there | +0.432 |
Tom | +0.431 |
Neg logit contributions | |
icol | -0.454 |
opl | -0.422 |
former | -0.414 |
destination | -0.410 |
achers | -0.390 |
Token | and |
Token ID | 290 |
Feature activation | -8.45e-03 |
Pos logit contributions | |
icol | +0.049 |
destination | +0.048 |
opl | +0.047 |
former | +0.046 |
en | +0.045 |
Neg logit contributions | |
do | -0.020 |
ily | -0.017 |
kids | -0.017 |
I | -0.017 |
oh | -0.016 |
Token | began |
Token ID | 2540 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
do | +0.000 |
ily | +0.000 |
I | +0.000 |
you | +0.000 |
there | +0.000 |
Neg logit contributions | |
icol | -0.001 |
destination | -0.001 |
former | -0.001 |
destinations | -0.001 |
en | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
icol | +0.017 |
opl | +0.016 |
former | +0.016 |
destination | +0.016 |
achers | +0.015 |
Neg logit contributions | |
do | -0.008 |
there | -0.007 |
Tom | -0.007 |
curious | -0.007 |
kids | -0.007 |
Token | read |
Token ID | 1100 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
icol | +0.056 |
destination | +0.054 |
former | +0.054 |
opl | +0.054 |
destinations | +0.051 |
Neg logit contributions | |
ily | -0.029 |
do | -0.027 |
there | -0.026 |
I | -0.026 |
you | -0.025 |
Token | books |
Token ID | 3835 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
do | +0.137 |
I | +0.113 |
ily | +0.111 |
did | +0.110 |
don | +0.108 |
Neg logit contributions | |
icol | -0.278 |
opl | -0.266 |
former | -0.258 |
destination | -0.258 |
destinations | -0.251 |
Token | , |
Token ID | 11 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
do | +0.073 |
oh | +0.069 |
kids | +0.068 |
I | +0.065 |
don | +0.064 |
Neg logit contributions | |
opl | -0.130 |
destination | -0.130 |
former | -0.121 |
brand | -0.121 |
destinations | -0.120 |
Token | but |
Token ID | 475 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
ily | +0.056 |
do | +0.052 |
oh | +0.049 |
I | +0.048 |
kids | +0.046 |
Neg logit contributions | |
icol | -0.071 |
opl | -0.071 |
particularly | -0.068 |
ric | -0.068 |
brand | -0.067 |
Token | her |
Token ID | 607 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
do | +0.000 |
ily | +0.000 |
kids | +0.000 |
curious | +0.000 |
I | +0.000 |
Neg logit contributions | |
icol | -0.001 |
destination | -0.001 |
former | -0.001 |
opl | -0.001 |
conflicts | -0.001 |
Token | books |
Token ID | 3835 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
do | +0.063 |
ily | +0.053 |
I | +0.053 |
there | +0.050 |
you | +0.050 |
Neg logit contributions | |
icol | -0.142 |
destination | -0.136 |
former | -0.136 |
opl | -0.133 |
destinations | -0.129 |
Token | he |
Token ID | 258 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
do | +0.061 |
kids | +0.056 |
I | +0.053 |
curious | +0.053 |
Tom | +0.052 |
Neg logit contributions | |
opl | -0.156 |
destination | -0.153 |
icol | -0.151 |
former | -0.148 |
brand | -0.145 |
Token | lf |
Token ID | 1652 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
do | +0.361 |
I | +0.338 |
don | +0.322 |
Tom | +0.319 |
curious | +0.315 |
Neg logit contributions | |
opl | -0.507 |
icol | -0.479 |
destination | -0.473 |
achers | -0.473 |
destinations | -0.460 |
Token | was |
Token ID | 373 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
do | +0.208 |
I | +0.186 |
kids | +0.180 |
Tom | +0.178 |
you | +0.178 |
Neg logit contributions | |
destination | -0.350 |
opl | -0.346 |
former | -0.338 |
icol | -0.334 |
destinations | -0.333 |
Token | very |
Token ID | 845 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
icol | +0.039 |
opl | +0.036 |
former | +0.035 |
destination | +0.035 |
achers | +0.035 |
Neg logit contributions | |
do | -0.018 |
there | -0.016 |
did | -0.015 |
I | -0.015 |
Tom | -0.015 |
Token | messy |
Token ID | 24097 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
icol | +0.024 |
former | +0.024 |
opl | +0.023 |
destination | +0.023 |
brand | +0.022 |
Neg logit contributions | |
do | -0.018 |
kids | -0.015 |
ily | -0.015 |
Tom | -0.015 |
oh | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
icol | +0.001 |
opl | +0.001 |
former | +0.001 |
destination | +0.001 |
en | +0.001 |
Neg logit contributions | |
do | -0.000 |
did | -0.000 |
I | -0.000 |
Tom | -0.000 |
ily | -0.000 |
Token | loo |
Token ID | 29680 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
do | +0.152 |
there | +0.135 |
did | +0.134 |
kids | +0.132 |
Tom | +0.132 |
Neg logit contributions | |
icol | -0.143 |
former | -0.130 |
opl | -0.126 |
destination | -0.125 |
destinations | -0.118 |
Token | and |
Token ID | 290 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
do | +0.074 |
I | +0.061 |
ily | +0.060 |
kids | +0.059 |
did | +0.058 |
Neg logit contributions | |
icol | -0.160 |
destination | -0.153 |
opl | -0.151 |
former | -0.150 |
en | -0.144 |
Token | pretended |
Token ID | 36766 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
do | +0.007 |
ily | +0.006 |
I | +0.006 |
kids | +0.006 |
you | +0.006 |
Neg logit contributions | |
icol | -0.012 |
destination | -0.011 |
opl | -0.011 |
former | -0.010 |
achers | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
icol | +0.056 |
opl | +0.054 |
former | +0.053 |
destination | +0.052 |
achers | +0.051 |
Neg logit contributions | |
do | -0.025 |
there | -0.019 |
I | -0.019 |
did | -0.019 |
Tom | -0.019 |
Token | be |
Token ID | 307 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
icol | +0.054 |
former | +0.053 |
destination | +0.053 |
opl | +0.052 |
ric | +0.050 |
Neg logit contributions | |
do | -0.022 |
ily | -0.020 |
there | -0.019 |
kids | -0.019 |
curious | -0.018 |
Token | Esk |
Token ID | 47534 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
do | +0.025 |
there | +0.019 |
Tom | +0.019 |
did | +0.019 |
kids | +0.019 |
Neg logit contributions | |
icol | -0.071 |
opl | -0.067 |
former | -0.067 |
destination | -0.066 |
achers | -0.064 |
Token | im |
Token ID | 320 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
do | +0.499 |
Tom | +0.470 |
did | +0.464 |
there | +0.459 |
kids | +0.429 |
Neg logit contributions | |
icol | -0.439 |
former | -0.376 |
lifelong | -0.367 |
brand | -0.366 |
pill | -0.356 |
Token | os |
Token ID | 418 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
opl | +0.003 |
icol | +0.003 |
destination | +0.003 |
achers | +0.003 |
ric | +0.003 |
Neg logit contributions | |
do | -0.004 |
I | -0.004 |
ily | -0.004 |
kids | -0.004 |
Tom | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
do | +0.061 |
I | +0.051 |
ily | +0.051 |
Tom | +0.049 |
did | +0.049 |
Neg logit contributions | |
icol | -0.131 |
opl | -0.131 |
destination | -0.126 |
former | -0.125 |
en | -0.123 |
Token | After |
Token ID | 2293 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
icol | +0.006 |
opl | +0.005 |
former | +0.005 |
destination | +0.005 |
achers | +0.005 |
Neg logit contributions | |
Tom | -0.002 |
do | -0.002 |
I | -0.002 |
there | -0.002 |
kids | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
icol | +0.093 |
opl | +0.088 |
former | +0.087 |
destination | +0.086 |
achers | +0.084 |
Neg logit contributions | |
do | -0.027 |
I | -0.019 |
did | -0.019 |
there | -0.019 |
ily | -0.019 |
Token | day |
Token ID | 1110 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
icol | +0.136 |
former | +0.128 |
opl | +0.126 |
destination | +0.124 |
achers | +0.121 |
Neg logit contributions | |
do | -0.071 |
there | -0.056 |
did | -0.055 |
I | -0.054 |
ily | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
icol | +0.090 |
destination | +0.084 |
opl | +0.083 |
former | +0.082 |
en | +0.081 |
Neg logit contributions | |
do | -0.027 |
ily | -0.019 |
curious | -0.019 |
did | -0.018 |
kids | -0.018 |
Token | she |
Token ID | 673 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
do | +0.035 |
did | +0.028 |
ily | +0.028 |
curious | +0.026 |
Tom | +0.025 |
Neg logit contributions | |
icol | -0.079 |
former | -0.079 |
destination | -0.077 |
Wed | -0.076 |
particularly | -0.076 |
Token | would |
Token ID | 561 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
do | +0.039 |
did | +0.035 |
there | +0.032 |
let | +0.031 |
kids | +0.030 |
Neg logit contributions | |
icol | -0.055 |
opl | -0.054 |
former | -0.052 |
destination | -0.051 |
alks | -0.049 |
Token | bat |
Token ID | 7365 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
icol | +0.222 |
opl | +0.213 |
former | +0.208 |
destination | +0.205 |
achers | +0.200 |
Neg logit contributions | |
do | -0.096 |
I | -0.070 |
did | -0.069 |
there | -0.068 |
kids | -0.065 |
Token | he |
Token ID | 258 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
icol | +0.197 |
opl | +0.191 |
former | +0.185 |
achers | +0.184 |
destination | +0.184 |
Neg logit contributions | |
do | -0.056 |
I | -0.041 |
Tom | -0.040 |
kids | -0.039 |
curious | -0.038 |
Token | for |
Token ID | 329 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
do | +0.254 |
Tom | +0.210 |
I | +0.203 |
kids | +0.196 |
ily | +0.193 |
Neg logit contributions | |
icol | -0.651 |
opl | -0.626 |
former | -0.625 |
destination | -0.610 |
achers | -0.600 |
Token | hours |
Token ID | 2250 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
do | +0.011 |
there | +0.008 |
kids | +0.008 |
Tom | +0.008 |
you | +0.008 |
Neg logit contributions | |
icol | -0.026 |
opl | -0.024 |
former | -0.024 |
destination | -0.024 |
achers | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
do | +0.106 |
I | +0.082 |
did | +0.080 |
kids | +0.079 |
Tom | +0.079 |
Neg logit contributions | |
icol | -0.263 |
opl | -0.254 |
former | -0.248 |
destination | -0.246 |
achers | -0.242 |
Token | her |
Token ID | 607 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
do | +0.030 |
there | +0.021 |
Tom | +0.015 |
kids | +0.014 |
you | +0.014 |
Neg logit contributions | |
icol | -0.186 |
former | -0.172 |
opl | -0.172 |
achers | -0.169 |
destination | -0.167 |
Token | royal |
Token ID | 15100 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
do | +0.078 |
there | +0.064 |
kids | +0.064 |
I | +0.062 |
curious | +0.061 |
Neg logit contributions | |
icol | -0.132 |
opl | -0.126 |
former | -0.122 |
achers | -0.119 |
irs | -0.118 |
Token | and |
Token ID | 290 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
do | +0.008 |
there | +0.005 |
did | +0.005 |
I | +0.005 |
Tom | +0.005 |
Neg logit contributions | |
icol | -0.025 |
opl | -0.024 |
former | -0.023 |
destination | -0.023 |
achers | -0.023 |
Token | said |
Token ID | 531 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
do | +0.009 |
ily | +0.007 |
I | +0.007 |
there | +0.007 |
kids | +0.007 |
Neg logit contributions | |
icol | -0.025 |
former | -0.023 |
opl | -0.023 |
destination | -0.023 |
destinations | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -9.63e-02 |
Pos logit contributions | |
do | +0.015 |
kids | +0.012 |
ily | +0.011 |
did | +0.011 |
Tom | +0.011 |
Neg logit contributions | |
icol | -0.037 |
destination | -0.034 |
former | -0.033 |
opl | -0.033 |
alks | -0.032 |
Token | " |
Token ID | 366 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
do | +0.005 |
ily | +0.004 |
kids | +0.004 |
did | +0.004 |
you | +0.004 |
Neg logit contributions | |
icol | -0.010 |
former | -0.009 |
opl | -0.009 |
destination | -0.009 |
brand | -0.009 |
Token | S |
Token ID | 50 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
do | +0.011 |
I | +0.009 |
there | +0.008 |
did | +0.008 |
you | +0.008 |
Neg logit contributions | |
icol | -0.024 |
opl | -0.023 |
destination | -0.022 |
former | -0.022 |
achers | -0.021 |
Token | hel |
Token ID | 2978 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
do | +0.071 |
you | +0.063 |
Tom | +0.062 |
I | +0.062 |
kids | +0.062 |
Neg logit contributions | |
icol | -0.059 |
opl | -0.054 |
former | -0.054 |
destination | -0.052 |
ric | -0.050 |
Token | ter |
Token ID | 353 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
do | +0.467 |
Tom | +0.406 |
I | +0.402 |
did | +0.395 |
kids | +0.394 |
Neg logit contributions | |
icol | -0.458 |
opl | -0.429 |
destination | -0.422 |
former | -0.413 |
achers | -0.406 |
Token | is |
Token ID | 318 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
do | +0.098 |
I | +0.073 |
there | +0.073 |
did | +0.072 |
Tom | +0.071 |
Neg logit contributions | |
icol | -0.278 |
opl | -0.263 |
former | -0.262 |
destination | -0.257 |
achers | -0.249 |
Token | when |
Token ID | 618 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
icol | +0.077 |
opl | +0.072 |
former | +0.071 |
achers | +0.070 |
destination | +0.070 |
Neg logit contributions | |
do | -0.026 |
there | -0.021 |
I | -0.021 |
Tom | -0.020 |
you | -0.019 |
Token | you |
Token ID | 345 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
do | +0.004 |
ily | +0.004 |
did | +0.003 |
Tom | +0.003 |
curious | +0.003 |
Neg logit contributions | |
destination | -0.021 |
icol | -0.021 |
former | -0.021 |
opl | -0.020 |
destinations | -0.020 |
Token | have |
Token ID | 423 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
do | +0.052 |
ily | +0.044 |
Tom | +0.044 |
there | +0.044 |
I | +0.044 |
Neg logit contributions | |
icol | -0.120 |
former | -0.115 |
destination | -0.115 |
opl | -0.115 |
achers | -0.110 |
Token | spotted |
Token ID | 13489 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
icol | +0.001 |
opl | +0.001 |
former | +0.001 |
destination | +0.001 |
achers | +0.001 |
Neg logit contributions | |
do | -0.000 |
did | -0.000 |
there | -0.000 |
I | -0.000 |
Tom | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
icol | +0.096 |
opl | +0.092 |
former | +0.091 |
destination | +0.090 |
achers | +0.088 |
Neg logit contributions | |
do | -0.023 |
I | -0.014 |
did | -0.014 |
there | -0.014 |
Tom | -0.014 |
Token | row |
Token ID | 5752 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
do | +0.010 |
there | +0.008 |
I | +0.008 |
did | +0.008 |
kids | +0.008 |
Neg logit contributions | |
icol | -0.019 |
opl | -0.018 |
former | -0.017 |
destination | -0.017 |
achers | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
do | +0.003 |
I | +0.002 |
Tom | +0.002 |
did | +0.002 |
kids | +0.002 |
Neg logit contributions | |
icol | -0.005 |
opl | -0.005 |
destination | -0.005 |
former | -0.005 |
achers | -0.005 |
Token | books |
Token ID | 3835 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
do | +0.094 |
kids | +0.081 |
there | +0.079 |
Tom | +0.076 |
did | +0.075 |
Neg logit contributions | |
icol | -0.134 |
opl | -0.124 |
former | -0.123 |
destination | -0.121 |
achers | -0.118 |
Token | hel |
Token ID | 2978 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
do | +0.049 |
oh | +0.045 |
kids | +0.045 |
I | +0.041 |
you | +0.041 |
Neg logit contributions | |
opl | -0.127 |
destination | -0.124 |
icol | -0.122 |
en | -0.120 |
achers | -0.117 |
Token | ves |
Token ID | 1158 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
do | +0.478 |
there | +0.415 |
I | +0.413 |
did | +0.413 |
Tom | +0.412 |
Neg logit contributions | |
icol | -0.460 |
opl | -0.424 |
former | -0.420 |
destination | -0.411 |
achers | -0.392 |
Token | in |
Token ID | 287 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
icol | +0.028 |
opl | +0.026 |
former | +0.026 |
destination | +0.026 |
achers | +0.025 |
Neg logit contributions | |
do | -0.010 |
there | -0.007 |
I | -0.007 |
did | -0.007 |
Tom | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
do | +0.030 |
there | +0.020 |
Tom | +0.020 |
kids | +0.018 |
I | +0.018 |
Neg logit contributions | |
icol | -0.142 |
opl | -0.134 |
former | -0.133 |
destination | -0.130 |
achers | -0.129 |
Token | grandparents |
Token ID | 28571 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
do | +0.061 |
I | +0.051 |
Tom | +0.051 |
there | +0.051 |
kids | +0.051 |
Neg logit contributions | |
icol | -0.093 |
opl | -0.087 |
former | -0.086 |
achers | -0.083 |
destination | -0.083 |
Token | ' |
Token ID | 6 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
icol | +0.174 |
opl | +0.167 |
destination | +0.167 |
former | +0.163 |
en | +0.159 |
Neg logit contributions | |
do | -0.070 |
ily | -0.057 |
I | -0.054 |
Tom | -0.054 |
did | -0.053 |
Token | on |
Token ID | 319 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
do | +0.131 |
I | +0.106 |
did | +0.106 |
Tom | +0.106 |
there | +0.106 |
Neg logit contributions | |
icol | -0.240 |
opl | -0.227 |
former | -0.225 |
destination | -0.223 |
destinations | -0.213 |
Token | the |
Token ID | 262 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
do | +0.008 |
there | +0.006 |
Tom | +0.006 |
you | +0.005 |
I | +0.005 |
Neg logit contributions | |
icol | -0.030 |
opl | -0.028 |
former | -0.028 |
achers | -0.028 |
ric | -0.027 |
Token | row |
Token ID | 5752 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
do | +0.003 |
ily | +0.003 |
there | +0.003 |
did | +0.003 |
Tom | +0.003 |
Neg logit contributions | |
icol | -0.004 |
destination | -0.004 |
opl | -0.004 |
former | -0.004 |
destinations | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
icol | +0.014 |
opl | +0.013 |
former | +0.013 |
destination | +0.013 |
achers | +0.012 |
Neg logit contributions | |
do | -0.006 |
I | -0.005 |
there | -0.004 |
did | -0.004 |
Tom | -0.004 |
Token | books |
Token ID | 3835 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
do | +0.059 |
ily | +0.054 |
did | +0.052 |
I | +0.052 |
there | +0.049 |
Neg logit contributions | |
icol | -0.091 |
opl | -0.088 |
destination | -0.086 |
former | -0.085 |
destinations | -0.083 |
Token | hel |
Token ID | 2978 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
do | +0.041 |
kids | +0.032 |
ily | +0.030 |
Tom | +0.030 |
curious | +0.030 |
Neg logit contributions | |
icol | -0.123 |
destination | -0.120 |
opl | -0.120 |
former | -0.118 |
destinations | -0.113 |
Token | ves |
Token ID | 1158 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
do | +0.479 |
there | +0.415 |
I | +0.413 |
did | +0.412 |
Tom | +0.412 |
Neg logit contributions | |
icol | -0.461 |
opl | -0.424 |
former | -0.421 |
destination | -0.410 |
achers | -0.392 |
Token | . |
Token ID | 13 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
icol | +0.053 |
opl | +0.050 |
former | +0.050 |
destination | +0.049 |
achers | +0.048 |
Neg logit contributions | |
do | -0.022 |
I | -0.017 |
there | -0.017 |
did | -0.017 |
Tom | -0.017 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
icol | +0.008 |
opl | +0.007 |
former | +0.007 |
destination | +0.007 |
destinations | +0.007 |
Neg logit contributions | |
do | -0.005 |
did | -0.004 |
there | -0.004 |
kids | -0.004 |
oh | -0.004 |
Token | Tom |
Token ID | 13787 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
icol | +0.235 |
opl | +0.225 |
destination | +0.216 |
former | +0.210 |
achers | +0.210 |
Neg logit contributions | |
do | -0.189 |
oh | -0.158 |
curious | -0.157 |
I | -0.157 |
did | -0.157 |
Token | was |
Token ID | 373 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
do | +0.153 |
did | +0.132 |
Tom | +0.130 |
there | +0.129 |
I | +0.126 |
Neg logit contributions | |
icol | -0.235 |
former | -0.223 |
opl | -0.217 |
destination | -0.213 |
destinations | -0.206 |
Token | had |
Token ID | 550 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
do | +0.037 |
kids | +0.031 |
I | +0.031 |
Tom | +0.031 |
there | +0.031 |
Neg logit contributions | |
icol | -0.069 |
opl | -0.066 |
former | -0.065 |
destination | -0.064 |
destinations | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
icol | +0.049 |
opl | +0.047 |
former | +0.047 |
destination | +0.046 |
destinations | +0.045 |
Neg logit contributions | |
do | -0.012 |
I | -0.008 |
there | -0.008 |
did | -0.008 |
Tom | -0.008 |
Token | really |
Token ID | 1107 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
do | +0.027 |
curious | +0.023 |
brave | +0.020 |
happy | +0.019 |
there | +0.019 |
Neg logit contributions | |
opl | -0.059 |
irs | -0.059 |
icol | -0.058 |
achers | -0.058 |
ays | -0.058 |
Token | modern |
Token ID | 3660 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
icol | +0.301 |
opl | +0.283 |
former | +0.280 |
destination | +0.280 |
achers | +0.272 |
Neg logit contributions | |
do | -0.160 |
did | -0.128 |
there | -0.126 |
I | -0.126 |
curious | -0.124 |
Token | books |
Token ID | 3835 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
icol | +0.077 |
opl | +0.073 |
achers | +0.071 |
irs | +0.071 |
former | +0.069 |
Neg logit contributions | |
do | -0.052 |
kids | -0.043 |
there | -0.041 |
curious | -0.041 |
I | -0.041 |
Token | he |
Token ID | 258 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
do | +0.065 |
kids | +0.057 |
don | +0.052 |
oh | +0.051 |
Tom | +0.051 |
Neg logit contributions | |
opl | -0.156 |
icol | -0.154 |
destination | -0.151 |
former | -0.147 |
brand | -0.145 |
Token | lf |
Token ID | 1652 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
do | +0.297 |
I | +0.245 |
Tom | +0.237 |
don | +0.236 |
did | +0.233 |
Neg logit contributions | |
icol | -0.589 |
opl | -0.586 |
destination | -0.567 |
former | -0.566 |
achers | -0.554 |
Token | . |
Token ID | 13 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
do | +0.173 |
kids | +0.138 |
I | +0.137 |
did | +0.135 |
Tom | +0.134 |
Neg logit contributions | |
icol | -0.401 |
opl | -0.397 |
former | -0.392 |
destination | -0.391 |
destinations | -0.377 |
Token | He |
Token ID | 679 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
do | +0.063 |
there | +0.053 |
did | +0.053 |
I | +0.053 |
Tom | +0.053 |
Neg logit contributions | |
icol | -0.083 |
opl | -0.077 |
former | -0.076 |
destination | -0.075 |
achers | -0.072 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
do | +0.017 |
there | +0.013 |
I | +0.013 |
did | +0.013 |
Tom | +0.013 |
Neg logit contributions | |
icol | -0.039 |
opl | -0.037 |
former | -0.036 |
destination | -0.036 |
achers | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
do | +0.012 |
there | +0.010 |
Tom | +0.010 |
kids | +0.010 |
you | +0.010 |
Neg logit contributions | |
icol | -0.026 |
former | -0.025 |
opl | -0.025 |
destination | -0.024 |
achers | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
icol | +0.042 |
former | +0.039 |
opl | +0.038 |
insepar | +0.037 |
brand | +0.037 |
Neg logit contributions | |
do | -0.013 |
don | -0.010 |
I | -0.010 |
did | -0.009 |
ily | -0.009 |
Token | bad |
Token ID | 2089 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
do | +0.029 |
curious | +0.023 |
did | +0.022 |
there | +0.022 |
kids | +0.022 |
Neg logit contributions | |
icol | -0.058 |
opl | -0.057 |
achers | -0.055 |
former | -0.054 |
destination | -0.054 |
Token | tum |
Token ID | 11814 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
icol | +0.018 |
opl | +0.017 |
former | +0.017 |
destination | +0.017 |
achers | +0.017 |
Neg logit contributions | |
do | -0.013 |
did | -0.011 |
kids | -0.011 |
I | -0.010 |
there | -0.010 |
Token | my |
Token ID | 1820 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
do | +0.154 |
curious | +0.132 |
I | +0.131 |
don | +0.131 |
kids | +0.130 |
Neg logit contributions | |
opl | -0.140 |
icol | -0.131 |
ric | -0.125 |
achers | -0.124 |
former | -0.123 |
Token | ac |
Token ID | 936 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
do | +0.002 |
Tom | +0.002 |
I | +0.001 |
kids | +0.001 |
ily | +0.001 |
Neg logit contributions | |
opl | -0.002 |
icol | -0.002 |
en | -0.002 |
former | -0.002 |
brand | -0.002 |
Token | he |
Token ID | 258 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
do | +0.078 |
kids | +0.071 |
oh | +0.069 |
Tom | +0.069 |
I | +0.069 |
Neg logit contributions | |
opl | -0.109 |
achers | -0.094 |
orns | -0.088 |
acking | -0.088 |
act | -0.088 |
Token | and |
Token ID | 290 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
do | +0.280 |
Tom | +0.246 |
don | +0.239 |
I | +0.238 |
kids | +0.230 |
Neg logit contributions | |
opl | -0.569 |
icol | -0.567 |
former | -0.557 |
destination | -0.542 |
en | -0.542 |
Token | her |
Token ID | 607 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
do | +0.041 |
ily | +0.037 |
kids | +0.036 |
Tom | +0.035 |
there | +0.034 |
Neg logit contributions | |
icol | -0.079 |
former | -0.076 |
opl | -0.075 |
brand | -0.074 |
conflicts | -0.072 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
do | +0.056 |
ily | +0.048 |
I | +0.047 |
there | +0.046 |
Tom | +0.046 |
Neg logit contributions | |
icol | -0.119 |
former | -0.115 |
destination | -0.112 |
opl | -0.111 |
destinations | -0.106 |
Token | my |
Token ID | 1820 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
do | +0.066 |
I | +0.058 |
ily | +0.057 |
kids | +0.057 |
you | +0.056 |
Neg logit contributions | |
icol | -0.072 |
opl | -0.069 |
former | -0.068 |
destination | -0.067 |
achers | -0.065 |
Token | gave |
Token ID | 2921 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
do | +0.015 |
I | +0.013 |
ily | +0.012 |
kids | +0.012 |
you | +0.012 |
Neg logit contributions | |
icol | -0.024 |
opl | -0.023 |
former | -0.022 |
destination | -0.022 |
achers | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
do | +0.107 |
ily | +0.094 |
don | +0.093 |
I | +0.090 |
did | +0.088 |
Neg logit contributions | |
icol | -0.176 |
destination | -0.171 |
former | -0.169 |
opl | -0.163 |
en | -0.163 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
do | +0.036 |
ily | +0.030 |
kids | +0.029 |
I | +0.028 |
Tom | +0.028 |
Neg logit contributions | |
icol | -0.062 |
destination | -0.056 |
former | -0.056 |
brand | -0.055 |
achers | -0.054 |
Token | the |
Token ID | 262 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
do | +0.022 |
there | +0.016 |
Tom | +0.016 |
kids | +0.015 |
I | +0.015 |
Neg logit contributions | |
icol | -0.085 |
opl | -0.081 |
former | -0.081 |
destination | -0.080 |
achers | -0.077 |
Token | gloomy |
Token ID | 46400 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
do | +0.042 |
I | +0.038 |
ily | +0.037 |
Tom | +0.037 |
don | +0.036 |
Neg logit contributions | |
icol | -0.059 |
opl | -0.058 |
former | -0.056 |
destination | -0.055 |
brand | -0.054 |
Token | books |
Token ID | 3835 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
do | +0.052 |
don | +0.048 |
ily | +0.046 |
you | +0.045 |
did | +0.044 |
Neg logit contributions | |
opl | -0.063 |
icol | -0.063 |
former | -0.057 |
destination | -0.056 |
en | -0.056 |
Token | he |
Token ID | 258 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
oh | +0.082 |
kids | +0.074 |
curious | +0.070 |
do | +0.070 |
don | +0.069 |
Neg logit contributions | |
opl | -0.134 |
destination | -0.127 |
ays | -0.123 |
channels | -0.122 |
brand | -0.121 |
Token | lf |
Token ID | 1652 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
do | +0.401 |
don | +0.387 |
I | +0.375 |
curious | +0.374 |
Tom | +0.346 |
Neg logit contributions | |
opl | -0.440 |
achers | -0.426 |
en | -0.422 |
destination | -0.417 |
icol | -0.414 |
Token | . |
Token ID | 13 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
do | +0.210 |
I | +0.200 |
don | +0.193 |
oh | +0.192 |
Tom | +0.182 |
Neg logit contributions | |
destination | -0.341 |
opl | -0.332 |
en | -0.327 |
former | -0.325 |
masterpiece | -0.316 |
Token | |
Token ID | 220 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
do | +0.040 |
did | +0.030 |
ily | +0.030 |
kids | +0.030 |
you | +0.029 |
Neg logit contributions | |
icol | -0.087 |
former | -0.080 |
opl | -0.079 |
destination | -0.079 |
ilts | -0.076 |
Token |
|
Token ID | 198 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
icol | +0.022 |
opl | +0.021 |
former | +0.020 |
destination | +0.020 |
ilts | +0.020 |
Neg logit contributions | |
do | -0.012 |
did | -0.010 |
I | -0.010 |
kids | -0.010 |
oh | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
do | +0.035 |
did | +0.028 |
I | +0.028 |
kids | +0.028 |
ily | +0.027 |
Neg logit contributions | |
icol | -0.071 |
opl | -0.067 |
destination | -0.066 |
former | -0.066 |
achers | -0.064 |
Token | L |
Token ID | 43 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
do | +0.042 |
curious | +0.036 |
Tom | +0.035 |
I | +0.034 |
did | +0.034 |
Neg logit contributions | |
icol | -0.049 |
former | -0.045 |
achers | -0.045 |
en | -0.043 |
opl | -0.043 |
Token | ily |
Token ID | 813 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
do | +0.021 |
curious | +0.015 |
I | +0.012 |
did | +0.012 |
don | +0.011 |
Neg logit contributions | |
icol | -0.083 |
opl | -0.082 |
en | -0.079 |
achers | -0.079 |
irs | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
do | +0.113 |
ily | +0.098 |
oh | +0.086 |
kids | +0.085 |
there | +0.083 |
Neg logit contributions | |
icol | -0.265 |
opl | -0.247 |
destination | -0.236 |
en | -0.235 |
achers | -0.233 |
Token | your |
Token ID | 534 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
ily | +0.028 |
curious | +0.026 |
he | +0.025 |
excited | +0.024 |
lock | +0.024 |
Neg logit contributions | |
icol | -0.042 |
brand | -0.041 |
en | -0.037 |
ric | -0.036 |
destination | -0.036 |
Token | books |
Token ID | 3835 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
icol | +0.093 |
destination | +0.087 |
opl | +0.087 |
former | +0.086 |
brand | +0.084 |
Neg logit contributions | |
do | -0.055 |
I | -0.048 |
there | -0.048 |
ily | -0.048 |
you | -0.047 |
Token | he |
Token ID | 258 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
oh | +0.066 |
curious | +0.063 |
do | +0.061 |
ily | +0.060 |
kids | +0.058 |
Neg logit contributions | |
opl | -0.150 |
destination | -0.138 |
icol | -0.133 |
brand | -0.132 |
achers | -0.130 |
Token | lf |
Token ID | 1652 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
do | +0.366 |
curious | +0.329 |
don | +0.327 |
Tom | +0.326 |
ily | +0.324 |
Neg logit contributions | |
opl | -0.507 |
achers | -0.468 |
icol | -0.463 |
destination | -0.461 |
destinations | -0.432 |
Token | is |
Token ID | 318 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
do | +0.226 |
oh | +0.205 |
ily | +0.199 |
curious | +0.195 |
Tom | +0.191 |
Neg logit contributions | |
opl | -0.329 |
destination | -0.315 |
icol | -0.313 |
en | -0.297 |
former | -0.295 |
Token | very |
Token ID | 845 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
icol | +0.027 |
opl | +0.025 |
former | +0.025 |
destination | +0.025 |
achers | +0.024 |
Neg logit contributions | |
do | -0.015 |
there | -0.013 |
I | -0.013 |
did | -0.013 |
Tom | -0.012 |
Token | messy |
Token ID | 24097 |
Feature activation | +9.62e-02 |
Pos logit contributions | |
former | +0.039 |
icol | +0.039 |
brand | +0.037 |
destination | +0.037 |
opl | +0.036 |
Neg logit contributions | |
do | -0.034 |
Tom | -0.030 |
ily | -0.030 |
kids | -0.029 |
oh | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
icol | +0.010 |
opl | +0.009 |
destination | +0.009 |
former | +0.009 |
en | +0.009 |
Neg logit contributions | |
do | -0.005 |
did | -0.004 |
ily | -0.004 |
Tom | -0.004 |
don | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
do | +0.010 |
ily | +0.009 |
kids | +0.008 |
there | +0.007 |
Tom | +0.007 |
Neg logit contributions | |
icol | -0.024 |
opl | -0.023 |
destination | -0.023 |
achers | -0.023 |
en | -0.022 |
Token | you |
Token ID | 345 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ily | +0.025 |
curious | +0.023 |
he | +0.021 |
do | +0.020 |
kids | +0.018 |
Neg logit contributions | |
icol | -0.069 |
destination | -0.066 |
ric | -0.065 |
brand | -0.064 |
en | -0.064 |
Token | need |
Token ID | 761 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
do | +0.103 |
Tom | +0.103 |
oh | +0.101 |
ily | +0.099 |
kids | +0.096 |
Neg logit contributions | |
icol | -0.106 |
destination | -0.103 |
former | -0.102 |
ilts | -0.100 |
ric | -0.097 |
Token | to |
Token ID | 284 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
icol | +0.107 |
opl | +0.105 |
former | +0.100 |
destination | +0.098 |
ric | +0.096 |
Neg logit contributions | |
do | -0.051 |
I | -0.042 |
you | -0.042 |
there | -0.041 |
kids | -0.039 |
Token | bat |
Token ID | 7365 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
former | +0.008 |
icol | +0.008 |
destination | +0.008 |
en | +0.008 |
opl | +0.008 |
Neg logit contributions | |
do | -0.004 |
Tom | -0.004 |
ily | -0.004 |
I | -0.003 |
did | -0.003 |
Token | he |
Token ID | 258 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
icol | +0.175 |
opl | +0.172 |
destination | +0.167 |
achers | +0.167 |
former | +0.166 |
Neg logit contributions | |
do | -0.052 |
curious | -0.039 |
I | -0.039 |
Tom | -0.037 |
did | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
do | +0.280 |
Tom | +0.238 |
don | +0.216 |
curious | +0.215 |
did | +0.214 |
Neg logit contributions | |
opl | -0.564 |
former | -0.556 |
icol | -0.555 |
destination | -0.545 |
achers | -0.542 |
Token | You |
Token ID | 921 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
do | +0.059 |
did | +0.050 |
there | +0.049 |
ily | +0.048 |
kids | +0.047 |
Neg logit contributions | |
icol | -0.085 |
opl | -0.081 |
former | -0.080 |
destination | -0.076 |
ric | -0.076 |
Token | are |
Token ID | 389 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
do | +0.024 |
Tom | +0.023 |
ily | +0.023 |
oh | +0.022 |
kids | +0.022 |
Neg logit contributions | |
icol | -0.032 |
destination | -0.032 |
former | -0.031 |
opl | -0.030 |
ric | -0.030 |
Token | too |
Token ID | 1165 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
do | +0.121 |
Tom | +0.097 |
ily | +0.097 |
did | +0.096 |
I | +0.096 |
Neg logit contributions | |
icol | -0.220 |
opl | -0.209 |
former | -0.209 |
destination | -0.205 |
achers | -0.198 |
Token | dirty |
Token ID | 11841 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
do | +0.062 |
ily | +0.051 |
Tom | +0.051 |
did | +0.050 |
I | +0.050 |
Neg logit contributions | |
icol | -0.115 |
opl | -0.109 |
former | -0.109 |
destination | -0.106 |
ilts | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
icol | +0.133 |
opl | +0.126 |
former | +0.125 |
destination | +0.123 |
achers | +0.120 |
Neg logit contributions | |
do | -0.051 |
there | -0.039 |
I | -0.039 |
Tom | -0.038 |
did | -0.038 |
Token | All |
Token ID | 1439 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
do | +0.070 |
did | +0.060 |
you | +0.058 |
oh | +0.058 |
don | +0.058 |
Neg logit contributions | |
icol | -0.084 |
opl | -0.078 |
alks | -0.076 |
former | -0.074 |
aters | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
do | +0.064 |
Tom | +0.045 |
did | +0.044 |
ily | +0.044 |
there | +0.044 |
Neg logit contributions | |
icol | -0.178 |
opl | -0.176 |
destination | -0.167 |
former | -0.167 |
en | -0.166 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
do | +0.026 |
kids | +0.018 |
there | +0.018 |
I | +0.018 |
did | +0.018 |
Neg logit contributions | |
icol | -0.089 |
opl | -0.084 |
former | -0.084 |
destination | -0.083 |
achers | -0.080 |
Token | clot |
Token ID | 5148 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
icol | +0.068 |
opl | +0.065 |
former | +0.065 |
destination | +0.062 |
achers | +0.060 |
Neg logit contributions | |
do | -0.046 |
kids | -0.040 |
there | -0.040 |
I | -0.038 |
did | -0.038 |
Token | he |
Token ID | 258 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
do | +0.070 |
curious | +0.052 |
kids | +0.052 |
Tom | +0.052 |
don | +0.050 |
Neg logit contributions | |
opl | -0.198 |
icol | -0.193 |
achers | -0.186 |
destination | -0.184 |
en | -0.181 |
Token | es |
Token ID | 274 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
do | +0.304 |
Tom | +0.246 |
I | +0.244 |
there | +0.240 |
did | +0.237 |
Neg logit contributions | |
icol | -0.604 |
opl | -0.574 |
former | -0.563 |
destination | -0.562 |
achers | -0.550 |
Token | were |
Token ID | 547 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
do | +0.144 |
Tom | +0.110 |
I | +0.109 |
there | +0.107 |
ily | +0.106 |
Neg logit contributions | |
icol | -0.379 |
opl | -0.363 |
former | -0.358 |
destination | -0.355 |
achers | -0.344 |
Token | marching |
Token ID | 26409 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
do | +0.105 |
there | +0.088 |
kids | +0.082 |
did | +0.081 |
I | +0.080 |
Neg logit contributions | |
icol | -0.247 |
opl | -0.229 |
former | -0.228 |
destination | -0.220 |
achers | -0.219 |
Token | down |
Token ID | 866 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
icol | +0.224 |
opl | +0.213 |
former | +0.211 |
destination | +0.206 |
achers | +0.202 |
Neg logit contributions | |
do | -0.088 |
there | -0.068 |
did | -0.066 |
I | -0.066 |
Tom | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
do | +0.014 |
there | +0.009 |
Tom | +0.008 |
kids | +0.008 |
I | +0.008 |
Neg logit contributions | |
icol | -0.081 |
opl | -0.076 |
former | -0.076 |
destination | -0.074 |
achers | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
do | +0.068 |
oh | +0.065 |
kids | +0.064 |
don | +0.061 |
I | +0.061 |
Neg logit contributions | |
opl | -0.118 |
destination | -0.117 |
former | -0.110 |
brand | -0.109 |
destinations | -0.109 |
Token | had |
Token ID | 550 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ily | +0.040 |
there | +0.034 |
do | +0.034 |
I | +0.033 |
Tom | +0.032 |
Neg logit contributions | |
icol | -0.087 |
former | -0.084 |
opl | -0.080 |
destination | -0.080 |
destinations | -0.078 |
Token | a |
Token ID | 257 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
icol | +0.043 |
former | +0.040 |
destination | +0.040 |
opl | +0.040 |
destinations | +0.039 |
Neg logit contributions | |
do | -0.019 |
don | -0.015 |
I | -0.015 |
ily | -0.015 |
did | -0.014 |
Token | big |
Token ID | 1263 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
do | +0.033 |
curious | +0.026 |
there | +0.026 |
did | +0.026 |
kids | +0.026 |
Neg logit contributions | |
icol | -0.057 |
opl | -0.056 |
achers | -0.055 |
former | -0.054 |
en | -0.053 |
Token | books |
Token ID | 3835 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
icol | +0.059 |
former | +0.056 |
opl | +0.056 |
destination | +0.054 |
achers | +0.054 |
Neg logit contributions | |
do | -0.033 |
did | -0.026 |
Tom | -0.026 |
kids | -0.026 |
there | -0.026 |
Token | he |
Token ID | 258 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
do | +0.055 |
kids | +0.049 |
oh | +0.049 |
don | +0.046 |
did | +0.043 |
Neg logit contributions | |
opl | -0.143 |
destination | -0.141 |
icol | -0.139 |
former | -0.136 |
brand | -0.131 |
Token | lf |
Token ID | 1652 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
do | +0.341 |
I | +0.312 |
don | +0.306 |
Tom | +0.301 |
you | +0.284 |
Neg logit contributions | |
opl | -0.513 |
icol | -0.497 |
destination | -0.484 |
former | -0.479 |
achers | -0.479 |
Token | in |
Token ID | 287 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
do | +0.182 |
don | +0.153 |
I | +0.150 |
kids | +0.150 |
Tom | +0.147 |
Neg logit contributions | |
former | -0.361 |
destination | -0.357 |
opl | -0.356 |
icol | -0.353 |
destinations | -0.344 |
Token | her |
Token ID | 607 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
do | +0.058 |
did | +0.046 |
I | +0.044 |
there | +0.043 |
ily | +0.043 |
Neg logit contributions | |
icol | -0.137 |
opl | -0.132 |
former | -0.130 |
destination | -0.129 |
destinations | -0.124 |
Token | room |
Token ID | 2119 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
do | +0.080 |
ily | +0.067 |
I | +0.067 |
don | +0.066 |
did | +0.066 |
Neg logit contributions | |
icol | -0.116 |
opl | -0.110 |
former | -0.109 |
destination | -0.108 |
destinations | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
do | +0.074 |
I | +0.055 |
did | +0.055 |
Tom | +0.054 |
ily | +0.054 |
Neg logit contributions | |
icol | -0.200 |
opl | -0.192 |
former | -0.192 |
destination | -0.190 |
destinations | -0.182 |
Token | it |
Token ID | 340 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
icol | +0.047 |
opl | +0.047 |
former | +0.046 |
destination | +0.044 |
achers | +0.044 |
Neg logit contributions | |
do | -0.009 |
Tom | -0.007 |
there | -0.007 |
did | -0.006 |
I | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
do | +0.036 |
did | +0.030 |
there | +0.029 |
Tom | +0.028 |
ily | +0.028 |
Neg logit contributions | |
icol | -0.076 |
opl | -0.074 |
former | -0.072 |
destination | -0.069 |
ric | -0.068 |
Token | time |
Token ID | 640 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
icol | +0.082 |
opl | +0.077 |
former | +0.076 |
achers | +0.073 |
destination | +0.072 |
Neg logit contributions | |
do | -0.064 |
there | -0.059 |
Tom | -0.057 |
did | -0.056 |
kids | -0.054 |
Token | to |
Token ID | 284 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
icol | +0.203 |
destination | +0.184 |
former | +0.181 |
opl | +0.181 |
alks | +0.174 |
Neg logit contributions | |
do | -0.154 |
kids | -0.130 |
I | -0.130 |
ily | -0.128 |
did | -0.126 |
Token | bat |
Token ID | 7365 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
icol | +0.033 |
destination | +0.031 |
opl | +0.031 |
former | +0.031 |
en | +0.029 |
Neg logit contributions | |
do | -0.015 |
I | -0.013 |
ily | -0.013 |
there | -0.013 |
oh | -0.012 |
Token | he |
Token ID | 258 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
icol | +0.194 |
opl | +0.187 |
former | +0.183 |
destination | +0.182 |
achers | +0.180 |
Neg logit contributions | |
do | -0.052 |
I | -0.036 |
did | -0.035 |
Tom | -0.035 |
kids | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
do | +0.290 |
I | +0.235 |
don | +0.231 |
did | +0.229 |
kids | +0.228 |
Neg logit contributions | |
icol | -0.569 |
former | -0.564 |
destination | -0.555 |
opl | -0.548 |
en | -0.532 |
Token | Fl |
Token ID | 1610 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
do | +0.031 |
Tom | +0.026 |
I | +0.026 |
there | +0.026 |
did | +0.026 |
Neg logit contributions | |
icol | -0.045 |
opl | -0.043 |
former | -0.042 |
destination | -0.041 |
achers | -0.040 |
Token | uffy |
Token ID | 15352 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
do | +0.084 |
I | +0.075 |
there | +0.075 |
Tom | +0.075 |
did | +0.074 |
Neg logit contributions | |
icol | -0.050 |
former | -0.047 |
opl | -0.046 |
destination | -0.044 |
achers | -0.042 |
Token | said |
Token ID | 531 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
icol | +0.083 |
destination | +0.077 |
former | +0.076 |
opl | +0.075 |
achers | +0.074 |
Neg logit contributions | |
do | -0.042 |
I | -0.035 |
ily | -0.035 |
there | -0.034 |
you | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
do | +0.033 |
kids | +0.027 |
ily | +0.025 |
children | +0.025 |
did | +0.025 |
Neg logit contributions | |
icol | -0.056 |
destination | -0.050 |
brand | -0.049 |
lifelong | -0.048 |
insepar | -0.048 |
Token | room |
Token ID | 2119 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
do | +0.067 |
there | +0.057 |
I | +0.056 |
kids | +0.055 |
Tom | +0.055 |
Neg logit contributions | |
icol | -0.122 |
opl | -0.119 |
former | -0.114 |
achers | -0.114 |
ilts | -0.111 |
Token | and |
Token ID | 290 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
do | +0.088 |
ily | +0.071 |
I | +0.069 |
did | +0.067 |
don | +0.067 |
Neg logit contributions | |
icol | -0.188 |
destination | -0.183 |
former | -0.181 |
opl | -0.173 |
destinations | -0.169 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
do | +0.048 |
ily | +0.042 |
kids | +0.041 |
Tom | +0.038 |
oh | +0.037 |
Neg logit contributions | |
icol | -0.069 |
destination | -0.065 |
former | -0.064 |
opl | -0.060 |
en | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
do | +0.023 |
did | +0.017 |
I | +0.016 |
don | +0.016 |
ily | +0.015 |
Neg logit contributions | |
icol | -0.072 |
former | -0.069 |
opl | -0.068 |
destination | -0.067 |
brand | -0.065 |
Token | books |
Token ID | 3835 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
do | +0.042 |
there | +0.035 |
I | +0.035 |
kids | +0.035 |
did | +0.035 |
Neg logit contributions | |
icol | -0.053 |
opl | -0.049 |
former | -0.048 |
destination | -0.048 |
achers | -0.046 |
Token | he |
Token ID | 258 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
oh | +0.064 |
kids | +0.059 |
do | +0.057 |
Tom | +0.054 |
ily | +0.053 |
Neg logit contributions | |
destination | -0.127 |
opl | -0.126 |
en | -0.119 |
brand | -0.119 |
ays | -0.116 |
Token | lf |
Token ID | 1652 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
do | +0.345 |
I | +0.313 |
don | +0.308 |
curious | +0.306 |
Tom | +0.299 |
Neg logit contributions | |
opl | -0.498 |
icol | -0.493 |
destination | -0.493 |
en | -0.482 |
achers | -0.473 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
do | +0.180 |
I | +0.164 |
don | +0.156 |
oh | +0.156 |
ily | +0.154 |
Neg logit contributions | |
destination | -0.365 |
former | -0.354 |
opl | -0.346 |
en | -0.345 |
icol | -0.341 |
Token | It |
Token ID | 632 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
do | +0.058 |
did | +0.046 |
you | +0.045 |
there | +0.044 |
kids | +0.044 |
Neg logit contributions | |
icol | -0.104 |
former | -0.099 |
destination | -0.096 |
opl | -0.096 |
alks | -0.094 |
Token | was |
Token ID | 373 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
do | +0.088 |
Tom | +0.070 |
I | +0.070 |
kids | +0.070 |
ily | +0.069 |
Neg logit contributions | |
icol | -0.180 |
opl | -0.170 |
former | -0.169 |
destination | -0.167 |
achers | -0.161 |
Token | brown |
Token ID | 7586 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
icol | +0.069 |
opl | +0.065 |
achers | +0.064 |
former | +0.063 |
destination | +0.062 |
Neg logit contributions | |
do | -0.027 |
there | -0.023 |
did | -0.021 |
Tom | -0.021 |
curious | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
do | +0.055 |
there | +0.046 |
Tom | +0.043 |
I | +0.043 |
did | +0.042 |
Neg logit contributions | |
icol | -0.104 |
opl | -0.101 |
former | -0.099 |
destination | -0.095 |
ric | -0.094 |
Token | the |
Token ID | 262 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
destination | +0.021 |
icol | +0.020 |
former | +0.020 |
destinations | +0.019 |
irs | +0.019 |
Neg logit contributions | |
ily | -0.010 |
did | -0.010 |
do | -0.009 |
I | -0.009 |
oh | -0.008 |
Token | river |
Token ID | 7850 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
do | +0.051 |
did | +0.045 |
Tom | +0.045 |
ily | +0.045 |
I | +0.044 |
Neg logit contributions | |
icol | -0.056 |
former | -0.052 |
destination | -0.052 |
opl | -0.051 |
destinations | -0.049 |
Token | to |
Token ID | 284 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
icol | +0.094 |
opl | +0.090 |
former | +0.090 |
destination | +0.089 |
achers | +0.086 |
Neg logit contributions | |
do | -0.038 |
ily | -0.030 |
I | -0.030 |
did | -0.030 |
Tom | -0.029 |
Token | bat |
Token ID | 7365 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
icol | +0.023 |
destination | +0.023 |
former | +0.023 |
opl | +0.022 |
en | +0.021 |
Neg logit contributions | |
ily | -0.012 |
do | -0.012 |
did | -0.011 |
I | -0.011 |
kids | -0.011 |
Token | he |
Token ID | 258 |
Feature activation | -5.75e+00 |
Pos logit contributions | |
opl | +0.191 |
icol | +0.190 |
achers | +0.185 |
en | +0.182 |
destination | +0.182 |
Neg logit contributions | |
do | -0.066 |
curious | -0.054 |
Tom | -0.052 |
I | -0.051 |
did | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
do | +0.291 |
Tom | +0.259 |
don | +0.253 |
did | +0.240 |
I | +0.239 |
Neg logit contributions | |
former | -0.533 |
en | -0.525 |
opl | -0.523 |
icol | -0.522 |
destination | -0.521 |
Token | She |
Token ID | 1375 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
do | +0.052 |
did | +0.044 |
ily | +0.044 |
kids | +0.043 |
there | +0.042 |
Neg logit contributions | |
icol | -0.078 |
destination | -0.070 |
opl | -0.070 |
former | -0.070 |
destinations | -0.066 |
Token | laughed |
Token ID | 13818 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
do | +0.028 |
I | +0.022 |
there | +0.022 |
Tom | +0.022 |
did | +0.022 |
Neg logit contributions | |
icol | -0.052 |
opl | -0.049 |
former | -0.049 |
destination | -0.048 |
achers | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
do | +0.009 |
I | +0.007 |
kids | +0.007 |
ily | +0.007 |
you | +0.007 |
Neg logit contributions | |
icol | -0.019 |
destination | -0.017 |
en | -0.017 |
former | -0.017 |
brand | -0.016 |
Token | spl |
Token ID | 4328 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
do | +0.027 |
ily | +0.023 |
I | +0.022 |
kids | +0.022 |
you | +0.022 |
Neg logit contributions | |
icol | -0.046 |
opl | -0.040 |
former | -0.040 |
destination | -0.040 |
en | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
do | +0.039 |
ily | +0.029 |
did | +0.028 |
there | +0.027 |
kids | +0.027 |
Neg logit contributions | |
icol | -0.120 |
opl | -0.112 |
destination | -0.111 |
former | -0.110 |
achers | -0.108 |
Token | Post |
Token ID | 2947 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
do | +0.019 |
ily | +0.018 |
did | +0.015 |
curious | +0.013 |
kids | +0.013 |
Neg logit contributions | |
icol | -0.047 |
destination | -0.045 |
opl | -0.044 |
former | -0.043 |
destinations | -0.042 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
icol | +0.020 |
opl | +0.019 |
former | +0.019 |
destination | +0.018 |
achers | +0.018 |
Neg logit contributions | |
do | -0.015 |
I | -0.013 |
there | -0.013 |
Tom | -0.013 |
kids | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
do | +0.086 |
ily | +0.073 |
did | +0.072 |
I | +0.072 |
Tom | +0.071 |
Neg logit contributions | |
icol | -0.122 |
opl | -0.114 |
former | -0.113 |
destination | -0.111 |
destinations | -0.107 |
Token | bat |
Token ID | 7365 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
opl | +0.027 |
icol | +0.027 |
former | +0.027 |
en | +0.026 |
destination | +0.025 |
Neg logit contributions | |
there | -0.018 |
oh | -0.017 |
ily | -0.017 |
Tom | -0.017 |
kids | -0.017 |
Token | he |
Token ID | 258 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
opl | +0.211 |
icol | +0.208 |
achers | +0.200 |
former | +0.197 |
destination | +0.196 |
Neg logit contributions | |
do | -0.067 |
I | -0.054 |
Tom | -0.053 |
curious | -0.052 |
did | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
do | +0.278 |
Tom | +0.248 |
I | +0.240 |
there | +0.224 |
ily | +0.223 |
Neg logit contributions | |
opl | -0.563 |
icol | -0.556 |
former | -0.544 |
en | -0.535 |
achers | -0.528 |
Token | He |
Token ID | 679 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
do | +0.037 |
I | +0.029 |
Tom | +0.029 |
there | +0.029 |
did | +0.029 |
Neg logit contributions | |
icol | -0.081 |
former | -0.076 |
opl | -0.076 |
destination | -0.074 |
achers | -0.072 |
Token | would |
Token ID | 561 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
do | +0.008 |
did | +0.007 |
there | +0.007 |
I | +0.007 |
kids | +0.007 |
Neg logit contributions | |
icol | -0.012 |
opl | -0.011 |
former | -0.011 |
destination | -0.011 |
achers | -0.010 |
Token | find |
Token ID | 1064 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
icol | +0.246 |
opl | +0.233 |
former | +0.230 |
destination | +0.227 |
achers | +0.220 |
Neg logit contributions | |
do | -0.122 |
I | -0.093 |
did | -0.091 |
there | -0.090 |
you | -0.089 |
Token | a |
Token ID | 257 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
do | +0.038 |
there | +0.030 |
kids | +0.030 |
Tom | +0.029 |
ily | +0.027 |
Neg logit contributions | |
icol | -0.112 |
opl | -0.106 |
former | -0.105 |
destination | -0.104 |
achers | -0.102 |
Token | Together |
Token ID | 17083 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
icol | +0.014 |
opl | +0.013 |
former | +0.013 |
destination | +0.013 |
achers | +0.013 |
Neg logit contributions | |
do | -0.008 |
did | -0.006 |
there | -0.006 |
kids | -0.006 |
I | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
icol | +0.208 |
destination | +0.196 |
opl | +0.195 |
former | +0.195 |
destinations | +0.187 |
Neg logit contributions | |
do | -0.071 |
I | -0.052 |
ily | -0.052 |
did | -0.051 |
kids | -0.050 |
Token | they |
Token ID | 484 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
icol | +0.033 |
destination | +0.031 |
former | +0.031 |
opl | +0.031 |
destinations | +0.030 |
Neg logit contributions | |
do | -0.016 |
ily | -0.014 |
did | -0.012 |
I | -0.012 |
curious | -0.011 |
Token | made |
Token ID | 925 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
icol | +0.085 |
opl | +0.079 |
former | +0.079 |
destination | +0.078 |
achers | +0.075 |
Neg logit contributions | |
do | -0.066 |
I | -0.056 |
there | -0.055 |
Tom | -0.055 |
kids | -0.055 |
Token | their |
Token ID | 511 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
icol | +0.213 |
opl | +0.201 |
former | +0.200 |
destination | +0.200 |
destinations | +0.192 |
Neg logit contributions | |
do | -0.072 |
I | -0.056 |
did | -0.054 |
ily | -0.053 |
there | -0.052 |
Token | way |
Token ID | 835 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
icol | +0.016 |
opl | +0.015 |
achers | +0.014 |
former | +0.014 |
ilts | +0.014 |
Neg logit contributions | |
do | -0.015 |
kids | -0.013 |
did | -0.012 |
there | -0.012 |
Tom | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
icol | +0.348 |
opl | +0.335 |
former | +0.324 |
destination | +0.307 |
achers | +0.305 |
Neg logit contributions | |
do | -0.210 |
there | -0.185 |
Tom | -0.169 |
I | -0.169 |
kids | -0.167 |
Token | a |
Token ID | 257 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
icol | +0.085 |
former | +0.084 |
destination | +0.083 |
opl | +0.082 |
ric | +0.078 |
Neg logit contributions | |
do | -0.029 |
ily | -0.025 |
I | -0.025 |
did | -0.024 |
there | -0.023 |
Token | quiet |
Token ID | 5897 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
icol | +0.038 |
opl | +0.037 |
aters | +0.035 |
ays | +0.035 |
achers | +0.034 |
Neg logit contributions | |
do | -0.025 |
there | -0.021 |
you | -0.020 |
kids | -0.020 |
curious | -0.019 |
Token | spot |
Token ID | 4136 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
do | +0.045 |
there | +0.039 |
kids | +0.038 |
I | +0.037 |
did | +0.037 |
Neg logit contributions | |
icol | -0.061 |
opl | -0.058 |
former | -0.056 |
destination | -0.054 |
achers | -0.053 |
Token | on |
Token ID | 319 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
do | +0.021 |
I | +0.016 |
did | +0.015 |
Tom | +0.015 |
there | +0.015 |
Neg logit contributions | |
icol | -0.055 |
opl | -0.052 |
former | -0.052 |
destination | -0.051 |
achers | -0.049 |
Token | leather |
Token ID | 11620 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
do | +0.019 |
I | +0.015 |
kids | +0.015 |
there | +0.015 |
Tom | +0.015 |
Neg logit contributions | |
icol | -0.027 |
former | -0.026 |
opl | -0.026 |
destination | -0.025 |
destinations | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
icol | +0.132 |
opl | +0.128 |
former | +0.128 |
destinations | +0.120 |
destination | +0.119 |
Neg logit contributions | |
do | -0.080 |
there | -0.067 |
I | -0.066 |
kids | -0.065 |
Tom | -0.064 |
Token | surprised |
Token ID | 6655 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
do | +0.017 |
ily | +0.015 |
kids | +0.015 |
I | +0.014 |
Tom | +0.014 |
Neg logit contributions | |
icol | -0.027 |
destination | -0.024 |
former | -0.024 |
brand | -0.023 |
opl | -0.023 |
Token | Sammy |
Token ID | 44067 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
icol | +0.063 |
opl | +0.062 |
former | +0.061 |
destination | +0.059 |
achers | +0.058 |
Neg logit contributions | |
do | -0.032 |
Tom | -0.027 |
kids | -0.027 |
there | -0.027 |
I | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
icol | +0.368 |
destination | +0.358 |
en | +0.341 |
former | +0.334 |
opl | +0.330 |
Neg logit contributions | |
do | -0.215 |
ily | -0.196 |
I | -0.193 |
kids | -0.188 |
Tom | -0.186 |
Token | Sammy |
Token ID | 44067 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
do | +0.014 |
Tom | +0.013 |
I | +0.012 |
there | +0.011 |
did | +0.011 |
Neg logit contributions | |
opl | -0.035 |
icol | -0.034 |
former | -0.033 |
destination | -0.033 |
achers | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
icol | +0.373 |
destination | +0.348 |
opl | +0.334 |
achers | +0.333 |
en | +0.331 |
Neg logit contributions | |
do | -0.226 |
ily | -0.195 |
I | -0.192 |
kids | -0.189 |
Tom | -0.187 |
Token | so |
Token ID | 523 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
icol | +0.124 |
opl | +0.117 |
former | +0.116 |
destination | +0.114 |
achers | +0.111 |
Neg logit contributions | |
do | -0.052 |
there | -0.040 |
I | -0.040 |
did | -0.040 |
Tom | -0.040 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
icol | +0.044 |
former | +0.043 |
opl | +0.043 |
lifelong | +0.042 |
destination | +0.042 |
Neg logit contributions | |
do | -0.018 |
oh | -0.014 |
ily | -0.014 |
I | -0.014 |
Tom | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
do | +0.100 |
I | +0.077 |
did | +0.077 |
ily | +0.077 |
kids | +0.076 |
Neg logit contributions | |
icol | -0.220 |
opl | -0.207 |
former | -0.205 |
destination | -0.203 |
achers | -0.196 |
Token | see |
Token ID | 766 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
icol | +0.064 |
opl | +0.060 |
former | +0.060 |
destination | +0.059 |
achers | +0.058 |
Neg logit contributions | |
do | -0.018 |
I | -0.012 |
there | -0.012 |
Tom | -0.012 |
did | -0.012 |
Token | from |
Token ID | 422 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
do | +0.043 |
there | +0.033 |
Tom | +0.032 |
did | +0.032 |
I | +0.032 |
Neg logit contributions | |
icol | -0.114 |
opl | -0.109 |
former | -0.108 |
destination | -0.106 |
achers | -0.103 |
Token | far |
Token ID | 1290 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
do | +0.056 |
there | +0.042 |
Tom | +0.042 |
kids | +0.038 |
I | +0.037 |
Neg logit contributions | |
icol | -0.192 |
opl | -0.184 |
former | -0.181 |
destination | -0.177 |
achers | -0.177 |
Token | away |
Token ID | 1497 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
do | +0.032 |
there | +0.030 |
Tom | +0.028 |
you | +0.028 |
kids | +0.027 |
Neg logit contributions | |
former | -0.038 |
icol | -0.038 |
opl | -0.038 |
ric | -0.035 |
sym | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
icol | +0.198 |
opl | +0.189 |
former | +0.187 |
destination | +0.182 |
achers | +0.179 |
Neg logit contributions | |
do | -0.063 |
there | -0.048 |
Tom | -0.045 |
I | -0.045 |
did | -0.044 |
Token | Rob |
Token ID | 3851 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
do | +0.004 |
Tom | +0.003 |
I | +0.003 |
there | +0.003 |
did | +0.003 |
Neg logit contributions | |
icol | -0.007 |
opl | -0.006 |
former | -0.006 |
destination | -0.006 |
achers | -0.006 |
Token | by |
Token ID | 1525 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
icol | +0.024 |
opl | +0.023 |
former | +0.023 |
destination | +0.022 |
achers | +0.021 |
Neg logit contributions | |
do | -0.013 |
did | -0.011 |
there | -0.011 |
Tom | -0.011 |
I | -0.011 |
Token | looked |
Token ID | 3114 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
icol | +0.452 |
destination | +0.419 |
former | +0.418 |
opl | +0.414 |
achers | +0.402 |
Neg logit contributions | |
do | -0.247 |
I | -0.202 |
Tom | -0.199 |
ily | -0.198 |
there | -0.197 |
Token | up |
Token ID | 510 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
opl | +0.067 |
icol | +0.067 |
former | +0.065 |
alks | +0.063 |
achers | +0.063 |
Neg logit contributions | |
do | -0.030 |
there | -0.030 |
curious | -0.027 |
Tom | -0.024 |
happy | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
icol | +0.219 |
opl | +0.215 |
former | +0.208 |
achers | +0.204 |
ric | +0.203 |
Neg logit contributions | |
do | -0.054 |
there | -0.046 |
Tom | -0.038 |
curious | -0.036 |
did | -0.036 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
icol | +0.002 |
destination | +0.002 |
former | +0.002 |
opl | +0.002 |
brand | +0.001 |
Neg logit contributions | |
do | -0.001 |
ily | -0.001 |
kids | -0.001 |
I | -0.001 |
you | -0.001 |
Token | his |
Token ID | 465 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
do | +0.002 |
I | +0.001 |
did | +0.001 |
there | +0.001 |
Tom | +0.001 |
Neg logit contributions | |
icol | -0.006 |
opl | -0.006 |
former | -0.006 |
destination | -0.006 |
achers | -0.005 |
Token | thing |
Token ID | 1517 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
opl | +0.089 |
former | +0.089 |
icol | +0.088 |
destination | +0.087 |
particularly | +0.085 |
Neg logit contributions | |
do | -0.089 |
Tom | -0.081 |
ily | -0.078 |
I | -0.078 |
kids | -0.078 |
Token | that |
Token ID | 326 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
icol | +0.077 |
opl | +0.073 |
former | +0.073 |
destination | +0.070 |
achers | +0.069 |
Neg logit contributions | |
do | -0.034 |
there | -0.027 |
I | -0.027 |
did | -0.027 |
Tom | -0.027 |
Token | it |
Token ID | 340 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
icol | +0.020 |
opl | +0.020 |
destination | +0.019 |
former | +0.019 |
destinations | +0.018 |
Neg logit contributions | |
do | -0.012 |
ily | -0.010 |
kids | -0.010 |
Tom | -0.009 |
I | -0.009 |
Token | noticed |
Token ID | 6810 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
do | +0.032 |
there | +0.026 |
I | +0.026 |
did | +0.026 |
Tom | +0.026 |
Neg logit contributions | |
icol | -0.063 |
opl | -0.059 |
former | -0.059 |
destination | -0.058 |
achers | -0.056 |
Token | was |
Token ID | 373 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
do | +0.009 |
there | +0.007 |
Tom | +0.007 |
did | +0.007 |
I | +0.007 |
Neg logit contributions | |
icol | -0.025 |
opl | -0.023 |
former | -0.023 |
destination | -0.022 |
achers | -0.022 |
Token | particularly |
Token ID | 3573 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
icol | +0.128 |
opl | +0.122 |
achers | +0.119 |
irs | +0.115 |
ilts | +0.115 |
Neg logit contributions | |
do | -0.025 |
there | -0.020 |
a | -0.016 |
did | -0.016 |
Tom | -0.015 |
Token | funny |
Token ID | 8258 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
icol | +0.404 |
former | +0.392 |
opl | +0.386 |
destination | +0.377 |
destinations | +0.363 |
Neg logit contributions | |
do | -0.263 |
Tom | -0.225 |
I | -0.225 |
did | -0.218 |
kids | -0.217 |
Token | . |
Token ID | 13 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
icol | +0.052 |
opl | +0.050 |
former | +0.049 |
destination | +0.049 |
achers | +0.047 |
Neg logit contributions | |
do | -0.020 |
there | -0.015 |
I | -0.015 |
did | -0.014 |
kids | -0.014 |
Token | A |
Token ID | 317 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
do | +0.018 |
did | +0.014 |
there | +0.014 |
kids | +0.014 |
ily | +0.014 |
Neg logit contributions | |
icol | -0.032 |
opl | -0.030 |
former | -0.030 |
destination | -0.030 |
destinations | -0.029 |
Token | small |
Token ID | 1402 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
icol | +0.112 |
opl | +0.107 |
former | +0.106 |
destination | +0.104 |
achers | +0.101 |
Neg logit contributions | |
do | -0.050 |
there | -0.039 |
I | -0.039 |
did | -0.039 |
kids | -0.039 |
Token | dog |
Token ID | 3290 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
icol | +0.006 |
opl | +0.006 |
former | +0.006 |
destination | +0.005 |
achers | +0.005 |
Neg logit contributions | |
do | -0.003 |
did | -0.003 |
I | -0.003 |
there | -0.003 |
Tom | -0.003 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
do | +0.047 |
oh | +0.040 |
I | +0.038 |
ily | +0.038 |
kids | +0.037 |
Neg logit contributions | |
icol | -0.102 |
opl | -0.099 |
en | -0.095 |
achers | -0.093 |
destination | -0.093 |
Token | to |
Token ID | 284 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
do | +0.104 |
did | +0.087 |
there | +0.086 |
I | +0.086 |
ily | +0.086 |
Neg logit contributions | |
icol | -0.154 |
opl | -0.144 |
former | -0.143 |
destination | -0.140 |
destinations | -0.135 |
Token | play |
Token ID | 711 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
icol | +0.008 |
opl | +0.008 |
former | +0.008 |
destination | +0.008 |
en | +0.007 |
Neg logit contributions | |
do | -0.005 |
there | -0.004 |
did | -0.004 |
ily | -0.004 |
kids | -0.004 |
Token | dress |
Token ID | 6576 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
do | +0.023 |
I | +0.020 |
did | +0.019 |
don | +0.019 |
Tom | +0.019 |
Neg logit contributions | |
icol | -0.054 |
former | -0.051 |
destination | -0.051 |
opl | -0.051 |
en | -0.049 |
Token | - |
Token ID | 12 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
do | +0.035 |
I | +0.030 |
did | +0.030 |
Tom | +0.030 |
there | +0.030 |
Neg logit contributions | |
icol | -0.041 |
opl | -0.038 |
former | -0.038 |
destination | -0.037 |
achers | -0.036 |
Token | up |
Token ID | 929 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
do | +0.192 |
there | +0.171 |
I | +0.171 |
did | +0.170 |
Tom | +0.170 |
Neg logit contributions | |
icol | -0.117 |
opl | -0.105 |
former | -0.104 |
destination | -0.101 |
achers | -0.094 |
Token | with |
Token ID | 351 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
icol | +0.313 |
destination | +0.298 |
former | +0.298 |
opl | +0.298 |
en | +0.290 |
Neg logit contributions | |
do | -0.146 |
Tom | -0.130 |
I | -0.129 |
ily | -0.121 |
did | -0.119 |
Token | her |
Token ID | 607 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
do | +0.021 |
Tom | +0.018 |
kids | +0.017 |
there | +0.016 |
ily | +0.014 |
Neg logit contributions | |
icol | -0.107 |
opl | -0.103 |
destination | -0.100 |
former | -0.100 |
achers | -0.099 |
Token | big |
Token ID | 1263 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
do | +0.044 |
there | +0.034 |
kids | +0.033 |
did | +0.031 |
Tom | +0.030 |
Neg logit contributions | |
icol | -0.161 |
opl | -0.157 |
former | -0.153 |
achers | -0.150 |
destination | -0.149 |
Token | sister |
Token ID | 6621 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
icol | +0.053 |
former | +0.051 |
opl | +0.050 |
achers | +0.049 |
destination | +0.047 |
Neg logit contributions | |
do | -0.032 |
kids | -0.028 |
there | -0.026 |
did | -0.026 |
I | -0.025 |
Token | 's |
Token ID | 338 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
icol | +0.026 |
opl | +0.025 |
former | +0.025 |
destination | +0.025 |
achers | +0.024 |
Neg logit contributions | |
do | -0.009 |
I | -0.007 |
there | -0.007 |
did | -0.007 |
Tom | -0.006 |
Token | know |
Token ID | 760 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
do | +0.012 |
oh | +0.012 |
there | +0.011 |
did | +0.011 |
I | +0.011 |
Neg logit contributions | |
opl | -0.022 |
icol | -0.021 |
former | -0.021 |
en | -0.021 |
destination | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
do | +0.092 |
ily | +0.072 |
did | +0.072 |
curious | +0.071 |
kids | +0.070 |
Neg logit contributions | |
icol | -0.176 |
destination | -0.169 |
opl | -0.166 |
en | -0.164 |
former | -0.157 |
Token | Ben |
Token ID | 3932 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
icol | +0.026 |
destination | +0.025 |
en | +0.025 |
former | +0.023 |
brand | +0.023 |
Neg logit contributions | |
do | -0.012 |
he | -0.011 |
lock | -0.010 |
ily | -0.010 |
climb | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
icol | +0.051 |
opl | +0.048 |
destination | +0.047 |
former | +0.046 |
en | +0.046 |
Neg logit contributions | |
do | -0.024 |
kids | -0.019 |
ily | -0.019 |
I | -0.018 |
Tom | -0.018 |
Token | Let |
Token ID | 3914 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
icol | +0.005 |
former | +0.004 |
destination | +0.004 |
opl | +0.004 |
alks | +0.004 |
Neg logit contributions | |
do | -0.003 |
did | -0.002 |
kids | -0.002 |
there | -0.002 |
children | -0.002 |
Token | 's |
Token ID | 338 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
do | +0.030 |
curious | +0.026 |
there | +0.025 |
did | +0.025 |
ily | +0.025 |
Neg logit contributions | |
icol | -0.053 |
destination | -0.051 |
opl | -0.051 |
en | -0.049 |
former | -0.048 |
Token | open |
Token ID | 1280 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
icol | +0.003 |
destination | +0.003 |
former | +0.003 |
opl | +0.003 |
en | +0.003 |
Neg logit contributions | |
do | -0.001 |
ily | -0.001 |
oh | -0.001 |
there | -0.001 |
kids | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
do | +0.010 |
did | +0.007 |
ily | +0.007 |
I | +0.006 |
kids | +0.006 |
Neg logit contributions | |
icol | -0.032 |
opl | -0.031 |
destination | -0.030 |
former | -0.030 |
achers | -0.029 |
Token | box |
Token ID | 3091 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
icol | +0.016 |
opl | +0.015 |
former | +0.014 |
destination | +0.014 |
achers | +0.014 |
Neg logit contributions | |
do | -0.011 |
there | -0.009 |
I | -0.009 |
kids | -0.009 |
did | -0.009 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
do | +0.052 |
oh | +0.044 |
ily | +0.043 |
did | +0.042 |
kids | +0.041 |
Neg logit contributions | |
destination | -0.101 |
icol | -0.094 |
en | -0.092 |
former | -0.092 |
opl | -0.090 |
Token | Anna |
Token ID | 11735 |
Feature activation | -1.61e-04 |
Pos logit contributions | |
do | +0.010 |
oh | +0.008 |
did | +0.007 |
don | +0.007 |
ily | +0.006 |
Neg logit contributions | |
icol | -0.027 |
destination | -0.025 |
former | -0.025 |
alks | -0.025 |
opl | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
icol | +0.284 |
former | +0.276 |
opl | +0.270 |
destination | +0.260 |
achers | +0.260 |
Neg logit contributions | |
do | -0.112 |
there | -0.100 |
I | -0.094 |
you | -0.091 |
did | -0.090 |
Token | fix |
Token ID | 4259 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
icol | +0.066 |
opl | +0.064 |
former | +0.064 |
destination | +0.064 |
en | +0.061 |
Neg logit contributions | |
do | -0.032 |
kids | -0.028 |
curious | -0.028 |
ily | -0.028 |
did | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
do | +0.004 |
there | +0.003 |
I | +0.003 |
Tom | +0.003 |
did | +0.003 |
Neg logit contributions | |
icol | -0.013 |
opl | -0.012 |
former | -0.012 |
destination | -0.012 |
achers | -0.012 |
Token | But |
Token ID | 887 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
do | +0.012 |
did | +0.010 |
there | +0.010 |
kids | +0.009 |
ily | +0.009 |
Neg logit contributions | |
icol | -0.023 |
former | -0.022 |
opl | -0.022 |
destination | -0.021 |
destinations | -0.021 |
Token | sue |
Token ID | 20889 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
icol | +0.071 |
destination | +0.070 |
former | +0.069 |
en | +0.064 |
opl | +0.064 |
Neg logit contributions | |
do | -0.032 |
ily | -0.027 |
kids | -0.025 |
curious | -0.023 |
did | -0.022 |
Token | still |
Token ID | 991 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
icol | +0.192 |
opl | +0.179 |
destination | +0.177 |
former | +0.176 |
achers | +0.172 |
Neg logit contributions | |
do | -0.132 |
I | -0.109 |
kids | -0.108 |
there | -0.107 |
curious | -0.106 |
Token | hugged |
Token ID | 41130 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
icol | +0.042 |
opl | +0.040 |
former | +0.039 |
destination | +0.039 |
achers | +0.037 |
Neg logit contributions | |
do | -0.021 |
ily | -0.017 |
kids | -0.017 |
Tom | -0.016 |
I | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
icol | +0.089 |
opl | +0.084 |
former | +0.084 |
destination | +0.083 |
en | +0.080 |
Neg logit contributions | |
do | -0.034 |
did | -0.025 |
I | -0.025 |
there | -0.025 |
kids | -0.025 |
Token | tight |
Token ID | 5381 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
do | +0.020 |
kids | +0.017 |
I | +0.017 |
Tom | +0.016 |
ily | +0.016 |
Neg logit contributions | |
icol | -0.033 |
former | -0.032 |
destination | -0.031 |
opl | -0.031 |
en | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
icol | +0.058 |
opl | +0.055 |
former | +0.055 |
destination | +0.055 |
achers | +0.052 |
Neg logit contributions | |
do | -0.021 |
kids | -0.016 |
I | -0.015 |
did | -0.015 |
there | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
icol | +0.067 |
opl | +0.066 |
former | +0.065 |
destination | +0.064 |
en | +0.062 |
Neg logit contributions | |
do | -0.030 |
there | -0.026 |
ily | -0.025 |
did | -0.025 |
I | -0.024 |
Token | his |
Token ID | 465 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
icol | +0.010 |
destination | +0.010 |
en | +0.010 |
opl | +0.010 |
brand | +0.009 |
Neg logit contributions | |
do | -0.010 |
I | -0.009 |
you | -0.008 |
did | -0.008 |
don | -0.008 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
icol | +0.037 |
former | +0.035 |
destination | +0.035 |
opl | +0.035 |
destinations | +0.034 |
Neg logit contributions | |
do | -0.009 |
I | -0.006 |
did | -0.006 |
there | -0.006 |
ily | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
do | +0.036 |
I | +0.029 |
ily | +0.029 |
did | +0.028 |
kids | +0.027 |
Neg logit contributions | |
destination | -0.080 |
icol | -0.079 |
opl | -0.078 |
former | -0.077 |
en | -0.076 |
Token | " |
Token ID | 366 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
do | +0.023 |
ily | +0.020 |
did | +0.019 |
kids | +0.019 |
you | +0.018 |
Neg logit contributions | |
icol | -0.030 |
brand | -0.030 |
particularly | -0.029 |
destination | -0.028 |
ric | -0.028 |
Token | Mom |
Token ID | 29252 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
do | +0.020 |
I | +0.016 |
Tom | +0.016 |
did | +0.016 |
kids | +0.016 |
Neg logit contributions | |
icol | -0.027 |
former | -0.025 |
opl | -0.025 |
destination | -0.025 |
achers | -0.025 |
Token | my |
Token ID | 1820 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
do | +0.060 |
ily | +0.057 |
oh | +0.052 |
curious | +0.051 |
kids | +0.050 |
Neg logit contributions | |
icol | -0.089 |
destination | -0.089 |
opl | -0.086 |
ric | -0.084 |
en | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
do | +0.001 |
ily | +0.001 |
oh | +0.001 |
kids | +0.001 |
curious | +0.001 |
Neg logit contributions | |
icol | -0.002 |
destination | -0.002 |
opl | -0.002 |
en | -0.002 |
achers | -0.002 |
Token | are |
Token ID | 389 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ily | +0.028 |
he | +0.025 |
curious | +0.024 |
excited | +0.022 |
cried | +0.022 |
Neg logit contributions | |
brand | -0.037 |
destination | -0.037 |
ric | -0.036 |
icol | -0.035 |
fault | -0.033 |
Token | you |
Token ID | 345 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
do | +0.080 |
ily | +0.059 |
he | +0.059 |
curious | +0.057 |
did | +0.057 |
Neg logit contributions | |
icol | -0.220 |
Wed | -0.216 |
insepar | -0.207 |
destinations | -0.204 |
ric | -0.204 |
Token | cold |
Token ID | 4692 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
do | +0.069 |
ily | +0.064 |
Tom | +0.058 |
Tom | +0.053 |
Amy | +0.052 |
Neg logit contributions | |
destination | -0.130 |
ric | -0.126 |
brand | -0.125 |
former | -0.121 |
fault | -0.121 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
do | +0.103 |
ily | +0.090 |
don | +0.090 |
curious | +0.087 |
did | +0.085 |
Neg logit contributions | |
icol | -0.159 |
opl | -0.156 |
en | -0.155 |
achers | -0.153 |
ained | -0.150 |
Token | to |
Token ID | 284 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
icol | +0.045 |
opl | +0.042 |
former | +0.042 |
destination | +0.041 |
achers | +0.040 |
Neg logit contributions | |
do | -0.024 |
there | -0.020 |
Tom | -0.020 |
I | -0.019 |
ily | -0.019 |
Token | Lily |
Token ID | 20037 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
icol | +0.094 |
opl | +0.089 |
former | +0.089 |
destination | +0.088 |
achers | +0.085 |
Neg logit contributions | |
do | -0.025 |
did | -0.017 |
there | -0.017 |
I | -0.016 |
kids | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
icol | +0.092 |
opl | +0.091 |
destination | +0.090 |
en | +0.089 |
former | +0.088 |
Neg logit contributions | |
do | -0.046 |
oh | -0.040 |
I | -0.039 |
ily | -0.037 |
did | -0.037 |
Token | Lily |
Token ID | 20037 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
icol | +0.043 |
opl | +0.042 |
destination | +0.042 |
achers | +0.041 |
former | +0.041 |
Neg logit contributions | |
do | -0.013 |
Tom | -0.012 |
I | -0.011 |
ily | -0.010 |
there | -0.010 |
Token | takes |
Token ID | 2753 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
icol | +0.084 |
former | +0.081 |
opl | +0.079 |
destination | +0.076 |
achers | +0.075 |
Neg logit contributions | |
do | -0.067 |
did | -0.058 |
Tom | -0.057 |
kids | -0.056 |
I | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
icol | +0.102 |
former | +0.098 |
opl | +0.098 |
destination | +0.094 |
ric | +0.094 |
Neg logit contributions | |
do | -0.022 |
Tom | -0.017 |
there | -0.015 |
ily | -0.014 |
kids | -0.014 |
Token | cr |
Token ID | 1067 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
icol | +0.015 |
opl | +0.014 |
destination | +0.014 |
former | +0.014 |
alks | +0.013 |
Neg logit contributions | |
do | -0.010 |
I | -0.008 |
there | -0.008 |
Tom | -0.008 |
did | -0.008 |
Token | ay |
Token ID | 323 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
do | +0.056 |
ily | +0.050 |
Tom | +0.049 |
I | +0.049 |
did | +0.048 |
Neg logit contributions | |
icol | -0.044 |
former | -0.042 |
destination | -0.039 |
destinations | -0.039 |
opl | -0.038 |
Token | on |
Token ID | 261 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
icol | +0.097 |
opl | +0.091 |
former | +0.091 |
destination | +0.089 |
achers | +0.086 |
Neg logit contributions | |
do | -0.049 |
there | -0.039 |
I | -0.039 |
did | -0.039 |
Tom | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
do | +0.082 |
I | +0.070 |
did | +0.068 |
kids | +0.068 |
oh | +0.068 |
Neg logit contributions | |
icol | -0.127 |
destination | -0.124 |
opl | -0.123 |
former | -0.118 |
alks | -0.117 |
Token | smiles |
Token ID | 21845 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
icol | +0.023 |
opl | +0.023 |
former | +0.023 |
destination | +0.022 |
achers | +0.022 |
Neg logit contributions | |
do | -0.017 |
Tom | -0.015 |
I | -0.015 |
did | -0.015 |
there | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
icol | +0.126 |
former | +0.119 |
destination | +0.118 |
opl | +0.118 |
destinations | +0.114 |
Neg logit contributions | |
do | -0.047 |
Tom | -0.036 |
I | -0.036 |
kids | -0.035 |
ily | -0.035 |
Token | She |
Token ID | 1375 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
do | +0.049 |
did | +0.042 |
there | +0.041 |
oh | +0.040 |
kids | +0.039 |
Neg logit contributions | |
icol | -0.077 |
opl | -0.076 |
former | -0.073 |
destination | -0.072 |
ric | -0.070 |
Token | would |
Token ID | 561 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
do | +0.037 |
there | +0.030 |
I | +0.030 |
Tom | +0.030 |
did | +0.030 |
Neg logit contributions | |
icol | -0.062 |
opl | -0.058 |
former | -0.058 |
destination | -0.057 |
achers | -0.055 |
Token | dance |
Token ID | 9280 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
icol | +0.212 |
opl | +0.199 |
former | +0.199 |
destination | +0.196 |
en | +0.187 |
Neg logit contributions | |
do | -0.135 |
Tom | -0.119 |
ily | -0.118 |
there | -0.118 |
kids | -0.117 |
Token | all |
Token ID | 477 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
icol | +0.118 |
former | +0.109 |
opl | +0.109 |
destination | +0.109 |
en | +0.104 |
Neg logit contributions | |
do | -0.052 |
kids | -0.042 |
I | -0.042 |
Tom | -0.041 |
ily | -0.041 |
Token | over |
Token ID | 625 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
do | +0.029 |
there | +0.023 |
I | +0.023 |
did | +0.023 |
Tom | +0.023 |
Neg logit contributions | |
icol | -0.052 |
former | -0.048 |
opl | -0.048 |
destination | -0.047 |
achers | -0.046 |
Token | her |
Token ID | 607 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
icol | +0.127 |
opl | +0.122 |
former | +0.120 |
destination | +0.119 |
destinations | +0.115 |
Neg logit contributions | |
do | -0.041 |
did | -0.030 |
I | -0.029 |
ily | -0.028 |
there | -0.028 |
Token | house |
Token ID | 2156 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
do | +0.062 |
ily | +0.057 |
Tom | +0.054 |
I | +0.053 |
did | +0.053 |
Neg logit contributions | |
icol | -0.105 |
destination | -0.101 |
former | -0.100 |
opl | -0.098 |
destinations | -0.095 |
Token | and |
Token ID | 290 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
do | +0.079 |
ily | +0.068 |
I | +0.066 |
kids | +0.064 |
Tom | +0.064 |
Neg logit contributions | |
icol | -0.162 |
destination | -0.159 |
former | -0.158 |
opl | -0.155 |
destinations | -0.150 |
Token | tw |
Token ID | 665 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
do | +0.026 |
ily | +0.025 |
Tom | +0.023 |
kids | +0.023 |
there | +0.023 |
Neg logit contributions | |
icol | -0.047 |
former | -0.045 |
opl | -0.044 |
destination | -0.044 |
en | -0.043 |
Token | irl |
Token ID | 1901 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
do | +0.021 |
there | +0.019 |
did | +0.019 |
you | +0.018 |
kids | +0.018 |
Neg logit contributions | |
icol | -0.014 |
former | -0.013 |
opl | -0.013 |
destination | -0.012 |
lifelong | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
do | +0.073 |
I | +0.058 |
ily | +0.057 |
don | +0.056 |
did | +0.056 |
Neg logit contributions | |
icol | -0.172 |
opl | -0.169 |
destination | -0.168 |
former | -0.165 |
destinations | -0.159 |
Token | He |
Token ID | 679 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
do | +0.034 |
you | +0.029 |
there | +0.029 |
don | +0.028 |
did | +0.028 |
Neg logit contributions | |
icol | -0.047 |
opl | -0.044 |
destination | -0.043 |
former | -0.042 |
destinations | -0.041 |
Token | sees |
Token ID | 7224 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
do | +0.002 |
did | +0.002 |
kids | +0.002 |
Tom | +0.002 |
I | +0.002 |
Neg logit contributions | |
icol | -0.003 |
former | -0.003 |
opl | -0.003 |
destination | -0.003 |
achers | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
do | +0.000 |
there | +0.000 |
Tom | +0.000 |
I | +0.000 |
did | +0.000 |
Neg logit contributions | |
icol | -0.001 |
opl | -0.001 |
former | -0.001 |
destination | -0.001 |
achers | -0.001 |
Token | big |
Token ID | 1263 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
do | +0.013 |
there | +0.010 |
kids | +0.009 |
did | +0.009 |
I | +0.009 |
Neg logit contributions | |
icol | -0.031 |
opl | -0.030 |
former | -0.030 |
achers | -0.028 |
destination | -0.028 |
Token | wall |
Token ID | 3355 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
icol | +0.084 |
opl | +0.079 |
destination | +0.078 |
former | +0.076 |
achers | +0.073 |
Neg logit contributions | |
do | -0.056 |
ily | -0.049 |
did | -0.048 |
I | -0.047 |
there | -0.047 |
Token | with |
Token ID | 351 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
do | +0.076 |
kids | +0.056 |
Tom | +0.055 |
did | +0.054 |
I | +0.054 |
Neg logit contributions | |
icol | -0.238 |
opl | -0.231 |
destination | -0.222 |
former | -0.221 |
achers | -0.217 |
Token | a |
Token ID | 257 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
do | +0.012 |
Tom | +0.009 |
kids | +0.008 |
there | +0.008 |
I | +0.008 |
Neg logit contributions | |
icol | -0.045 |
opl | -0.042 |
former | -0.042 |
destination | -0.042 |
achers | -0.041 |
Token | picture |
Token ID | 4286 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
do | +0.016 |
there | +0.013 |
I | +0.013 |
did | +0.013 |
kids | +0.013 |
Neg logit contributions | |
icol | -0.025 |
opl | -0.024 |
former | -0.024 |
destination | -0.023 |
achers | -0.023 |
Token | of |
Token ID | 286 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
icol | +0.135 |
opl | +0.131 |
destination | +0.125 |
former | +0.125 |
achers | +0.122 |
Neg logit contributions | |
do | -0.060 |
did | -0.046 |
I | -0.046 |
kids | -0.046 |
don | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
do | +0.035 |
did | +0.024 |
ily | +0.023 |
there | +0.023 |
I | +0.022 |
Neg logit contributions | |
icol | -0.144 |
opl | -0.139 |
former | -0.138 |
destination | -0.136 |
destinations | -0.132 |
Token | " |
Token ID | 366 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
icol | +0.025 |
opl | +0.023 |
former | +0.023 |
destination | +0.023 |
achers | +0.022 |
Neg logit contributions | |
do | -0.010 |
there | -0.007 |
did | -0.007 |
I | -0.007 |
kids | -0.007 |
Token | We |
Token ID | 1135 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
icol | +0.023 |
opl | +0.022 |
former | +0.022 |
destination | +0.022 |
destinations | +0.021 |
Neg logit contributions | |
do | -0.014 |
I | -0.012 |
there | -0.011 |
Tom | -0.011 |
did | -0.011 |
Token | can |
Token ID | 460 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
icol | +0.083 |
opl | +0.078 |
former | +0.078 |
destination | +0.077 |
achers | +0.074 |
Neg logit contributions | |
do | -0.040 |
there | -0.032 |
I | -0.032 |
Tom | -0.031 |
did | -0.031 |
Token | use |
Token ID | 779 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
icol | +0.116 |
opl | +0.110 |
former | +0.110 |
destination | +0.109 |
achers | +0.105 |
Neg logit contributions | |
do | -0.058 |
there | -0.047 |
did | -0.047 |
ily | -0.047 |
Tom | -0.046 |
Token | this |
Token ID | 428 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
icol | +0.131 |
former | +0.124 |
opl | +0.124 |
achers | +0.121 |
sym | +0.119 |
Neg logit contributions | |
do | -0.023 |
you | -0.020 |
there | -0.019 |
I | -0.017 |
Tom | -0.017 |
Token | branch |
Token ID | 8478 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
icol | +0.026 |
opl | +0.024 |
former | +0.023 |
achers | +0.023 |
ric | +0.022 |
Neg logit contributions | |
do | -0.017 |
there | -0.014 |
I | -0.014 |
you | -0.013 |
kids | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
do | +0.113 |
I | +0.092 |
there | +0.091 |
did | +0.089 |
Tom | +0.089 |
Neg logit contributions | |
icol | -0.233 |
opl | -0.218 |
former | -0.217 |
destination | -0.212 |
achers | -0.207 |
Token | play |
Token ID | 711 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
opl | +0.055 |
destination | +0.055 |
former | +0.054 |
icol | +0.054 |
ric | +0.051 |
Neg logit contributions | |
ily | -0.027 |
do | -0.027 |
kids | -0.027 |
there | -0.026 |
did | -0.026 |
Token | instead |
Token ID | 2427 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
do | +0.002 |
did | +0.002 |
ily | +0.002 |
kids | +0.002 |
curious | +0.002 |
Neg logit contributions | |
icol | -0.005 |
opl | -0.005 |
destination | -0.005 |
former | -0.005 |
en | -0.005 |
Token | ." |
Token ID | 526 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
do | +0.126 |
did | +0.103 |
curious | +0.100 |
Tom | +0.099 |
kids | +0.099 |
Neg logit contributions | |
opl | -0.234 |
icol | -0.231 |
destination | -0.227 |
former | -0.224 |
achers | -0.218 |
Token | The |
Token ID | 383 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
do | +0.014 |
there | +0.011 |
I | +0.011 |
did | +0.011 |
Tom | +0.011 |
Neg logit contributions | |
icol | -0.030 |
opl | -0.028 |
former | -0.028 |
destination | -0.028 |
achers | -0.027 |
Token | together |
Token ID | 1978 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
do | +0.025 |
I | +0.020 |
did | +0.020 |
ily | +0.020 |
Tom | +0.020 |
Neg logit contributions | |
icol | -0.058 |
destination | -0.054 |
former | -0.054 |
opl | -0.054 |
achers | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
do | +0.013 |
I | +0.010 |
ily | +0.010 |
did | +0.010 |
Tom | +0.010 |
Neg logit contributions | |
icol | -0.034 |
destination | -0.032 |
opl | -0.032 |
former | -0.032 |
destinations | -0.031 |
Token | They |
Token ID | 1119 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
do | +0.017 |
Tom | +0.014 |
I | +0.014 |
there | +0.014 |
did | +0.013 |
Neg logit contributions | |
icol | -0.028 |
opl | -0.027 |
former | -0.027 |
destination | -0.026 |
achers | -0.025 |
Token | played |
Token ID | 2826 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
icol | +0.054 |
destination | +0.051 |
former | +0.050 |
opl | +0.049 |
en | +0.048 |
Neg logit contributions | |
do | -0.031 |
I | -0.027 |
ily | -0.027 |
oh | -0.026 |
you | -0.026 |
Token | lots |
Token ID | 6041 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
I | +0.007 |
do | +0.006 |
don | +0.006 |
ily | +0.006 |
kids | +0.006 |
Neg logit contributions | |
icol | -0.012 |
destination | -0.011 |
brand | -0.011 |
sym | -0.011 |
lifelong | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
icol | +0.031 |
opl | +0.031 |
former | +0.029 |
destination | +0.029 |
achers | +0.028 |
Neg logit contributions | |
do | -0.017 |
did | -0.014 |
Tom | -0.014 |
I | -0.013 |
there | -0.013 |
Token | games |
Token ID | 1830 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
I | +0.069 |
do | +0.069 |
Tom | +0.066 |
ily | +0.065 |
don | +0.064 |
Neg logit contributions | |
icol | -0.085 |
opl | -0.080 |
lifelong | -0.076 |
brand | -0.076 |
sym | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
do | +0.058 |
I | +0.046 |
ily | +0.045 |
kids | +0.044 |
did | +0.043 |
Neg logit contributions | |
icol | -0.145 |
destination | -0.136 |
opl | -0.136 |
former | -0.133 |
achers | -0.130 |
Token | even |
Token ID | 772 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
icol | +0.003 |
former | +0.002 |
opl | +0.002 |
destination | +0.002 |
en | +0.002 |
Neg logit contributions | |
do | -0.002 |
I | -0.002 |
ily | -0.002 |
there | -0.001 |
curious | -0.001 |
Token | made |
Token ID | 925 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
icol | +0.184 |
former | +0.171 |
opl | +0.167 |
destination | +0.166 |
en | +0.162 |
Neg logit contributions | |
do | -0.124 |
I | -0.106 |
ily | -0.100 |
you | -0.100 |
kids | -0.100 |
Token | sand |
Token ID | 6450 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
icol | +0.157 |
former | +0.144 |
destination | +0.144 |
opl | +0.142 |
destinations | +0.141 |
Neg logit contributions | |
do | -0.093 |
I | -0.084 |
did | -0.078 |
ily | -0.076 |
don | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
icol | +0.311 |
opl | +0.298 |
former | +0.295 |
destination | +0.293 |
achers | +0.282 |
Neg logit contributions | |
do | -0.116 |
Tom | -0.088 |
did | -0.088 |
kids | -0.087 |
I | -0.087 |
Token | make |
Token ID | 787 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
do | +0.035 |
I | +0.027 |
there | +0.027 |
did | +0.027 |
Tom | +0.026 |
Neg logit contributions | |
icol | -0.088 |
opl | -0.083 |
former | -0.082 |
destination | -0.081 |
achers | -0.079 |
Token | music |
Token ID | 2647 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
icol | +0.033 |
opl | +0.031 |
former | +0.031 |
destination | +0.030 |
en | +0.029 |
Neg logit contributions | |
do | -0.015 |
I | -0.013 |
did | -0.012 |
ily | -0.012 |
Tom | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
do | +0.016 |
Tom | +0.012 |
did | +0.012 |
I | +0.012 |
ily | +0.012 |
Neg logit contributions | |
icol | -0.040 |
opl | -0.037 |
former | -0.037 |
destination | -0.037 |
destinations | -0.035 |
Token | However |
Token ID | 2102 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
do | +0.051 |
there | +0.042 |
did | +0.042 |
I | +0.041 |
kids | +0.041 |
Neg logit contributions | |
icol | -0.075 |
opl | -0.071 |
former | -0.070 |
destination | -0.069 |
destinations | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
do | +0.022 |
kids | +0.018 |
ily | +0.018 |
curious | +0.018 |
I | +0.017 |
Neg logit contributions | |
icol | -0.050 |
destination | -0.049 |
former | -0.047 |
en | -0.047 |
opl | -0.046 |
Token | it |
Token ID | 340 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
do | +0.029 |
ily | +0.028 |
kids | +0.024 |
I | +0.023 |
did | +0.022 |
Neg logit contributions | |
former | -0.060 |
destination | -0.060 |
icol | -0.059 |
particularly | -0.056 |
en | -0.055 |
Token | was |
Token ID | 373 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
do | +0.040 |
did | +0.032 |
there | +0.032 |
I | +0.031 |
Tom | +0.030 |
Neg logit contributions | |
icol | -0.080 |
opl | -0.075 |
former | -0.074 |
destination | -0.073 |
achers | -0.071 |
Token | often |
Token ID | 1690 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
icol | +0.098 |
achers | +0.090 |
opl | +0.089 |
irs | +0.085 |
destination | +0.085 |
Neg logit contributions | |
do | -0.030 |
there | -0.028 |
did | -0.025 |
a | -0.025 |
Tom | -0.024 |
Token | difficult |
Token ID | 2408 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
icol | +0.049 |
opl | +0.047 |
achers | +0.046 |
former | +0.045 |
destination | +0.044 |
Neg logit contributions | |
do | -0.021 |
there | -0.019 |
did | -0.017 |
curious | -0.017 |
Tom | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
icol | +0.204 |
opl | +0.192 |
former | +0.191 |
destination | +0.186 |
achers | +0.183 |
Neg logit contributions | |
do | -0.086 |
there | -0.068 |
I | -0.064 |
you | -0.064 |
kids | -0.064 |
Token | Because |
Token ID | 8128 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
icol | +0.005 |
former | +0.004 |
opl | +0.004 |
destination | +0.004 |
destinations | +0.004 |
Neg logit contributions | |
do | -0.004 |
Tom | -0.004 |
kids | -0.004 |
I | -0.004 |
there | -0.004 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
destination | +0.100 |
channels | +0.097 |
destinations | +0.095 |
icol | +0.095 |
en | +0.094 |
Neg logit contributions | |
ily | -0.038 |
do | -0.036 |
he | -0.031 |
did | -0.031 |
Tom | -0.027 |
Token | is |
Token ID | 318 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
do | +0.002 |
ily | +0.001 |
oh | +0.001 |
kids | +0.001 |
I | +0.001 |
Neg logit contributions | |
icol | -0.002 |
opl | -0.002 |
destination | -0.002 |
en | -0.002 |
former | -0.002 |
Token | working |
Token ID | 1762 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
icol | +0.078 |
opl | +0.074 |
former | +0.074 |
destination | +0.073 |
destinations | +0.070 |
Neg logit contributions | |
do | -0.042 |
ily | -0.034 |
did | -0.034 |
I | -0.034 |
Tom | -0.034 |
Token | hard |
Token ID | 1327 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
do | +0.041 |
I | +0.033 |
Tom | +0.033 |
did | +0.033 |
ily | +0.033 |
Neg logit contributions | |
icol | -0.081 |
opl | -0.076 |
former | -0.076 |
destination | -0.075 |
destinations | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
icol | +0.042 |
opl | +0.040 |
former | +0.040 |
destination | +0.040 |
destinations | +0.038 |
Neg logit contributions | |
do | -0.016 |
I | -0.012 |
Tom | -0.012 |
ily | -0.012 |
did | -0.012 |
Token | needs |
Token ID | 2476 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
do | +0.007 |
ily | +0.006 |
kids | +0.006 |
Tom | +0.005 |
there | +0.005 |
Neg logit contributions | |
icol | -0.016 |
former | -0.015 |
destination | -0.015 |
opl | -0.015 |
destinations | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
icol | +0.143 |
opl | +0.136 |
former | +0.132 |
achers | +0.130 |
destination | +0.129 |
Neg logit contributions | |
do | -0.056 |
there | -0.045 |
I | -0.044 |
you | -0.044 |
kids | -0.043 |
Token | rest |
Token ID | 1334 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
destination | +0.052 |
former | +0.051 |
opl | +0.048 |
destinations | +0.047 |
en | +0.047 |
Neg logit contributions | |
ily | -0.025 |
curious | -0.023 |
oh | -0.023 |
there | -0.023 |
did | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
do | +0.063 |
ily | +0.048 |
did | +0.048 |
Tom | +0.048 |
I | +0.046 |
Neg logit contributions | |
icol | -0.163 |
former | -0.162 |
destination | -0.158 |
opl | -0.157 |
conflicts | -0.153 |
Token | brain |
Token ID | 3632 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
do | +0.049 |
ily | +0.042 |
Tom | +0.042 |
I | +0.042 |
there | +0.041 |
Neg logit contributions | |
icol | -0.067 |
former | -0.064 |
opl | -0.063 |
destination | -0.062 |
destinations | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
do | +0.018 |
oh | +0.015 |
don | +0.014 |
did | +0.014 |
ily | +0.014 |
Neg logit contributions | |
icol | -0.020 |
opl | -0.018 |
former | -0.018 |
alks | -0.018 |
destination | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
do | +0.016 |
oh | +0.015 |
kids | +0.014 |
I | +0.014 |
did | +0.014 |
Neg logit contributions | |
icol | -0.026 |
opl | -0.025 |
destination | -0.024 |
ilts | -0.023 |
achers | -0.023 |
Token | Together |
Token ID | 41631 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
do | +0.019 |
Tom | +0.017 |
kids | +0.017 |
there | +0.016 |
I | +0.016 |
Neg logit contributions | |
icol | -0.022 |
opl | -0.022 |
former | -0.022 |
achers | -0.021 |
destination | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
icol | +0.083 |
destination | +0.078 |
opl | +0.075 |
alks | +0.075 |
en | +0.074 |
Neg logit contributions | |
do | -0.036 |
oh | -0.028 |
don | -0.027 |
ily | -0.027 |
I | -0.027 |
Token | they |
Token ID | 484 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
ily | +0.006 |
do | +0.006 |
oh | +0.005 |
did | +0.005 |
kids | +0.004 |
Neg logit contributions | |
icol | -0.010 |
alks | -0.010 |
destination | -0.010 |
lifelong | -0.010 |
former | -0.009 |
Token | sat |
Token ID | 3332 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
icol | +0.049 |
en | +0.046 |
destination | +0.046 |
former | +0.046 |
ples | +0.045 |
Neg logit contributions | |
do | -0.046 |
I | -0.045 |
oh | -0.044 |
you | -0.043 |
Tom | -0.042 |
Token | under |
Token ID | 739 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
do | +0.238 |
I | +0.211 |
ily | +0.197 |
Tom | +0.193 |
you | +0.193 |
Neg logit contributions | |
icol | -0.255 |
former | -0.253 |
opl | -0.247 |
ained | -0.245 |
destination | -0.243 |
Token | the |
Token ID | 262 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
do | +0.035 |
ily | +0.027 |
I | +0.025 |
did | +0.025 |
don | +0.023 |
Neg logit contributions | |
icol | -0.104 |
former | -0.097 |
destination | -0.097 |
opl | -0.096 |
alks | -0.094 |
Token | tree |
Token ID | 5509 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
do | +0.005 |
did | +0.005 |
ily | +0.005 |
don | +0.005 |
oh | +0.005 |
Neg logit contributions | |
icol | -0.009 |
opl | -0.009 |
destination | -0.008 |
brand | -0.008 |
alks | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
do | +0.101 |
I | +0.089 |
ily | +0.085 |
you | +0.083 |
oh | +0.083 |
Neg logit contributions | |
former | -0.182 |
icol | -0.181 |
opl | -0.179 |
destination | -0.178 |
destinations | -0.169 |
Token | The |
Token ID | 383 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
do | +0.013 |
did | +0.010 |
there | +0.010 |
ily | +0.010 |
kids | +0.010 |
Neg logit contributions | |
icol | -0.022 |
former | -0.020 |
opl | -0.020 |
destination | -0.019 |
destinations | -0.019 |
Token | Max |
Token ID | 5436 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
do | +0.007 |
Tom | +0.006 |
I | +0.006 |
there | +0.006 |
did | +0.006 |
Neg logit contributions | |
icol | -0.018 |
opl | -0.017 |
former | -0.017 |
destination | -0.017 |
achers | -0.016 |
Token | said |
Token ID | 531 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
icol | +0.065 |
former | +0.060 |
destination | +0.059 |
opl | +0.058 |
en | +0.057 |
Neg logit contributions | |
do | -0.036 |
I | -0.032 |
ily | -0.031 |
you | -0.031 |
kids | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
do | +0.011 |
kids | +0.010 |
ily | +0.009 |
he | +0.009 |
children | +0.009 |
Neg logit contributions | |
icol | -0.022 |
brand | -0.022 |
destination | -0.020 |
particularly | -0.019 |
insepar | -0.019 |
Token | " |
Token ID | 366 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
do | +0.001 |
ily | +0.001 |
kids | +0.001 |
did | +0.001 |
there | +0.001 |
Neg logit contributions | |
icol | -0.002 |
opl | -0.002 |
brand | -0.001 |
former | -0.001 |
destination | -0.001 |
Token | I |
Token ID | 40 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
icol | +0.006 |
opl | +0.006 |
former | +0.006 |
destination | +0.006 |
achers | +0.006 |
Neg logit contributions | |
do | -0.004 |
there | -0.003 |
kids | -0.003 |
Tom | -0.003 |
did | -0.003 |
Token | don |
Token ID | 836 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
icol | +0.072 |
opl | +0.068 |
former | +0.067 |
destination | +0.066 |
achers | +0.064 |
Neg logit contributions | |
do | -0.034 |
there | -0.026 |
I | -0.026 |
did | -0.026 |
Tom | -0.026 |
Token | 't |
Token ID | 470 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
do | +0.235 |
did | +0.210 |
ily | +0.208 |
Tom | +0.206 |
kids | +0.206 |
Neg logit contributions | |
opl | -0.293 |
icol | -0.292 |
achers | -0.272 |
destination | -0.269 |
ilts | -0.264 |
Token | want |
Token ID | 765 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
Leo | +0.021 |
Tom | +0.021 |
oh | +0.020 |
do | +0.020 |
ily | +0.020 |
Neg logit contributions | |
en | -0.036 |
ilts | -0.035 |
icol | -0.034 |
opl | -0.034 |
former | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
do | +0.095 |
I | +0.090 |
you | +0.090 |
Tom | +0.084 |
there | +0.084 |
Neg logit contributions | |
icol | -0.244 |
former | -0.233 |
opl | -0.231 |
ric | -0.219 |
achers | -0.218 |
Token | clean |
Token ID | 3424 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
destination | +0.034 |
icol | +0.033 |
former | +0.033 |
en | +0.032 |
ilts | +0.031 |
Neg logit contributions | |
ily | -0.017 |
curious | -0.017 |
did | -0.017 |
oh | -0.016 |
there | -0.016 |
Token | up |
Token ID | 510 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
icol | +0.046 |
opl | +0.043 |
destination | +0.042 |
former | +0.042 |
achers | +0.041 |
Neg logit contributions | |
do | -0.031 |
did | -0.026 |
ily | -0.026 |
I | -0.026 |
there | -0.025 |
Token | paper |
Token ID | 3348 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
icol | +0.016 |
opl | +0.016 |
former | +0.015 |
ric | +0.015 |
fault | +0.015 |
Neg logit contributions | |
do | -0.010 |
there | -0.009 |
kids | -0.009 |
I | -0.008 |
you | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
icol | +0.091 |
opl | +0.086 |
destination | +0.086 |
former | +0.086 |
achers | +0.082 |
Neg logit contributions | |
do | -0.034 |
did | -0.026 |
I | -0.025 |
ily | -0.025 |
Tom | -0.025 |
Token | Sue |
Token ID | 26089 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
do | +0.029 |
oh | +0.025 |
you | +0.024 |
don | +0.024 |
kids | +0.024 |
Neg logit contributions | |
opl | -0.042 |
icol | -0.042 |
alks | -0.038 |
ained | -0.038 |
aters | -0.037 |
Token | could |
Token ID | 714 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
icol | +0.011 |
destination | +0.010 |
en | +0.010 |
destinations | +0.010 |
former | +0.010 |
Neg logit contributions | |
do | -0.007 |
I | -0.006 |
oh | -0.006 |
you | -0.006 |
Tom | -0.006 |
Token | not |
Token ID | 407 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
do | +0.047 |
kids | +0.044 |
ily | +0.043 |
Tom | +0.040 |
there | +0.040 |
Neg logit contributions | |
icol | -0.122 |
former | -0.116 |
destination | -0.116 |
opl | -0.112 |
brand | -0.110 |
Token | wait |
Token ID | 4043 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
kids | +0.061 |
there | +0.059 |
Tom | +0.058 |
I | +0.058 |
oh | +0.057 |
Neg logit contributions | |
destination | -0.131 |
icol | -0.130 |
former | -0.127 |
en | -0.122 |
masterpiece | -0.117 |
Token | to |
Token ID | 284 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
do | +0.216 |
I | +0.180 |
did | +0.178 |
kids | +0.178 |
ily | +0.177 |
Neg logit contributions | |
icol | -0.325 |
opl | -0.300 |
former | -0.300 |
destination | -0.297 |
destinations | -0.282 |
Token | see |
Token ID | 766 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
icol | +0.042 |
destination | +0.040 |
former | +0.039 |
opl | +0.038 |
en | +0.038 |
Neg logit contributions | |
ily | -0.019 |
do | -0.019 |
oh | -0.018 |
did | -0.018 |
there | -0.017 |
Token | what |
Token ID | 644 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
do | +0.027 |
did | +0.022 |
ily | +0.021 |
I | +0.020 |
kids | +0.019 |
Neg logit contributions | |
icol | -0.061 |
destination | -0.060 |
opl | -0.059 |
former | -0.058 |
en | -0.057 |
Token | was |
Token ID | 373 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
do | +0.050 |
kids | +0.039 |
ily | +0.038 |
don | +0.038 |
curious | +0.037 |
Neg logit contributions | |
icol | -0.112 |
destination | -0.107 |
opl | -0.106 |
former | -0.104 |
destinations | -0.103 |
Token | inside |
Token ID | 2641 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
icol | +0.085 |
opl | +0.079 |
destination | +0.078 |
former | +0.077 |
destinations | +0.075 |
Neg logit contributions | |
do | -0.045 |
I | -0.036 |
kids | -0.035 |
did | -0.035 |
Tom | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +9.61e-02 |
Pos logit contributions | |
icol | +0.007 |
opl | +0.007 |
former | +0.007 |
destination | +0.007 |
achers | +0.007 |
Neg logit contributions | |
do | -0.003 |
did | -0.002 |
I | -0.002 |
there | -0.002 |
kids | -0.002 |
Token | They |
Token ID | 2990 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
icol | +0.009 |
opl | +0.009 |
former | +0.009 |
destination | +0.009 |
achers | +0.009 |
Neg logit contributions | |
do | -0.006 |
did | -0.005 |
kids | -0.005 |
I | -0.005 |
Tom | -0.005 |
Token | went |
Token ID | 1816 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
icol | +0.065 |
former | +0.061 |
destination | +0.061 |
opl | +0.060 |
destinations | +0.058 |
Neg logit contributions | |
do | -0.040 |
I | -0.035 |
there | -0.033 |
kids | -0.033 |
you | -0.033 |
Token | outside |
Token ID | 2354 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
icol | +0.024 |
opl | +0.024 |
former | +0.023 |
ric | +0.022 |
achers | +0.022 |
Neg logit contributions | |
do | -0.014 |
there | -0.012 |
Tom | -0.011 |
kids | -0.011 |
I | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
icol | +0.003 |
destination | +0.003 |
former | +0.003 |
en | +0.003 |
opl | +0.003 |
Neg logit contributions | |
do | -0.002 |
ily | -0.001 |
did | -0.001 |
I | -0.001 |
oh | -0.001 |
Token | sat |
Token ID | 3332 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
do | +0.015 |
ily | +0.014 |
kids | +0.013 |
I | +0.013 |
you | +0.012 |
Neg logit contributions | |
icol | -0.021 |
destination | -0.020 |
former | -0.020 |
en | -0.018 |
sym | -0.018 |
Token | on |
Token ID | 319 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
do | +0.213 |
I | +0.184 |
ily | +0.184 |
don | +0.173 |
you | +0.171 |
Neg logit contributions | |
icol | -0.275 |
former | -0.259 |
destination | -0.258 |
opl | -0.245 |
en | -0.240 |
Token | the |
Token ID | 262 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
do | +0.012 |
there | +0.008 |
I | +0.008 |
did | +0.008 |
Tom | +0.008 |
Neg logit contributions | |
icol | -0.045 |
opl | -0.043 |
former | -0.043 |
destination | -0.043 |
achers | -0.041 |
Token | grass |
Token ID | 8701 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
do | +0.004 |
did | +0.003 |
there | +0.003 |
Tom | +0.003 |
I | +0.003 |
Neg logit contributions | |
icol | -0.005 |
opl | -0.005 |
former | -0.005 |
destination | -0.005 |
achers | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
do | +0.046 |
I | +0.037 |
kids | +0.035 |
ily | +0.035 |
you | +0.034 |
Neg logit contributions | |
icol | -0.104 |
destination | -0.100 |
former | -0.099 |
opl | -0.099 |
en | -0.094 |
Token | Daddy |
Token ID | 26926 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
do | +0.009 |
Tom | +0.008 |
I | +0.008 |
there | +0.008 |
did | +0.007 |
Neg logit contributions | |
icol | -0.016 |
opl | -0.015 |
former | -0.015 |
destination | -0.014 |
achers | -0.014 |
Token | day |
Token ID | 1110 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
I | +0.006 |
do | +0.006 |
don | +0.006 |
you | +0.006 |
kids | +0.006 |
Neg logit contributions | |
opl | -0.004 |
single | -0.004 |
lifelong | -0.004 |
ained | -0.004 |
particularly | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
icol | +0.089 |
opl | +0.084 |
destination | +0.082 |
former | +0.082 |
achers | +0.081 |
Neg logit contributions | |
do | -0.030 |
I | -0.022 |
ily | -0.022 |
kids | -0.022 |
did | -0.021 |
Token | Mitt |
Token ID | 16627 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
do | +0.062 |
ily | +0.058 |
kids | +0.056 |
curious | +0.054 |
I | +0.054 |
Neg logit contributions | |
icol | -0.039 |
achers | -0.032 |
former | -0.032 |
opl | -0.031 |
destination | -0.031 |
Token | ens |
Token ID | 641 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
icol | +0.168 |
opl | +0.160 |
achers | +0.151 |
former | +0.151 |
destination | +0.146 |
Neg logit contributions | |
do | -0.113 |
there | -0.097 |
I | -0.097 |
curious | -0.095 |
kids | -0.093 |
Token | was |
Token ID | 373 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
do | +0.087 |
I | +0.077 |
oh | +0.075 |
ily | +0.075 |
Tom | +0.075 |
Neg logit contributions | |
icol | -0.129 |
destination | -0.120 |
achers | -0.117 |
former | -0.116 |
en | -0.114 |
Token | sitting |
Token ID | 5586 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
icol | +0.044 |
former | +0.042 |
opl | +0.041 |
destination | +0.041 |
destinations | +0.039 |
Neg logit contributions | |
do | -0.032 |
I | -0.027 |
Tom | -0.027 |
ily | -0.027 |
did | -0.027 |
Token | under |
Token ID | 739 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
do | +0.213 |
I | +0.196 |
don | +0.187 |
Tom | +0.176 |
we | +0.173 |
Neg logit contributions | |
opl | -0.302 |
achers | -0.300 |
ained | -0.300 |
former | -0.299 |
ined | -0.289 |
Token | a |
Token ID | 257 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
do | +0.039 |
did | +0.025 |
I | +0.024 |
ily | +0.023 |
kids | +0.022 |
Neg logit contributions | |
icol | -0.166 |
opl | -0.158 |
former | -0.156 |
destination | -0.154 |
achers | -0.150 |
Token | tree |
Token ID | 5509 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
do | +0.024 |
there | +0.018 |
I | +0.018 |
Tom | +0.018 |
did | +0.017 |
Neg logit contributions | |
icol | -0.060 |
former | -0.057 |
opl | -0.056 |
destination | -0.056 |
destinations | -0.054 |
Token | when |
Token ID | 618 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
do | +0.103 |
I | +0.086 |
ily | +0.085 |
kids | +0.085 |
don | +0.082 |
Neg logit contributions | |
icol | -0.234 |
opl | -0.234 |
former | -0.228 |
destination | -0.225 |
achers | -0.220 |
Token | a |
Token ID | 257 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
do | +0.018 |
kids | +0.012 |
I | +0.012 |
did | +0.012 |
ily | +0.011 |
Neg logit contributions | |
icol | -0.071 |
opl | -0.067 |
former | -0.067 |
destination | -0.066 |
achers | -0.064 |