Token | twenty |
Token ID | 8208 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
dives | +0.150 |
eway | +0.140 |
villains | +0.129 |
mer | +0.129 |
films | +0.129 |
Neg logit contributions | |
Em | -0.090 |
Gem | -0.087 |
ama | -0.084 |
expensive | -0.082 |
checkout | -0.080 |
Token | - |
Token ID | 12 |
Feature activation | +7.95e+00 |
Pos logit contributions | |
dives | +0.134 |
eway | +0.118 |
tricks | +0.115 |
films | +0.111 |
mer | +0.110 |
Neg logit contributions | |
Em | -0.150 |
ama | -0.147 |
Gem | -0.146 |
Johnson | -0.143 |
groceries | -0.143 |
Token | eight |
Token ID | 26022 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
dives | +0.190 |
eway | +0.166 |
films | +0.159 |
mer | +0.157 |
tricks | +0.157 |
Neg logit contributions | |
Em | -0.201 |
ama | -0.197 |
Gem | -0.196 |
checkout | -0.188 |
Johnson | -0.188 |
Token | , |
Token ID | 11 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
dives | +0.088 |
tricks | +0.082 |
poses | +0.078 |
eway | +0.078 |
dances | +0.077 |
Neg logit contributions | |
groceries | -0.068 |
infected | -0.067 |
Em | -0.066 |
severe | -0.066 |
Gem | -0.066 |
Token | twenty |
Token ID | 8208 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
dives | +0.136 |
eway | +0.123 |
tricks | +0.119 |
films | +0.119 |
mer | +0.118 |
Neg logit contributions | |
Em | -0.085 |
ama | -0.085 |
Gem | -0.082 |
groceries | -0.080 |
Johnson | -0.080 |
Token | - |
Token ID | 12 |
Feature activation | +7.65e+00 |
Pos logit contributions | |
dives | +0.127 |
eway | +0.111 |
tricks | +0.108 |
films | +0.104 |
dances | +0.102 |
Neg logit contributions | |
Em | -0.151 |
ama | -0.149 |
Gem | -0.148 |
Johnson | -0.145 |
groceries | -0.145 |
Token | nine |
Token ID | 30888 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
dives | +0.177 |
eway | +0.157 |
tricks | +0.149 |
films | +0.148 |
mer | +0.147 |
Neg logit contributions | |
Em | -0.195 |
ama | -0.194 |
Gem | -0.190 |
Johnson | -0.185 |
groceries | -0.185 |
Token | , |
Token ID | 11 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
dives | +0.124 |
tricks | +0.110 |
eway | +0.107 |
dances | +0.107 |
hops | +0.106 |
Neg logit contributions | |
ama | -0.078 |
groceries | -0.076 |
Em | -0.076 |
Gem | -0.076 |
checkout | -0.074 |
Token | thirty |
Token ID | 12277 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
dives | +0.126 |
eway | +0.112 |
films | +0.112 |
tricks | +0.111 |
mer | +0.111 |
Neg logit contributions | |
ama | -0.082 |
Em | -0.080 |
groceries | -0.078 |
Gem | -0.078 |
Johnson | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
dives | +0.086 |
eway | +0.074 |
tricks | +0.071 |
films | +0.068 |
mer | +0.068 |
Neg logit contributions | |
Em | -0.125 |
ama | -0.123 |
Gem | -0.122 |
groceries | -0.120 |
Johnson | -0.119 |
Token | thirty |
Token ID | 12277 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
dives | +0.127 |
eway | +0.113 |
films | +0.113 |
mer | +0.112 |
tricks | +0.112 |
Neg logit contributions | |
ama | -0.081 |
Em | -0.079 |
groceries | -0.078 |
Gem | -0.077 |
Johnson | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
dives | +0.024 |
eway | +0.022 |
RO | +0.021 |
films | +0.021 |
Fly | +0.021 |
Neg logit contributions | |
Em | -0.011 |
ama | -0.010 |
groceries | -0.010 |
checkout | -0.010 |
expensive | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
eway | +0.015 |
dives | +0.015 |
mer | +0.014 |
ile | +0.014 |
ull | +0.014 |
Neg logit contributions | |
Em | -0.007 |
ama | -0.007 |
grandma | -0.007 |
checkout | -0.007 |
Johnson | -0.007 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
eway | +0.010 |
dives | +0.010 |
films | +0.010 |
tricks | +0.009 |
mer | +0.009 |
Neg logit contributions | |
Em | -0.006 |
expensive | -0.006 |
already | -0.006 |
checkout | -0.006 |
Gem | -0.006 |
Token | through |
Token ID | 832 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
eway | +0.033 |
dives | +0.032 |
villains | +0.030 |
films | +0.030 |
Fly | +0.029 |
Neg logit contributions | |
Em | -0.027 |
expensive | -0.026 |
Gem | -0.026 |
groceries | -0.025 |
tired | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
dives | +0.061 |
eway | +0.057 |
igators | +0.054 |
films | +0.054 |
RO | +0.054 |
Neg logit contributions | |
Em | -0.030 |
groceries | -0.028 |
Gem | -0.028 |
expensive | -0.028 |
Johnson | -0.027 |
Token | ey |
Token ID | 1926 |
Feature activation | +7.30e+00 |
Pos logit contributions | |
Em | +0.006 |
ama | +0.006 |
Gem | +0.006 |
Johnson | +0.006 |
groceries | +0.006 |
Neg logit contributions | |
dives | -0.009 |
eway | -0.008 |
tricks | -0.008 |
films | -0.008 |
mer | -0.008 |
Token | ep |
Token ID | 538 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
dives | +0.185 |
villains | +0.163 |
films | +0.162 |
dances | +0.155 |
warriors | +0.154 |
Neg logit contributions | |
ama | -0.171 |
infected | -0.165 |
expensive | -0.160 |
already | -0.160 |
bur | -0.160 |
Token | iece |
Token ID | 8535 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
dives | +0.018 |
eway | +0.016 |
films | +0.016 |
igators | +0.016 |
RO | +0.015 |
Neg logit contributions | |
ama | -0.015 |
Em | -0.015 |
Gem | -0.014 |
first | -0.014 |
checkout | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
dives | +0.021 |
RO | +0.019 |
igators | +0.019 |
films | +0.018 |
Fly | +0.018 |
Neg logit contributions | |
ama | -0.009 |
already | -0.008 |
first | -0.008 |
no | -0.007 |
Gem | -0.007 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
eway | +0.008 |
dives | +0.008 |
films | +0.008 |
igators | +0.008 |
villains | +0.007 |
Neg logit contributions | |
Em | -0.004 |
Gem | -0.004 |
first | -0.004 |
grandma | -0.004 |
tired | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
dives | +0.022 |
eway | +0.021 |
RO | +0.020 |
films | +0.019 |
villains | +0.019 |
Neg logit contributions | |
Em | -0.008 |
expensive | -0.007 |
grandma | -0.007 |
Gem | -0.007 |
groceries | -0.007 |
Token | slide |
Token ID | 10649 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
dives | +0.025 |
eway | +0.023 |
films | +0.022 |
tricks | +0.022 |
mer | +0.022 |
Neg logit contributions | |
Em | -0.017 |
ama | -0.017 |
Gem | -0.016 |
groceries | -0.016 |
checkout | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Em | +0.015 |
ama | +0.015 |
Gem | +0.015 |
groceries | +0.014 |
Johnson | +0.014 |
Neg logit contributions | |
dives | -0.020 |
eway | -0.018 |
tricks | -0.017 |
mer | -0.017 |
films | -0.017 |
Token | looked |
Token ID | 3114 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
Em | +0.003 |
checkout | +0.003 |
Gem | +0.003 |
grandma | +0.003 |
groceries | +0.003 |
Neg logit contributions | |
eway | -0.005 |
dives | -0.005 |
ile | -0.005 |
films | -0.005 |
ag | -0.005 |
Token | through |
Token ID | 832 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
dives | +0.025 |
eway | +0.025 |
villains | +0.023 |
films | +0.023 |
Fly | +0.022 |
Neg logit contributions | |
Em | -0.022 |
expensive | -0.021 |
Gem | -0.021 |
groceries | -0.021 |
ama | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
dives | +0.048 |
eway | +0.045 |
films | +0.042 |
RO | +0.042 |
tricks | +0.042 |
Neg logit contributions | |
Em | -0.026 |
Gem | -0.025 |
groceries | -0.024 |
expensive | -0.024 |
ama | -0.024 |
Token | ey |
Token ID | 1926 |
Feature activation | +7.25e+00 |
Pos logit contributions | |
groceries | +0.010 |
Em | +0.010 |
ama | +0.010 |
checkout | +0.010 |
Gem | +0.010 |
Neg logit contributions | |
dives | -0.020 |
eway | -0.019 |
Fly | -0.018 |
villains | -0.018 |
films | -0.018 |
Token | ep |
Token ID | 538 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
dives | +0.192 |
villains | +0.170 |
films | +0.170 |
dances | +0.163 |
Fly | +0.162 |
Neg logit contributions | |
ama | -0.158 |
infected | -0.157 |
bur | -0.151 |
expensive | -0.151 |
already | -0.149 |
Token | iece |
Token ID | 8535 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
dives | +0.006 |
eway | +0.005 |
films | +0.005 |
igators | +0.005 |
RO | +0.005 |
Neg logit contributions | |
ama | -0.003 |
Em | -0.003 |
first | -0.003 |
Gem | -0.003 |
groceries | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
dives | +0.008 |
RO | +0.008 |
igators | +0.007 |
Fly | +0.007 |
films | +0.007 |
Neg logit contributions | |
ama | -0.003 |
already | -0.002 |
first | -0.002 |
Gem | -0.002 |
no | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
dives | +0.000 |
eway | +0.000 |
igators | +0.000 |
films | +0.000 |
mer | +0.000 |
Neg logit contributions | |
Em | -0.000 |
Gem | -0.000 |
ama | -0.000 |
Johnson | -0.000 |
checkout | -0.000 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
Em | +0.003 |
ama | +0.003 |
Gem | +0.003 |
checkout | +0.003 |
expensive | +0.003 |
Neg logit contributions | |
dives | -0.004 |
eway | -0.004 |
films | -0.004 |
tricks | -0.004 |
mer | -0.004 |
Token | nine |
Token ID | 30888 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
dives | +0.177 |
eway | +0.157 |
tricks | +0.149 |
films | +0.148 |
mer | +0.147 |
Neg logit contributions | |
Em | -0.195 |
ama | -0.194 |
Gem | -0.190 |
Johnson | -0.185 |
groceries | -0.185 |
Token | , |
Token ID | 11 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
dives | +0.124 |
tricks | +0.110 |
eway | +0.107 |
dances | +0.107 |
hops | +0.106 |
Neg logit contributions | |
ama | -0.078 |
groceries | -0.076 |
Em | -0.076 |
Gem | -0.076 |
checkout | -0.074 |
Token | thirty |
Token ID | 12277 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
dives | +0.126 |
eway | +0.112 |
films | +0.112 |
tricks | +0.111 |
mer | +0.111 |
Neg logit contributions | |
ama | -0.082 |
Em | -0.080 |
groceries | -0.078 |
Gem | -0.078 |
Johnson | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
dives | +0.086 |
eway | +0.074 |
tricks | +0.071 |
films | +0.068 |
mer | +0.068 |
Neg logit contributions | |
Em | -0.125 |
ama | -0.123 |
Gem | -0.122 |
groceries | -0.120 |
Johnson | -0.119 |
Token | thirty |
Token ID | 12277 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
dives | +0.127 |
eway | +0.113 |
films | +0.113 |
mer | +0.112 |
tricks | +0.112 |
Neg logit contributions | |
ama | -0.081 |
Em | -0.079 |
groceries | -0.078 |
Gem | -0.077 |
Johnson | -0.077 |
Token | - |
Token ID | 12 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
dives | +0.081 |
eway | +0.069 |
tricks | +0.066 |
films | +0.064 |
mer | +0.064 |
Neg logit contributions | |
Em | -0.118 |
ama | -0.117 |
Gem | -0.115 |
groceries | -0.113 |
Johnson | -0.113 |
Token | one |
Token ID | 505 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
dives | +0.166 |
eway | +0.146 |
tricks | +0.139 |
films | +0.139 |
mer | +0.138 |
Neg logit contributions | |
Em | -0.178 |
ama | -0.177 |
Gem | -0.174 |
Johnson | -0.168 |
groceries | -0.168 |
Token | , |
Token ID | 11 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
dives | +0.068 |
eway | +0.061 |
tricks | +0.060 |
films | +0.058 |
dances | +0.057 |
Neg logit contributions | |
Em | -0.051 |
ama | -0.050 |
Gem | -0.050 |
groceries | -0.049 |
checkout | -0.048 |
Token | thirty |
Token ID | 12277 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
dives | +0.123 |
films | +0.109 |
eway | +0.109 |
mer | +0.108 |
tricks | +0.108 |
Neg logit contributions | |
ama | -0.080 |
Em | -0.077 |
groceries | -0.076 |
Johnson | -0.075 |
Gem | -0.075 |
Token | - |
Token ID | 12 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
dives | +0.070 |
eway | +0.060 |
tricks | +0.057 |
films | +0.055 |
mer | +0.054 |
Neg logit contributions | |
Em | -0.107 |
ama | -0.105 |
Gem | -0.105 |
groceries | -0.103 |
Johnson | -0.103 |
Token | two |
Token ID | 11545 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
dives | +0.150 |
eway | +0.133 |
tricks | +0.126 |
films | +0.125 |
mer | +0.125 |
Neg logit contributions | |
Em | -0.164 |
ama | -0.164 |
Gem | -0.160 |
Johnson | -0.156 |
groceries | -0.156 |
Token | and |
Token ID | 290 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
dives | +0.041 |
eway | +0.037 |
mer | +0.036 |
tricks | +0.036 |
films | +0.035 |
Neg logit contributions | |
Em | -0.024 |
ama | -0.024 |
Gem | -0.023 |
groceries | -0.022 |
Johnson | -0.022 |
Token | carefully |
Token ID | 7773 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
dives | +0.049 |
eway | +0.047 |
films | +0.046 |
RO | +0.045 |
ile | +0.044 |
Neg logit contributions | |
Em | -0.020 |
buy | -0.020 |
Gem | -0.020 |
groceries | -0.019 |
expensive | -0.019 |
Token | picked |
Token ID | 6497 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
dives | +0.061 |
eway | +0.057 |
films | +0.055 |
mer | +0.054 |
tricks | +0.054 |
Neg logit contributions | |
Em | -0.037 |
Gem | -0.036 |
ama | -0.036 |
checkout | -0.034 |
groceries | -0.034 |
Token | up |
Token ID | 510 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
dives | +0.024 |
eway | +0.022 |
films | +0.021 |
tricks | +0.021 |
mer | +0.021 |
Neg logit contributions | |
Em | -0.018 |
ama | -0.017 |
Gem | -0.017 |
groceries | -0.017 |
Johnson | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
dives | +0.116 |
eway | +0.106 |
tricks | +0.101 |
films | +0.101 |
mer | +0.101 |
Neg logit contributions | |
Em | -0.070 |
ama | -0.069 |
Gem | -0.068 |
groceries | -0.066 |
Johnson | -0.065 |
Token | pe |
Token ID | 613 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
dives | +0.062 |
eway | +0.057 |
tricks | +0.055 |
mer | +0.054 |
films | +0.054 |
Neg logit contributions | |
Em | -0.041 |
ama | -0.040 |
Gem | -0.039 |
Johnson | -0.038 |
groceries | -0.037 |
Token | b |
Token ID | 65 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
dives | +0.157 |
eway | +0.140 |
films | +0.138 |
mer | +0.134 |
Fly | +0.131 |
Neg logit contributions | |
ama | -0.160 |
Em | -0.158 |
Gem | -0.157 |
groceries | -0.152 |
expensive | -0.150 |
Token | ble |
Token ID | 903 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
dives | +0.118 |
eway | +0.107 |
films | +0.106 |
mer | +0.103 |
tricks | +0.102 |
Neg logit contributions | |
ama | -0.069 |
Em | -0.068 |
Gem | -0.067 |
groceries | -0.063 |
Johnson | -0.062 |
Token | for |
Token ID | 329 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
dives | +0.067 |
eway | +0.061 |
films | +0.059 |
tricks | +0.058 |
mer | +0.058 |
Neg logit contributions | |
ama | -0.048 |
Em | -0.048 |
Gem | -0.047 |
groceries | -0.046 |
Johnson | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
dives | +0.039 |
eway | +0.035 |
films | +0.033 |
tricks | +0.033 |
mer | +0.033 |
Neg logit contributions | |
Em | -0.027 |
ama | -0.026 |
Gem | -0.026 |
groceries | -0.025 |
Johnson | -0.025 |
Token | bunny |
Token ID | 44915 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
dives | +0.029 |
eway | +0.026 |
tricks | +0.025 |
mer | +0.025 |
films | +0.025 |
Neg logit contributions | |
Em | -0.017 |
ama | -0.017 |
Gem | -0.017 |
Johnson | -0.016 |
groceries | -0.016 |
Token | thirty |
Token ID | 12277 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
dives | +0.127 |
eway | +0.113 |
films | +0.113 |
mer | +0.112 |
tricks | +0.112 |
Neg logit contributions | |
ama | -0.081 |
Em | -0.079 |
groceries | -0.078 |
Gem | -0.077 |
Johnson | -0.077 |
Token | - |
Token ID | 12 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
dives | +0.081 |
eway | +0.069 |
tricks | +0.066 |
films | +0.064 |
mer | +0.064 |
Neg logit contributions | |
Em | -0.118 |
ama | -0.117 |
Gem | -0.115 |
groceries | -0.113 |
Johnson | -0.113 |
Token | one |
Token ID | 505 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
dives | +0.166 |
eway | +0.146 |
tricks | +0.139 |
films | +0.139 |
mer | +0.138 |
Neg logit contributions | |
Em | -0.178 |
ama | -0.177 |
Gem | -0.174 |
Johnson | -0.168 |
groceries | -0.168 |
Token | , |
Token ID | 11 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
dives | +0.068 |
eway | +0.061 |
tricks | +0.060 |
films | +0.058 |
dances | +0.057 |
Neg logit contributions | |
Em | -0.051 |
ama | -0.050 |
Gem | -0.050 |
groceries | -0.049 |
checkout | -0.048 |
Token | thirty |
Token ID | 12277 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
dives | +0.123 |
films | +0.109 |
eway | +0.109 |
mer | +0.108 |
tricks | +0.108 |
Neg logit contributions | |
ama | -0.080 |
Em | -0.077 |
groceries | -0.076 |
Johnson | -0.075 |
Gem | -0.075 |
Token | - |
Token ID | 12 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
dives | +0.070 |
eway | +0.060 |
tricks | +0.057 |
films | +0.055 |
mer | +0.054 |
Neg logit contributions | |
Em | -0.107 |
ama | -0.105 |
Gem | -0.105 |
groceries | -0.103 |
Johnson | -0.103 |
Token | two |
Token ID | 11545 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
dives | +0.150 |
eway | +0.133 |
tricks | +0.126 |
films | +0.125 |
mer | +0.125 |
Neg logit contributions | |
Em | -0.164 |
ama | -0.164 |
Gem | -0.160 |
Johnson | -0.156 |
groceries | -0.156 |
Token | , |
Token ID | 11 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
dives | +0.066 |
tricks | +0.060 |
eway | +0.057 |
dances | +0.056 |
hops | +0.055 |
Neg logit contributions | |
Em | -0.049 |
groceries | -0.048 |
Johnson | -0.048 |
Gem | -0.047 |
ama | -0.047 |
Token | thirty |
Token ID | 12277 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
dives | +0.110 |
eway | +0.098 |
films | +0.097 |
mer | +0.097 |
tricks | +0.097 |
Neg logit contributions | |
ama | -0.066 |
Em | -0.064 |
groceries | -0.063 |
Gem | -0.062 |
Johnson | -0.062 |
Token | - |
Token ID | 12 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
dives | +0.053 |
eway | +0.045 |
tricks | +0.044 |
films | +0.041 |
mer | +0.041 |
Neg logit contributions | |
Em | -0.086 |
ama | -0.085 |
Gem | -0.084 |
Johnson | -0.083 |
groceries | -0.083 |
Token | three |
Token ID | 15542 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
dives | +0.127 |
eway | +0.113 |
tricks | +0.108 |
mer | +0.106 |
films | +0.106 |
Neg logit contributions | |
ama | -0.131 |
Em | -0.131 |
Gem | -0.128 |
Johnson | -0.125 |
groceries | -0.125 |
Token | |
Token ID | 220 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ama | +0.003 |
Em | +0.003 |
Gem | +0.003 |
Johnson | +0.003 |
checkout | +0.003 |
Neg logit contributions | |
dives | -0.005 |
eway | -0.004 |
tricks | -0.004 |
films | -0.004 |
mer | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
checkout | +0.035 |
Em | +0.035 |
infected | +0.034 |
Gem | +0.034 |
groceries | +0.034 |
Neg logit contributions | |
dives | -0.044 |
eway | -0.043 |
films | -0.038 |
tricks | -0.038 |
ull | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
dives | +0.002 |
eway | +0.002 |
tricks | +0.002 |
mer | +0.002 |
films | +0.002 |
Neg logit contributions | |
Em | -0.001 |
ama | -0.001 |
Gem | -0.001 |
groceries | -0.001 |
Johnson | -0.001 |
Token | M |
Token ID | 44 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ama | +0.013 |
Em | +0.012 |
Gem | +0.012 |
Johnson | +0.012 |
checkout | +0.011 |
Neg logit contributions | |
dives | -0.021 |
eway | -0.019 |
tricks | -0.019 |
films | -0.019 |
mer | -0.018 |
Token | ummy |
Token ID | 13513 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Em | +0.019 |
Gem | +0.017 |
infected | +0.017 |
checkout | +0.017 |
Johnson | +0.017 |
Neg logit contributions | |
dives | -0.054 |
eway | -0.050 |
tricks | -0.049 |
mer | -0.048 |
films | -0.048 |
Token | pe |
Token ID | 613 |
Feature activation | +6.36e+00 |
Pos logit contributions | |
dives | +0.069 |
eway | +0.068 |
tricks | +0.065 |
villains | +0.064 |
poses | +0.063 |
Neg logit contributions | |
ama | -0.031 |
Em | -0.031 |
Gem | -0.030 |
Johnson | -0.029 |
checkout | -0.026 |
Token | ered |
Token ID | 1068 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
dives | +0.158 |
eway | +0.138 |
films | +0.136 |
mer | +0.133 |
tricks | +0.132 |
Neg logit contributions | |
ama | -0.157 |
Em | -0.151 |
Gem | -0.149 |
infected | -0.143 |
checkout | -0.142 |
Token | down |
Token ID | 866 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
dives | +0.052 |
villains | +0.049 |
eway | +0.048 |
tricks | +0.047 |
RO | +0.045 |
Neg logit contributions | |
Em | -0.042 |
Gem | -0.042 |
groceries | -0.041 |
ama | -0.040 |
expensive | -0.039 |
Token | at |
Token ID | 379 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
dives | +0.020 |
eway | +0.018 |
tricks | +0.018 |
films | +0.018 |
mer | +0.018 |
Neg logit contributions | |
Em | -0.015 |
ama | -0.015 |
Gem | -0.014 |
Johnson | -0.014 |
groceries | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
ama | +0.006 |
Em | +0.006 |
infected | +0.006 |
Gem | +0.006 |
Johnson | +0.005 |
Neg logit contributions | |
dives | -0.007 |
eway | -0.006 |
films | -0.006 |
mer | -0.006 |
tricks | -0.006 |
Token | ground |
Token ID | 2323 |
Feature activation | +3.21e-03 |
Pos logit contributions | |
dives | +0.019 |
eway | +0.016 |
mer | +0.016 |
tricks | +0.016 |
films | +0.016 |
Neg logit contributions | |
ama | -0.014 |
Em | -0.014 |
Gem | -0.014 |
infected | -0.013 |
Johnson | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
dives | +0.004 |
eway | +0.004 |
Fly | +0.004 |
tricks | +0.004 |
films | +0.004 |
Neg logit contributions | |
checkout | -0.004 |
Em | -0.004 |
groceries | -0.003 |
infected | -0.003 |
Gem | -0.003 |
Token | Mary |
Token ID | 24119 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Em | +0.016 |
ama | +0.016 |
Gem | +0.016 |
groceries | +0.015 |
Johnson | +0.015 |
Neg logit contributions | |
dives | -0.023 |
eway | -0.021 |
tricks | -0.020 |
films | -0.020 |
mer | -0.020 |
Token | carefully |
Token ID | 7773 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
dives | +0.033 |
eway | +0.030 |
tricks | +0.029 |
films | +0.029 |
mer | +0.029 |
Neg logit contributions | |
Em | -0.023 |
ama | -0.023 |
Gem | -0.023 |
Johnson | -0.022 |
groceries | -0.022 |
Token | placed |
Token ID | 4624 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
dives | +0.050 |
eway | +0.045 |
tricks | +0.043 |
films | +0.043 |
mer | +0.043 |
Neg logit contributions | |
Em | -0.037 |
ama | -0.037 |
Gem | -0.036 |
Johnson | -0.035 |
groceries | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
dives | +0.012 |
films | +0.011 |
eway | +0.011 |
tricks | +0.011 |
mer | +0.010 |
Neg logit contributions | |
ama | -0.011 |
Em | -0.010 |
Gem | -0.010 |
Johnson | -0.010 |
infected | -0.010 |
Token | pe |
Token ID | 613 |
Feature activation | +6.30e+00 |
Pos logit contributions | |
dives | +0.028 |
tricks | +0.025 |
eway | +0.025 |
films | +0.024 |
mer | +0.024 |
Neg logit contributions | |
Em | -0.022 |
ama | -0.022 |
Gem | -0.021 |
Johnson | -0.021 |
checkout | -0.020 |
Token | b |
Token ID | 65 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
dives | +0.151 |
eway | +0.136 |
films | +0.130 |
mer | +0.130 |
villains | +0.127 |
Neg logit contributions | |
ama | -0.155 |
Em | -0.151 |
Gem | -0.150 |
groceries | -0.147 |
infected | -0.145 |
Token | ble |
Token ID | 903 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
dives | +0.113 |
eway | +0.104 |
tricks | +0.100 |
mer | +0.098 |
films | +0.097 |
Neg logit contributions | |
Em | -0.070 |
ama | -0.067 |
Gem | -0.066 |
checkout | -0.065 |
Johnson | -0.065 |
Token | inside |
Token ID | 2641 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
dives | +0.058 |
eway | +0.052 |
films | +0.050 |
tricks | +0.050 |
mer | +0.049 |
Neg logit contributions | |
ama | -0.057 |
Em | -0.057 |
Gem | -0.056 |
groceries | -0.055 |
Johnson | -0.054 |
Token | her |
Token ID | 607 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ama | +0.007 |
Em | +0.007 |
Gem | +0.007 |
Johnson | +0.007 |
infected | +0.007 |
Neg logit contributions | |
dives | -0.008 |
eway | -0.007 |
films | -0.007 |
tricks | -0.007 |
mer | -0.007 |
Token | dough |
Token ID | 15756 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
dives | +0.005 |
tricks | +0.004 |
films | +0.004 |
eway | +0.004 |
mer | +0.004 |
Neg logit contributions | |
Em | -0.003 |
Gem | -0.003 |
ama | -0.003 |
Johnson | -0.003 |
infected | -0.003 |
Token | children |
Token ID | 1751 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
dives | +0.036 |
eway | +0.033 |
RO | +0.031 |
films | +0.030 |
tricks | +0.030 |
Neg logit contributions | |
Em | -0.025 |
ama | -0.025 |
groceries | -0.024 |
checkout | -0.024 |
Gem | -0.024 |
Token | agreed |
Token ID | 4987 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
dives | +0.055 |
eway | +0.052 |
films | +0.049 |
tricks | +0.049 |
mer | +0.048 |
Neg logit contributions | |
Em | -0.033 |
ama | -0.032 |
Gem | -0.031 |
checkout | -0.030 |
Johnson | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Em | +0.022 |
ama | +0.021 |
Gem | +0.021 |
Johnson | +0.020 |
groceries | +0.020 |
Neg logit contributions | |
dives | -0.038 |
eway | -0.035 |
RO | -0.034 |
films | -0.034 |
mer | -0.033 |
Token | let |
Token ID | 1309 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
eway | +0.036 |
dives | +0.035 |
films | +0.034 |
RO | +0.033 |
tricks | +0.033 |
Neg logit contributions | |
Em | -0.022 |
Gem | -0.022 |
checkout | -0.021 |
already | -0.021 |
buy | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Em | +0.007 |
ama | +0.007 |
Gem | +0.007 |
groceries | +0.007 |
Johnson | +0.007 |
Neg logit contributions | |
dives | -0.008 |
eway | -0.008 |
tricks | -0.007 |
mer | -0.007 |
films | -0.007 |
Token | pe |
Token ID | 613 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
dives | +0.038 |
eway | +0.036 |
RO | +0.033 |
mer | +0.033 |
Fly | +0.033 |
Neg logit contributions | |
ama | -0.019 |
Em | -0.019 |
Gem | -0.018 |
groceries | -0.018 |
expensive | -0.018 |
Token | b |
Token ID | 65 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
dives | +0.182 |
films | +0.175 |
villains | +0.170 |
eway | +0.169 |
mer | +0.167 |
Neg logit contributions | |
ama | -0.115 |
Gem | -0.107 |
infected | -0.105 |
Em | -0.104 |
groceries | -0.103 |
Token | ble |
Token ID | 903 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
dives | +0.098 |
eway | +0.088 |
films | +0.085 |
tricks | +0.084 |
mer | +0.084 |
Neg logit contributions | |
ama | -0.073 |
Em | -0.073 |
Gem | -0.071 |
groceries | -0.069 |
Johnson | -0.068 |
Token | help |
Token ID | 1037 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
dives | +0.091 |
eway | +0.087 |
villains | +0.086 |
films | +0.085 |
RO | +0.083 |
Neg logit contributions | |
Gem | -0.056 |
buy | -0.056 |
Em | -0.055 |
groceries | -0.055 |
ama | -0.055 |
Token | measure |
Token ID | 3953 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Em | +0.002 |
Gem | +0.002 |
ama | +0.002 |
Johnson | +0.002 |
groceries | +0.002 |
Neg logit contributions | |
dives | -0.003 |
eway | -0.003 |
films | -0.003 |
mer | -0.003 |
tricks | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
dives | +0.044 |
eway | +0.040 |
tricks | +0.038 |
films | +0.038 |
mer | +0.038 |
Neg logit contributions | |
Em | -0.032 |
ama | -0.032 |
Gem | -0.031 |
Johnson | -0.030 |
groceries | -0.030 |
Token | 'm |
Token ID | 1101 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
dives | +0.103 |
eway | +0.096 |
films | +0.093 |
tricks | +0.091 |
mer | +0.090 |
Neg logit contributions | |
Em | -0.054 |
ama | -0.052 |
Gem | -0.051 |
infected | -0.049 |
checkout | -0.049 |
Token | glad |
Token ID | 9675 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
dives | +0.073 |
eway | +0.069 |
films | +0.065 |
tricks | +0.064 |
villains | +0.064 |
Neg logit contributions | |
Em | -0.036 |
Gem | -0.034 |
ama | -0.034 |
expensive | -0.032 |
infected | -0.032 |
Token | you |
Token ID | 345 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
dives | +0.028 |
eway | +0.028 |
RO | +0.026 |
films | +0.026 |
mer | +0.025 |
Neg logit contributions | |
Em | -0.010 |
ama | -0.010 |
grandma | -0.009 |
Gem | -0.009 |
Johnson | -0.009 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
dives | +0.065 |
mer | +0.058 |
dances | +0.058 |
tricks | +0.055 |
RO | +0.055 |
Neg logit contributions | |
ama | -0.054 |
groceries | -0.051 |
Gem | -0.049 |
Johnson | -0.048 |
checkout | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
dives | +0.006 |
tricks | +0.006 |
eway | +0.006 |
films | +0.006 |
mer | +0.006 |
Neg logit contributions | |
ama | -0.004 |
Em | -0.004 |
Gem | -0.004 |
Johnson | -0.004 |
checkout | -0.004 |
Token | pe |
Token ID | 613 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
dives | +0.066 |
eway | +0.061 |
films | +0.057 |
tricks | +0.057 |
mer | +0.057 |
Neg logit contributions | |
Em | -0.041 |
ama | -0.041 |
Gem | -0.040 |
groceries | -0.040 |
Johnson | -0.039 |
Token | aches |
Token ID | 3694 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
dives | +0.146 |
eway | +0.129 |
films | +0.125 |
mer | +0.123 |
tricks | +0.122 |
Neg logit contributions | |
ama | -0.154 |
Em | -0.152 |
Gem | -0.150 |
groceries | -0.145 |
expensive | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
dives | +0.006 |
eway | +0.005 |
fish | +0.005 |
tricks | +0.005 |
igators | +0.005 |
Neg logit contributions | |
Em | -0.005 |
ama | -0.005 |
Gem | -0.005 |
infected | -0.005 |
checkout | -0.005 |
Token | Have |
Token ID | 8192 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
dives | +0.030 |
eway | +0.027 |
Fly | +0.026 |
films | +0.026 |
mer | +0.026 |
Neg logit contributions | |
groceries | -0.028 |
ama | -0.028 |
Em | -0.027 |
infected | -0.027 |
Gem | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
dives | +0.080 |
eway | +0.074 |
films | +0.071 |
tricks | +0.070 |
mer | +0.070 |
Neg logit contributions | |
Em | -0.042 |
ama | -0.041 |
Gem | -0.041 |
groceries | -0.039 |
Johnson | -0.038 |
Token | nice |
Token ID | 3621 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Em | +0.004 |
ama | +0.004 |
Gem | +0.003 |
groceries | +0.003 |
checkout | +0.003 |
Neg logit contributions | |
dives | -0.009 |
eway | -0.008 |
films | -0.008 |
tricks | -0.008 |
mer | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
dives | +0.010 |
aids | +0.010 |
zo | +0.010 |
fins | +0.010 |
ull | +0.010 |
Neg logit contributions | |
first | -0.002 |
groceries | -0.001 |
buy | -0.001 |
Johnson | -0.001 |
Em | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
Em | +0.029 |
ama | +0.029 |
Gem | +0.028 |
Johnson | +0.027 |
groceries | +0.027 |
Neg logit contributions | |
dives | -0.056 |
eway | -0.051 |
tricks | -0.049 |
films | -0.049 |
mer | -0.049 |
Token | accidentally |
Token ID | 14716 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Em | +0.013 |
ama | +0.013 |
Gem | +0.013 |
groceries | +0.012 |
Johnson | +0.012 |
Neg logit contributions | |
dives | -0.015 |
eway | -0.014 |
tricks | -0.013 |
mer | -0.013 |
films | -0.013 |
Token | threw |
Token ID | 9617 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
dives | +0.056 |
eway | +0.054 |
films | +0.053 |
igators | +0.051 |
tricks | +0.049 |
Neg logit contributions | |
Em | -0.031 |
infected | -0.030 |
Gem | -0.029 |
ama | -0.029 |
Johnson | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
dives | +0.015 |
eway | +0.015 |
films | +0.014 |
mer | +0.014 |
fish | +0.014 |
Neg logit contributions | |
Em | -0.004 |
expensive | -0.004 |
groceries | -0.004 |
infected | -0.004 |
Gem | -0.004 |
Token | pe |
Token ID | 613 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
dives | +0.038 |
eway | +0.037 |
films | +0.036 |
dances | +0.035 |
Fly | +0.034 |
Neg logit contributions | |
expensive | -0.021 |
Em | -0.019 |
groceries | -0.019 |
infected | -0.018 |
ama | -0.018 |
Token | b |
Token ID | 65 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
dives | +0.141 |
eway | +0.126 |
films | +0.123 |
mer | +0.119 |
dances | +0.116 |
Neg logit contributions | |
ama | -0.153 |
Em | -0.151 |
Gem | -0.149 |
infected | -0.145 |
groceries | -0.145 |
Token | ble |
Token ID | 903 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
dives | +0.108 |
eway | +0.100 |
tricks | +0.097 |
mer | +0.094 |
ull | +0.093 |
Neg logit contributions | |
Em | -0.071 |
checkout | -0.069 |
Gem | -0.068 |
Johnson | -0.068 |
groceries | -0.067 |
Token | at |
Token ID | 379 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
dives | +0.060 |
films | +0.058 |
eway | +0.057 |
villains | +0.054 |
dances | +0.054 |
Neg logit contributions | |
first | -0.033 |
infected | -0.033 |
Em | -0.033 |
expensive | -0.033 |
already | -0.033 |
Token | her |
Token ID | 607 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
ama | +0.010 |
severe | +0.009 |
pricey | +0.009 |
infected | +0.009 |
pling | +0.009 |
Neg logit contributions | |
dives | -0.009 |
eway | -0.008 |
Fly | -0.008 |
films | -0.008 |
tricks | -0.008 |
Token | friend |
Token ID | 1545 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
Em | +0.002 |
Gem | +0.002 |
checkout | +0.002 |
ama | +0.002 |
groceries | +0.002 |
Neg logit contributions | |
dives | -0.002 |
tricks | -0.002 |
mer | -0.002 |
eway | -0.002 |
dances | -0.002 |
Token | spoon |
Token ID | 24556 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
eway | +0.052 |
dives | +0.052 |
villains | +0.048 |
films | +0.048 |
tricks | +0.048 |
Neg logit contributions | |
Em | -0.033 |
checkout | -0.032 |
Gem | -0.032 |
groceries | -0.031 |
expensive | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
dives | +0.032 |
eway | +0.028 |
mer | +0.027 |
tricks | +0.027 |
dances | +0.026 |
Neg logit contributions | |
Em | -0.029 |
ama | -0.029 |
Gem | -0.028 |
Johnson | -0.027 |
checkout | -0.027 |
Token | She |
Token ID | 1375 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
dives | +0.033 |
eway | +0.030 |
tricks | +0.029 |
films | +0.029 |
mer | +0.029 |
Neg logit contributions | |
Em | -0.019 |
ama | -0.019 |
Gem | -0.019 |
Johnson | -0.018 |
groceries | -0.018 |
Token | put |
Token ID | 1234 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
eway | +0.031 |
dives | +0.030 |
films | +0.028 |
villains | +0.028 |
tricks | +0.028 |
Neg logit contributions | |
Em | -0.020 |
ama | -0.020 |
checkout | -0.020 |
expensive | -0.019 |
Gem | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
dives | +0.044 |
mer | +0.038 |
tricks | +0.037 |
eway | +0.037 |
films | +0.037 |
Neg logit contributions | |
ama | -0.037 |
Em | -0.036 |
Johnson | -0.035 |
Gem | -0.035 |
checkout | -0.034 |
Token | pe |
Token ID | 613 |
Feature activation | +6.03e+00 |
Pos logit contributions | |
dives | +0.038 |
eway | +0.035 |
tricks | +0.034 |
films | +0.034 |
mer | +0.033 |
Neg logit contributions | |
Em | -0.023 |
ama | -0.023 |
Gem | -0.023 |
Johnson | -0.022 |
groceries | -0.022 |
Token | aches |
Token ID | 3694 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
dives | +0.141 |
eway | +0.127 |
films | +0.121 |
mer | +0.119 |
tricks | +0.118 |
Neg logit contributions | |
ama | -0.151 |
Em | -0.150 |
Gem | -0.148 |
groceries | -0.144 |
checkout | -0.142 |
Token | in |
Token ID | 287 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
dives | +0.026 |
eway | +0.022 |
mer | +0.022 |
tricks | +0.021 |
films | +0.020 |
Neg logit contributions | |
Em | -0.036 |
ama | -0.035 |
Gem | -0.034 |
Johnson | -0.034 |
checkout | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
dives | +0.018 |
mer | +0.017 |
eway | +0.016 |
films | +0.016 |
tricks | +0.016 |
Neg logit contributions | |
ama | -0.017 |
Em | -0.016 |
infected | -0.016 |
ongo | -0.015 |
Johnson | -0.015 |
Token | bowl |
Token ID | 9396 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
dives | +0.017 |
eway | +0.015 |
films | +0.015 |
tricks | +0.015 |
mer | +0.014 |
Neg logit contributions | |
Em | -0.009 |
ama | -0.009 |
Gem | -0.009 |
groceries | -0.009 |
checkout | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
Em | +0.032 |
ama | +0.030 |
Gem | +0.030 |
infected | +0.029 |
Johnson | +0.029 |
Neg logit contributions | |
dives | -0.032 |
eway | -0.029 |
mer | -0.028 |
films | -0.027 |
tricks | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
dives | +0.037 |
eway | +0.034 |
tricks | +0.033 |
films | +0.032 |
mer | +0.032 |
Neg logit contributions | |
Em | -0.026 |
ama | -0.026 |
Gem | -0.025 |
Johnson | -0.024 |
groceries | -0.024 |
Token | Anna |
Token ID | 11735 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
dives | +0.015 |
eway | +0.013 |
tricks | +0.013 |
films | +0.013 |
dances | +0.012 |
Neg logit contributions | |
Em | -0.012 |
Gem | -0.011 |
ama | -0.011 |
Johnson | -0.011 |
groceries | -0.011 |
Token | picked |
Token ID | 6497 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Em | +0.005 |
ama | +0.005 |
Gem | +0.005 |
groceries | +0.005 |
Johnson | +0.005 |
Neg logit contributions | |
dives | -0.006 |
eway | -0.006 |
tricks | -0.005 |
films | -0.005 |
mer | -0.005 |
Token | up |
Token ID | 510 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
dives | +0.003 |
eway | +0.003 |
tricks | +0.003 |
mer | +0.003 |
films | +0.003 |
Neg logit contributions | |
Em | -0.002 |
ama | -0.002 |
Gem | -0.002 |
groceries | -0.002 |
Johnson | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
dives | +0.085 |
eway | +0.078 |
tricks | +0.075 |
films | +0.075 |
mer | +0.074 |
Neg logit contributions | |
Em | -0.049 |
ama | -0.049 |
Gem | -0.048 |
Johnson | -0.046 |
groceries | -0.046 |
Token | pe |
Token ID | 613 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
dives | +0.051 |
eway | +0.047 |
films | +0.045 |
tricks | +0.044 |
mer | +0.044 |
Neg logit contributions | |
Em | -0.030 |
ama | -0.029 |
Gem | -0.029 |
Johnson | -0.028 |
groceries | -0.028 |
Token | b |
Token ID | 65 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
dives | +0.146 |
films | +0.132 |
eway | +0.131 |
mer | +0.125 |
villains | +0.125 |
Neg logit contributions | |
ama | -0.145 |
Em | -0.142 |
Gem | -0.140 |
expensive | -0.137 |
groceries | -0.137 |
Token | ble |
Token ID | 903 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
dives | +0.092 |
eway | +0.086 |
tricks | +0.083 |
mer | +0.081 |
ull | +0.080 |
Neg logit contributions | |
Em | -0.062 |
checkout | -0.060 |
Johnson | -0.060 |
groceries | -0.059 |
Gem | -0.059 |
Token | that |
Token ID | 326 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
dives | +0.043 |
eway | +0.039 |
films | +0.038 |
RO | +0.037 |
villains | +0.037 |
Neg logit contributions | |
ama | -0.023 |
Em | -0.023 |
Gem | -0.022 |
groceries | -0.022 |
Johnson | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
Em | +0.018 |
Gem | +0.017 |
ama | +0.017 |
expensive | +0.016 |
Johnson | +0.016 |
Neg logit contributions | |
dives | -0.029 |
eway | -0.027 |
films | -0.026 |
tricks | -0.025 |
villains | -0.025 |
Token | different |
Token ID | 1180 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ama | +0.001 |
Em | +0.001 |
Gem | +0.001 |
Johnson | +0.001 |
groceries | +0.001 |
Neg logit contributions | |
dives | -0.002 |
eway | -0.002 |
tricks | -0.002 |
mer | -0.002 |
films | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ama | +0.007 |
Em | +0.006 |
Gem | +0.006 |
expensive | +0.006 |
groceries | +0.006 |
Neg logit contributions | |
dives | -0.009 |
eway | -0.008 |
tricks | -0.008 |
films | -0.008 |
villains | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
dives | +0.063 |
eway | +0.057 |
mer | +0.055 |
tricks | +0.055 |
films | +0.055 |
Neg logit contributions | |
Em | -0.034 |
ama | -0.033 |
Gem | -0.033 |
checkout | -0.032 |
groceries | -0.032 |
Token | she |
Token ID | 673 |
Feature activation | -8.70e-03 |
Pos logit contributions | |
dives | +0.005 |
eway | +0.005 |
tricks | +0.004 |
films | +0.004 |
mer | +0.004 |
Neg logit contributions | |
Em | -0.003 |
ama | -0.003 |
Gem | -0.003 |
Johnson | -0.003 |
groceries | -0.003 |
Token | found |
Token ID | 1043 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Em | +0.000 |
ama | +0.000 |
Gem | +0.000 |
expensive | +0.000 |
checkout | +0.000 |
Neg logit contributions | |
dives | -0.000 |
eway | -0.000 |
tricks | -0.000 |
films | -0.000 |
poses | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
dives | +0.005 |
eway | +0.005 |
mer | +0.004 |
tricks | +0.004 |
films | +0.004 |
Neg logit contributions | |
ama | -0.003 |
Em | -0.003 |
Gem | -0.003 |
Johnson | -0.003 |
checkout | -0.003 |
Token | pe |
Token ID | 613 |
Feature activation | +6.01e+00 |
Pos logit contributions | |
dives | +0.040 |
eway | +0.037 |
films | +0.036 |
tricks | +0.035 |
RO | +0.035 |
Neg logit contributions | |
Em | -0.017 |
ama | -0.017 |
Gem | -0.017 |
expensive | -0.016 |
groceries | -0.016 |
Token | b |
Token ID | 65 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
dives | +0.141 |
eway | +0.125 |
films | +0.124 |
mer | +0.118 |
Fly | +0.117 |
Neg logit contributions | |
ama | -0.151 |
Em | -0.148 |
Gem | -0.147 |
expensive | -0.142 |
groceries | -0.141 |
Token | ble |
Token ID | 903 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
dives | +0.100 |
eway | +0.094 |
tricks | +0.090 |
mer | +0.089 |
ull | +0.087 |
Neg logit contributions | |
Em | -0.066 |
checkout | -0.064 |
groceries | -0.064 |
Gem | -0.063 |
Johnson | -0.062 |
Token | that |
Token ID | 326 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
dives | +0.052 |
eway | +0.048 |
films | +0.048 |
RO | +0.046 |
villains | +0.046 |
Neg logit contributions | |
ama | -0.032 |
Em | -0.031 |
Gem | -0.031 |
expensive | -0.031 |
Johnson | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Em | +0.014 |
ama | +0.014 |
Gem | +0.013 |
Johnson | +0.013 |
groceries | +0.013 |
Neg logit contributions | |
dives | -0.021 |
eway | -0.019 |
films | -0.018 |
tricks | -0.018 |
mer | -0.018 |
Token | very |
Token ID | 845 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
dives | +0.012 |
eway | +0.011 |
films | +0.011 |
tricks | +0.011 |
dances | +0.011 |
Neg logit contributions | |
Em | -0.005 |
ama | -0.005 |
Gem | -0.005 |
expensive | -0.004 |
Johnson | -0.004 |
Token | me |
Token ID | 502 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
ama | +0.033 |
Em | +0.032 |
groceries | +0.032 |
Gem | +0.032 |
infected | +0.031 |
Neg logit contributions | |
dives | -0.030 |
dances | -0.024 |
hops | -0.024 |
tricks | -0.024 |
mer | -0.024 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
dives | +0.150 |
films | +0.145 |
eway | +0.144 |
villains | +0.143 |
RO | +0.138 |
Neg logit contributions | |
ama | -0.073 |
Em | -0.070 |
first | -0.068 |
Gem | -0.068 |
already | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
dives | +0.054 |
eway | +0.051 |
tricks | +0.049 |
films | +0.048 |
mer | +0.047 |
Neg logit contributions | |
Em | -0.026 |
Gem | -0.025 |
ama | -0.024 |
Johnson | -0.023 |
grandma | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
dives | +0.066 |
tricks | +0.060 |
eway | +0.059 |
films | +0.059 |
mer | +0.058 |
Neg logit contributions | |
ama | -0.023 |
Em | -0.023 |
Gem | -0.021 |
Johnson | -0.020 |
grandma | -0.018 |
Token | An |
Token ID | 2025 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
dives | +0.035 |
tricks | +0.031 |
films | +0.031 |
eway | +0.031 |
dances | +0.030 |
Neg logit contributions | |
Em | -0.016 |
ama | -0.016 |
Gem | -0.015 |
Johnson | -0.015 |
Mom | -0.014 |
Token | ch |
Token ID | 354 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
dives | +0.048 |
eway | +0.044 |
tricks | +0.043 |
films | +0.042 |
mer | +0.042 |
Neg logit contributions | |
Em | -0.023 |
ama | -0.023 |
expensive | -0.022 |
Gem | -0.021 |
checkout | -0.020 |
Token | or |
Token ID | 273 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
dives | +0.148 |
films | +0.132 |
warriors | +0.128 |
villains | +0.126 |
tricks | +0.126 |
Neg logit contributions | |
ama | -0.152 |
Em | -0.141 |
Johnson | -0.134 |
infected | -0.134 |
Gem | -0.133 |
Token | said |
Token ID | 531 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
dives | +0.090 |
eway | +0.081 |
films | +0.079 |
mer | +0.077 |
tricks | +0.077 |
Neg logit contributions | |
Em | -0.083 |
ama | -0.082 |
Gem | -0.080 |
Johnson | -0.077 |
checkout | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
dives | +0.037 |
films | +0.035 |
eway | +0.034 |
igators | +0.034 |
villains | +0.033 |
Neg logit contributions | |
Em | -0.011 |
ama | -0.010 |
Gem | -0.010 |
Johnson | -0.009 |
Wil | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
dives | +0.062 |
eway | +0.057 |
igators | +0.056 |
villains | +0.056 |
tricks | +0.055 |
Neg logit contributions | |
Em | -0.038 |
Johnson | -0.036 |
Gem | -0.036 |
ama | -0.035 |
Wil | -0.032 |
Token | Yes |
Token ID | 5297 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
Em | +0.008 |
Gem | +0.007 |
ama | +0.007 |
Johnson | +0.007 |
checkout | +0.007 |
Neg logit contributions | |
dives | -0.015 |
eway | -0.013 |
films | -0.013 |
tricks | -0.013 |
dances | -0.013 |
Token | ed |
Token ID | 276 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
dives | +0.017 |
eway | +0.015 |
tricks | +0.014 |
films | +0.014 |
mer | +0.014 |
Neg logit contributions | |
Em | -0.021 |
ama | -0.021 |
Gem | -0.021 |
groceries | -0.020 |
Johnson | -0.020 |
Token | up |
Token ID | 510 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Em | +0.003 |
Gem | +0.003 |
ama | +0.003 |
groceries | +0.003 |
Johnson | +0.003 |
Neg logit contributions | |
dives | -0.004 |
eway | -0.004 |
films | -0.004 |
tricks | -0.004 |
mer | -0.004 |
Token | some |
Token ID | 617 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
dives | +0.077 |
eway | +0.071 |
films | +0.068 |
tricks | +0.068 |
mer | +0.067 |
Neg logit contributions | |
Em | -0.040 |
Gem | -0.039 |
ama | -0.038 |
groceries | -0.037 |
Johnson | -0.037 |
Token | of |
Token ID | 286 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
dives | +0.006 |
eway | +0.006 |
films | +0.005 |
tricks | +0.005 |
mer | +0.005 |
Neg logit contributions | |
Em | -0.004 |
ama | -0.004 |
groceries | -0.004 |
Gem | -0.004 |
expensive | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
dives | +0.046 |
eway | +0.043 |
tricks | +0.040 |
films | +0.040 |
mer | +0.040 |
Neg logit contributions | |
Em | -0.023 |
Gem | -0.023 |
groceries | -0.021 |
ama | -0.021 |
checkout | -0.021 |
Token | pe |
Token ID | 613 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
dives | +0.015 |
eway | +0.014 |
films | +0.013 |
tricks | +0.013 |
mer | +0.013 |
Neg logit contributions | |
Em | -0.010 |
ama | -0.010 |
groceries | -0.010 |
Gem | -0.010 |
checkout | -0.010 |
Token | b |
Token ID | 65 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
dives | +0.147 |
films | +0.133 |
eway | +0.133 |
villains | +0.128 |
mer | +0.128 |
Neg logit contributions | |
ama | -0.141 |
Gem | -0.137 |
Em | -0.136 |
groceries | -0.133 |
expensive | -0.131 |
Token | bles |
Token ID | 7689 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
dives | +0.093 |
eway | +0.085 |
tricks | +0.082 |
mer | +0.081 |
films | +0.080 |
Neg logit contributions | |
Em | -0.059 |
ama | -0.057 |
Gem | -0.056 |
Johnson | -0.055 |
checkout | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
dives | +0.011 |
eway | +0.010 |
films | +0.009 |
tricks | +0.009 |
mer | +0.009 |
Neg logit contributions | |
Em | -0.007 |
ama | -0.007 |
Gem | -0.007 |
groceries | -0.007 |
Johnson | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
eway | +0.032 |
dives | +0.031 |
films | +0.030 |
villains | +0.029 |
ag | +0.028 |
Neg logit contributions | |
Em | -0.022 |
Gem | -0.022 |
checkout | -0.021 |
ama | -0.020 |
groceries | -0.020 |
Token | sticks |
Token ID | 16461 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
dives | +0.013 |
eway | +0.012 |
tricks | +0.011 |
films | +0.011 |
mer | +0.011 |
Neg logit contributions | |
Em | -0.009 |
ama | -0.009 |
Gem | -0.009 |
Johnson | -0.008 |
groceries | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
dives | +0.077 |
mer | +0.070 |
RO | +0.068 |
eway | +0.068 |
films | +0.067 |
Neg logit contributions | |
Em | -0.034 |
Johnson | -0.033 |
Gem | -0.032 |
expensive | -0.032 |
first | -0.032 |
Token | phone |
Token ID | 3072 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
dives | +0.034 |
eway | +0.032 |
RO | +0.031 |
mer | +0.031 |
Fly | +0.030 |
Neg logit contributions | |
ama | -0.017 |
groceries | -0.017 |
expensive | -0.017 |
Em | -0.016 |
grandma | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
dives | +0.010 |
eway | +0.009 |
tricks | +0.009 |
films | +0.009 |
mer | +0.009 |
Neg logit contributions | |
Em | -0.006 |
ama | -0.006 |
Gem | -0.006 |
Johnson | -0.006 |
groceries | -0.006 |
Token | threw |
Token ID | 9617 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
eway | +0.022 |
dives | +0.021 |
ile | +0.020 |
ull | +0.020 |
Fly | +0.019 |
Neg logit contributions | |
Em | -0.015 |
grandma | -0.015 |
expensive | -0.014 |
Gem | -0.014 |
already | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
dives | +0.049 |
eway | +0.047 |
films | +0.045 |
villains | +0.045 |
mer | +0.044 |
Neg logit contributions | |
Em | -0.029 |
groceries | -0.028 |
Gem | -0.027 |
expensive | -0.026 |
infected | -0.025 |
Token | pe |
Token ID | 613 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
dives | +0.045 |
eway | +0.041 |
Fly | +0.039 |
films | +0.038 |
dances | +0.038 |
Neg logit contributions | |
Em | -0.029 |
groceries | -0.029 |
expensive | -0.028 |
Gem | -0.027 |
infected | -0.027 |
Token | b |
Token ID | 65 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
dives | +0.156 |
films | +0.148 |
villains | +0.141 |
eway | +0.141 |
Fly | +0.140 |
Neg logit contributions | |
ama | -0.127 |
Gem | -0.122 |
infected | -0.122 |
expensive | -0.120 |
Em | -0.120 |
Token | ble |
Token ID | 903 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
dives | +0.096 |
eway | +0.087 |
films | +0.085 |
tricks | +0.084 |
mer | +0.083 |
Neg logit contributions | |
ama | -0.061 |
Em | -0.060 |
Gem | -0.059 |
groceries | -0.056 |
Johnson | -0.056 |
Token | as |
Token ID | 355 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
dives | +0.052 |
films | +0.048 |
eway | +0.048 |
RO | +0.046 |
villains | +0.046 |
Neg logit contributions | |
Em | -0.037 |
ama | -0.037 |
expensive | -0.036 |
groceries | -0.036 |
Gem | -0.036 |
Token | hard |
Token ID | 1327 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
dives | +0.029 |
eway | +0.026 |
films | +0.025 |
tricks | +0.025 |
mer | +0.025 |
Neg logit contributions | |
Em | -0.015 |
ama | -0.015 |
Gem | -0.015 |
groceries | -0.014 |
Johnson | -0.014 |
Token | as |
Token ID | 355 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
dives | +0.034 |
eway | +0.033 |
films | +0.031 |
igators | +0.030 |
mer | +0.030 |
Neg logit contributions | |
Em | -0.031 |
Gem | -0.030 |
groceries | -0.029 |
ama | -0.029 |
expensive | -0.028 |
Token | He |
Token ID | 679 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
ama | +0.009 |
Johnson | +0.008 |
Em | +0.008 |
grandma | +0.008 |
Gem | +0.008 |
Neg logit contributions | |
dives | -0.018 |
eway | -0.017 |
mer | -0.017 |
films | -0.017 |
ile | -0.016 |
Token | picked |
Token ID | 6497 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
eway | +0.018 |
films | +0.017 |
igators | +0.016 |
stunts | +0.015 |
asm | +0.015 |
Neg logit contributions | |
already | -0.008 |
still | -0.008 |
expensive | -0.007 |
first | -0.007 |
spoiled | -0.007 |
Token | up |
Token ID | 510 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
dives | +0.012 |
eway | +0.012 |
villains | +0.012 |
films | +0.011 |
RO | +0.011 |
Neg logit contributions | |
Em | -0.006 |
Gem | -0.006 |
groceries | -0.006 |
expensive | -0.006 |
ama | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
dives | +0.076 |
mer | +0.068 |
eway | +0.067 |
tricks | +0.067 |
films | +0.067 |
Neg logit contributions | |
ama | -0.052 |
Em | -0.050 |
Gem | -0.049 |
checkout | -0.047 |
Johnson | -0.046 |
Token | round |
Token ID | 2835 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
dives | +0.049 |
eway | +0.044 |
tricks | +0.043 |
mer | +0.043 |
films | +0.043 |
Neg logit contributions | |
Em | -0.030 |
ama | -0.029 |
Gem | -0.029 |
Johnson | -0.028 |
groceries | -0.028 |
Token | pe |
Token ID | 613 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
dives | +0.068 |
films | +0.064 |
eway | +0.064 |
villains | +0.063 |
igators | +0.062 |
Neg logit contributions | |
Em | -0.042 |
ama | -0.042 |
Gem | -0.041 |
checkout | -0.040 |
expensive | -0.040 |
Token | b |
Token ID | 65 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
dives | +0.149 |
films | +0.143 |
eway | +0.137 |
villains | +0.135 |
mer | +0.132 |
Neg logit contributions | |
ama | -0.134 |
Gem | -0.126 |
expensive | -0.125 |
Em | -0.125 |
infected | -0.123 |
Token | ble |
Token ID | 903 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
dives | +0.109 |
eway | +0.100 |
tricks | +0.096 |
films | +0.096 |
mer | +0.096 |
Neg logit contributions | |
Em | -0.057 |
ama | -0.057 |
Gem | -0.055 |
Johnson | -0.052 |
groceries | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
dives | +0.059 |
eway | +0.057 |
films | +0.057 |
villains | +0.056 |
RO | +0.056 |
Neg logit contributions | |
first | -0.026 |
ama | -0.024 |
already | -0.023 |
expensive | -0.023 |
no | -0.021 |
Token | threw |
Token ID | 9617 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
eway | +0.028 |
films | +0.025 |
villains | +0.024 |
aids | +0.024 |
ile | +0.024 |
Neg logit contributions | |
Em | -0.016 |
expensive | -0.015 |
Gem | -0.015 |
already | -0.014 |
tired | -0.014 |
Token | it |
Token ID | 340 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
dives | +0.050 |
eway | +0.049 |
films | +0.049 |
villains | +0.047 |
igators | +0.046 |
Neg logit contributions | |
Em | -0.022 |
Gem | -0.020 |
expensive | -0.019 |
infected | -0.018 |
first | -0.018 |
Token | saw |
Token ID | 2497 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Em | +0.009 |
ama | +0.009 |
Gem | +0.009 |
Johnson | +0.008 |
checkout | +0.008 |
Neg logit contributions | |
dives | -0.012 |
eway | -0.011 |
films | -0.011 |
tricks | -0.011 |
mer | -0.011 |
Token | something |
Token ID | 1223 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
dives | +0.011 |
eway | +0.010 |
tricks | +0.010 |
mer | +0.010 |
films | +0.010 |
Neg logit contributions | |
ama | -0.007 |
Em | -0.007 |
Gem | -0.007 |
checkout | -0.007 |
Johnson | -0.007 |
Token | strange |
Token ID | 6283 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
dives | +0.048 |
eway | +0.045 |
films | +0.044 |
villains | +0.043 |
RO | +0.043 |
Neg logit contributions | |
expensive | -0.018 |
Em | -0.017 |
Gem | -0.016 |
groceries | -0.015 |
ama | -0.015 |
Token | ! |
Token ID | 0 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
dives | +0.083 |
villains | +0.080 |
films | +0.077 |
RO | +0.076 |
Fly | +0.076 |
Neg logit contributions | |
already | -0.020 |
expensive | -0.020 |
first | -0.019 |
yet | -0.018 |
Johnson | -0.016 |
Token | A |
Token ID | 317 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
dives | +0.015 |
films | +0.014 |
eway | +0.013 |
tricks | +0.013 |
villains | +0.013 |
Neg logit contributions | |
ama | -0.016 |
Gem | -0.015 |
Em | -0.014 |
bur | -0.014 |
checkout | -0.014 |
Token | pe |
Token ID | 613 |
Feature activation | +5.90e+00 |
Pos logit contributions | |
dives | +0.022 |
eway | +0.020 |
tricks | +0.019 |
mer | +0.019 |
films | +0.019 |
Neg logit contributions | |
Em | -0.011 |
ama | -0.011 |
Gem | -0.011 |
groceries | -0.010 |
Johnson | -0.010 |
Token | b |
Token ID | 65 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
dives | +0.133 |
eway | +0.117 |
films | +0.112 |
tricks | +0.110 |
mer | +0.110 |
Neg logit contributions | |
ama | -0.154 |
Em | -0.154 |
Gem | -0.151 |
Johnson | -0.146 |
groceries | -0.145 |
Token | ble |
Token ID | 903 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
dives | +0.092 |
eway | +0.089 |
ull | +0.084 |
mer | +0.082 |
tricks | +0.081 |
Neg logit contributions | |
checkout | -0.073 |
groceries | -0.072 |
Em | -0.070 |
expensive | -0.066 |
Gem | -0.066 |
Token | next |
Token ID | 1306 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
films | +0.077 |
dives | +0.077 |
eway | +0.073 |
poses | +0.072 |
villains | +0.071 |
Neg logit contributions | |
already | -0.031 |
ama | -0.031 |
Em | -0.030 |
expensive | -0.030 |
Johnson | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
villains | +0.094 |
bors | +0.091 |
RO | +0.090 |
films | +0.090 |
tunes | +0.089 |
Neg logit contributions | |
first | -0.031 |
ama | -0.027 |
last | -0.024 |
grandma | -0.024 |
Gem | -0.023 |
Token | him |
Token ID | 683 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
ama | +0.012 |
Gem | +0.009 |
hardest | +0.009 |
Johnson | +0.009 |
infected | +0.009 |
Neg logit contributions | |
dives | -0.011 |
films | -0.010 |
tricks | -0.010 |
swim | -0.010 |
mer | -0.010 |
Token | So |
Token ID | 1406 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
dives | +0.028 |
eway | +0.025 |
films | +0.024 |
dances | +0.024 |
mer | +0.023 |
Neg logit contributions | |
ama | -0.018 |
Em | -0.018 |
groceries | -0.017 |
Gem | -0.017 |
infected | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
infected | +0.033 |
groceries | +0.033 |
bur | +0.031 |
severe | +0.031 |
Johnson | +0.031 |
Neg logit contributions | |
dives | -0.034 |
mer | -0.029 |
dances | -0.028 |
jokes | -0.027 |
tricks | -0.027 |
Token | Lily |
Token ID | 20037 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
dives | +0.003 |
mer | +0.003 |
films | +0.003 |
eway | +0.003 |
tricks | +0.003 |
Neg logit contributions | |
ama | -0.003 |
Em | -0.003 |
infected | -0.003 |
Gem | -0.003 |
groceries | -0.003 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Em | +0.014 |
ama | +0.014 |
groceries | +0.014 |
Gem | +0.014 |
Johnson | +0.014 |
Neg logit contributions | |
dives | -0.019 |
mer | -0.016 |
tricks | -0.016 |
eway | -0.016 |
dances | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ama | +0.045 |
Gem | +0.043 |
pricey | +0.043 |
severe | +0.043 |
infected | +0.042 |
Neg logit contributions | |
dives | -0.038 |
films | -0.034 |
mer | -0.033 |
jokes | -0.033 |
tricks | -0.032 |
Token | pe |
Token ID | 613 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
dives | +0.021 |
tricks | +0.020 |
mer | +0.018 |
ull | +0.016 |
hops | +0.016 |
Neg logit contributions | |
Johnson | -0.042 |
severe | -0.042 |
checkout | -0.041 |
infected | -0.041 |
ama | -0.041 |
Token | b |
Token ID | 65 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
dives | +0.127 |
eway | +0.111 |
tricks | +0.105 |
films | +0.104 |
mer | +0.104 |
Neg logit contributions | |
Em | -0.158 |
ama | -0.157 |
Gem | -0.154 |
Johnson | -0.151 |
groceries | -0.150 |
Token | ble |
Token ID | 903 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
dives | +0.096 |
eway | +0.089 |
tricks | +0.087 |
ull | +0.085 |
mer | +0.084 |
Neg logit contributions | |
checkout | -0.070 |
Em | -0.069 |
groceries | -0.067 |
Johnson | -0.066 |
Gem | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
dives | +0.056 |
eway | +0.051 |
tricks | +0.049 |
films | +0.048 |
mer | +0.048 |
Neg logit contributions | |
Em | -0.040 |
ama | -0.040 |
Gem | -0.039 |
groceries | -0.038 |
Johnson | -0.038 |
Token | Jack |
Token ID | 3619 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
pricey | +0.045 |
infected | +0.045 |
ama | +0.045 |
groceries | +0.044 |
expensive | +0.043 |
Neg logit contributions | |
dives | -0.056 |
mer | -0.055 |
jokes | -0.054 |
films | -0.054 |
tricks | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
ama | +0.003 |
Em | +0.003 |
Gem | +0.003 |
Johnson | +0.002 |
groceries | +0.002 |
Neg logit contributions | |
dives | -0.003 |
eway | -0.003 |
tricks | -0.003 |
films | -0.003 |
mer | -0.003 |
Token | lonely |
Token ID | 21757 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Gem | +0.009 |
Em | +0.009 |
ama | +0.008 |
infected | +0.008 |
Wil | +0.008 |
Neg logit contributions | |
dives | -0.010 |
films | -0.010 |
tricks | -0.010 |
tunes | -0.009 |
poses | -0.009 |
Token | clock |
Token ID | 8801 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
dives | +0.007 |
eway | +0.006 |
tricks | +0.006 |
films | +0.006 |
mer | +0.006 |
Neg logit contributions | |
Em | -0.004 |
ama | -0.004 |
Gem | -0.004 |
Johnson | -0.003 |
groceries | -0.003 |
Token | on |
Token ID | 319 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
dives | +0.024 |
eway | +0.022 |
RO | +0.021 |
films | +0.021 |
mer | +0.021 |
Neg logit contributions | |
Em | -0.017 |
ama | -0.017 |
Johnson | -0.016 |
groceries | -0.016 |
Gem | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ama | +0.017 |
Em | +0.016 |
Gem | +0.016 |
infected | +0.015 |
Johnson | +0.015 |
Neg logit contributions | |
dives | -0.018 |
eway | -0.017 |
tricks | -0.016 |
films | -0.016 |
mer | -0.016 |
Token | bed |
Token ID | 3996 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
Em | +0.030 |
Gem | +0.029 |
ama | +0.029 |
infected | +0.028 |
Johnson | +0.027 |
Neg logit contributions | |
dives | -0.045 |
tricks | -0.041 |
films | -0.041 |
dances | -0.039 |
jokes | -0.039 |
Token | side |
Token ID | 1589 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
Em | +0.057 |
ama | +0.057 |
Gem | +0.056 |
Johnson | +0.054 |
groceries | +0.053 |
Neg logit contributions | |
dives | -0.089 |
eway | -0.081 |
tricks | -0.078 |
films | -0.078 |
mer | -0.078 |
Token | table |
Token ID | 3084 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Gem | +0.077 |
ama | +0.076 |
Em | +0.076 |
groceries | +0.074 |
Johnson | +0.073 |
Neg logit contributions | |
dives | -0.178 |
RO | -0.163 |
eway | -0.162 |
Fly | -0.160 |
mer | -0.155 |
Token | and |
Token ID | 290 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
Em | +0.059 |
ama | +0.059 |
Gem | +0.058 |
Johnson | +0.056 |
groceries | +0.056 |
Neg logit contributions | |
dives | -0.095 |
eway | -0.087 |
tricks | -0.083 |
films | -0.083 |
mer | -0.082 |
Token | he |
Token ID | 339 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
Em | +0.007 |
buy | +0.007 |
checkout | +0.007 |
Gem | +0.007 |
grandma | +0.006 |
Neg logit contributions | |
dives | -0.012 |
eway | -0.012 |
films | -0.011 |
ile | -0.011 |
RO | -0.011 |
Token | made |
Token ID | 925 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
ama | +0.019 |
Em | +0.019 |
Gem | +0.018 |
Johnson | +0.018 |
groceries | +0.018 |
Neg logit contributions | |
dives | -0.026 |
eway | -0.024 |
tricks | -0.023 |
mer | -0.023 |
films | -0.022 |
Token | sure |
Token ID | 1654 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Em | +0.005 |
groceries | +0.005 |
grandma | +0.005 |
expensive | +0.005 |
Gem | +0.005 |
Neg logit contributions | |
dives | -0.014 |
igators | -0.013 |
eway | -0.013 |
ile | -0.013 |
RO | -0.013 |
Token | toys |
Token ID | 14958 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Em | +0.003 |
ama | +0.003 |
Gem | +0.003 |
Johnson | +0.003 |
checkout | +0.003 |
Neg logit contributions | |
dives | -0.007 |
eway | -0.007 |
tricks | -0.006 |
films | -0.006 |
mer | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ama | +0.050 |
Em | +0.050 |
Gem | +0.048 |
infected | +0.047 |
checkout | +0.046 |
Neg logit contributions | |
dives | -0.051 |
eway | -0.046 |
mer | -0.044 |
tricks | -0.044 |
films | -0.043 |
Token | clothes |
Token ID | 8242 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Em | +0.007 |
Gem | +0.006 |
groceries | +0.006 |
ama | +0.006 |
checkout | +0.006 |
Neg logit contributions | |
dives | -0.010 |
eway | -0.009 |
films | -0.008 |
tricks | -0.008 |
mer | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ama | +0.060 |
Em | +0.059 |
Gem | +0.057 |
infected | +0.056 |
Johnson | +0.055 |
Neg logit contributions | |
dives | -0.062 |
tricks | -0.055 |
mer | -0.055 |
eway | -0.055 |
films | -0.053 |
Token | their |
Token ID | 511 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ama | +0.036 |
uch | +0.033 |
ongo | +0.033 |
infected | +0.032 |
mm | +0.032 |
Neg logit contributions | |
films | -0.017 |
dives | -0.015 |
tricks | -0.013 |
eway | -0.013 |
mer | -0.013 |
Token | bags |
Token ID | 11668 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
groceries | +0.036 |
ama | +0.036 |
Em | +0.035 |
expensive | +0.035 |
grandma | +0.035 |
Neg logit contributions | |
dives | -0.070 |
eway | -0.068 |
RO | -0.062 |
mer | -0.062 |
ull | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Em | +0.143 |
ama | +0.141 |
infected | +0.141 |
Gem | +0.134 |
mm | +0.131 |
Neg logit contributions | |
dives | -0.103 |
eway | -0.098 |
mer | -0.091 |
tricks | -0.090 |
ag | -0.088 |
Token | They |
Token ID | 1119 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ama | +0.006 |
Em | +0.006 |
infected | +0.006 |
Gem | +0.006 |
groceries | +0.006 |
Neg logit contributions | |
dives | -0.009 |
eway | -0.008 |
films | -0.007 |
dances | -0.007 |
tricks | -0.007 |
Token | got |
Token ID | 1392 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ama | +0.038 |
groceries | +0.035 |
Johnson | +0.035 |
mm | +0.035 |
infected | +0.035 |
Neg logit contributions | |
dives | -0.031 |
mer | -0.027 |
swim | -0.026 |
dances | -0.025 |
RO | -0.025 |
Token | in |
Token ID | 287 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
ama | +0.023 |
Em | +0.023 |
Gem | +0.023 |
Johnson | +0.022 |
checkout | +0.022 |
Neg logit contributions | |
dives | -0.029 |
eway | -0.026 |
films | -0.025 |
tricks | -0.025 |
mer | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ama | +0.016 |
uch | +0.015 |
ongo | +0.014 |
ppa | +0.014 |
mm | +0.014 |
Neg logit contributions | |
dives | -0.008 |
films | -0.008 |
eway | -0.007 |
mer | -0.007 |
dances | -0.007 |
Token | packed |
Token ID | 11856 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ama | +0.048 |
groceries | +0.046 |
ummy | +0.045 |
mm | +0.045 |
Johnson | +0.044 |
Neg logit contributions | |
dives | -0.033 |
swim | -0.030 |
slit | -0.029 |
jokes | -0.028 |
tricks | -0.028 |
Token | many |
Token ID | 867 |
Feature activation | -7.63e-02 |
Pos logit contributions | |
ama | +0.037 |
Em | +0.036 |
Gem | +0.036 |
Johnson | +0.035 |
infected | +0.035 |
Neg logit contributions | |
dives | -0.022 |
eway | -0.018 |
tricks | -0.018 |
films | -0.018 |
mer | -0.017 |
Token | toys |
Token ID | 14958 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ama | +0.002 |
Johnson | +0.002 |
Em | +0.002 |
Gem | +0.002 |
infected | +0.002 |
Neg logit contributions | |
dives | -0.002 |
films | -0.002 |
tricks | -0.002 |
dances | -0.002 |
mer | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ama | +0.039 |
Em | +0.038 |
infected | +0.038 |
Gem | +0.037 |
Johnson | +0.035 |
Neg logit contributions | |
dives | -0.032 |
eway | -0.028 |
tricks | -0.028 |
mer | -0.028 |
films | -0.027 |
Token | their |
Token ID | 511 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ongo | +0.040 |
uch | +0.040 |
ama | +0.040 |
mm | +0.037 |
ivery | +0.036 |
Neg logit contributions | |
films | -0.014 |
their | -0.012 |
games | -0.009 |
harmony | -0.009 |
dives | -0.009 |
Token | bags |
Token ID | 11668 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
Em | +0.042 |
ama | +0.042 |
Gem | +0.041 |
infected | +0.040 |
Johnson | +0.039 |
Neg logit contributions | |
dives | -0.064 |
films | -0.058 |
tricks | -0.056 |
dances | -0.055 |
mer | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
infected | +0.159 |
Em | +0.156 |
ama | +0.149 |
Gem | +0.143 |
severe | +0.143 |
Neg logit contributions | |
dives | -0.077 |
eway | -0.074 |
films | -0.066 |
ag | -0.065 |
mer | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
infected | +0.011 |
ama | +0.011 |
severe | +0.011 |
pling | +0.010 |
lowest | +0.010 |
Neg logit contributions | |
dives | -0.009 |
films | -0.009 |
dances | -0.008 |
Fly | -0.007 |
eway | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
dives | +0.010 |
eway | +0.009 |
films | +0.009 |
tricks | +0.008 |
Fly | +0.008 |
Neg logit contributions | |
groceries | -0.008 |
Em | -0.008 |
Gem | -0.008 |
checkout | -0.008 |
ama | -0.008 |
Token | Mom |
Token ID | 29252 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
ama | +0.017 |
Em | +0.017 |
Gem | +0.017 |
groceries | +0.017 |
Johnson | +0.017 |
Neg logit contributions | |
dives | -0.020 |
eway | -0.018 |
films | -0.018 |
mer | -0.018 |
RO | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Em | +0.021 |
Gem | +0.021 |
ama | +0.021 |
groceries | +0.020 |
infected | +0.020 |
Neg logit contributions | |
dives | -0.024 |
mer | -0.020 |
eway | -0.020 |
films | -0.020 |
tricks | -0.020 |
Token | v |
Token ID | 410 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
dives | +0.010 |
eway | +0.010 |
films | +0.009 |
tricks | +0.009 |
RO | +0.009 |
Neg logit contributions | |
Em | -0.005 |
ama | -0.005 |
Gem | -0.005 |
checkout | -0.005 |
groceries | -0.004 |
Token | ase |
Token ID | 589 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
dives | +0.005 |
eway | +0.004 |
films | +0.004 |
tricks | +0.004 |
mer | +0.004 |
Neg logit contributions | |
ama | -0.007 |
Em | -0.007 |
Gem | -0.007 |
Johnson | -0.007 |
checkout | -0.007 |
Token | on |
Token ID | 319 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
Em | +0.019 |
ama | +0.019 |
Gem | +0.019 |
Johnson | +0.018 |
groceries | +0.018 |
Neg logit contributions | |
dives | -0.028 |
eway | -0.026 |
tricks | -0.024 |
films | -0.024 |
mer | -0.024 |
Token | her |
Token ID | 607 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ama | +0.015 |
infected | +0.013 |
ongo | +0.013 |
groceries | +0.013 |
Gem | +0.013 |
Neg logit contributions | |
dives | -0.014 |
eway | -0.013 |
films | -0.013 |
tricks | -0.013 |
mer | -0.013 |
Token | bed |
Token ID | 3996 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
Em | +0.020 |
ama | +0.019 |
Gem | +0.019 |
Johnson | +0.018 |
infected | +0.018 |
Neg logit contributions | |
dives | -0.032 |
tricks | -0.029 |
eway | -0.029 |
films | -0.028 |
mer | -0.028 |
Token | side |
Token ID | 1589 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
Em | +0.060 |
ama | +0.060 |
Gem | +0.058 |
groceries | +0.057 |
Johnson | +0.056 |
Neg logit contributions | |
dives | -0.085 |
eway | -0.078 |
tricks | -0.075 |
mer | -0.075 |
films | -0.074 |
Token | table |
Token ID | 3084 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
Gem | +0.075 |
ama | +0.073 |
Em | +0.072 |
groceries | +0.071 |
checkout | +0.070 |
Neg logit contributions | |
dives | -0.172 |
RO | -0.158 |
eway | -0.156 |
Fly | -0.155 |
films | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
Em | +0.057 |
ama | +0.056 |
Gem | +0.055 |
Johnson | +0.053 |
groceries | +0.053 |
Neg logit contributions | |
dives | -0.094 |
eway | -0.085 |
films | -0.082 |
tricks | -0.082 |
mer | -0.081 |
Token | She |
Token ID | 1375 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
dives | +0.007 |
eway | +0.006 |
Fly | +0.006 |
dances | +0.006 |
films | +0.006 |
Neg logit contributions | |
ama | -0.005 |
groceries | -0.005 |
infected | -0.005 |
severe | -0.004 |
expensive | -0.004 |
Token | remembered |
Token ID | 12086 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ama | +0.004 |
Em | +0.004 |
Gem | +0.004 |
groceries | +0.004 |
Johnson | +0.004 |
Neg logit contributions | |
dives | -0.006 |
eway | -0.005 |
mer | -0.005 |
tricks | -0.005 |
dances | -0.005 |
Token | why |
Token ID | 1521 |
Feature activation | +8.48e-02 |
Pos logit contributions | |
ama | +0.004 |
Em | +0.004 |
Gem | +0.004 |
Johnson | +0.004 |
checkout | +0.004 |
Neg logit contributions | |
dives | -0.005 |
eway | -0.005 |
mer | -0.005 |
tricks | -0.005 |
films | -0.004 |
Token | clothes |
Token ID | 8242 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
ama | +0.014 |
Johnson | +0.013 |
Em | +0.012 |
mm | +0.012 |
Gem | +0.012 |
Neg logit contributions | |
dives | -0.017 |
films | -0.015 |
tricks | -0.015 |
mer | -0.014 |
dances | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
infected | +0.081 |
ama | +0.080 |
Em | +0.080 |
mm | +0.076 |
Phill | +0.075 |
Neg logit contributions | |
dives | -0.048 |
mer | -0.045 |
fish | -0.040 |
eway | -0.039 |
swim | -0.039 |
Token | toys |
Token ID | 14958 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
dives | +0.012 |
eway | +0.011 |
tricks | +0.011 |
films | +0.011 |
mer | +0.011 |
Neg logit contributions | |
ama | -0.009 |
Em | -0.009 |
Gem | -0.009 |
Johnson | -0.008 |
groceries | -0.008 |
Token | into |
Token ID | 656 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ama | +0.052 |
Em | +0.050 |
Gem | +0.048 |
infected | +0.048 |
Johnson | +0.047 |
Neg logit contributions | |
dives | -0.054 |
eway | -0.048 |
tricks | -0.047 |
mer | -0.047 |
films | -0.045 |
Token | big |
Token ID | 1263 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
ama | +0.002 |
Johnson | +0.002 |
Em | +0.002 |
Gem | +0.002 |
mm | +0.002 |
Neg logit contributions | |
dives | -0.003 |
films | -0.002 |
tricks | -0.002 |
eway | -0.002 |
mer | -0.002 |
Token | bags |
Token ID | 11668 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
ama | +0.015 |
Em | +0.014 |
Gem | +0.014 |
Johnson | +0.014 |
checkout | +0.014 |
Neg logit contributions | |
dives | -0.023 |
films | -0.021 |
tricks | -0.020 |
dances | -0.020 |
mer | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
Em | +0.130 |
ama | +0.130 |
infected | +0.129 |
mm | +0.124 |
Gem | +0.121 |
Neg logit contributions | |
dives | -0.104 |
eway | -0.098 |
mer | -0.093 |
tricks | -0.088 |
films | -0.086 |
Token | |
Token ID | 220 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
dives | +0.014 |
eway | +0.013 |
films | +0.012 |
Fly | +0.012 |
dances | +0.012 |
Neg logit contributions | |
ama | -0.010 |
Em | -0.010 |
Gem | -0.010 |
groceries | -0.010 |
infected | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
checkout | +0.042 |
Em | +0.041 |
Gem | +0.040 |
groceries | +0.040 |
ama | +0.040 |
Neg logit contributions | |
dives | -0.054 |
eway | -0.052 |
films | -0.048 |
Fly | -0.047 |
tricks | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
dives | +0.009 |
eway | +0.009 |
films | +0.008 |
tricks | +0.008 |
mer | +0.008 |
Neg logit contributions | |
ama | -0.006 |
Em | -0.006 |
Gem | -0.006 |
groceries | -0.006 |
checkout | -0.006 |
Token | When |
Token ID | 2215 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
Em | +0.007 |
ama | +0.006 |
Gem | +0.006 |
Johnson | +0.006 |
groceries | +0.006 |
Neg logit contributions | |
dives | -0.010 |
eway | -0.009 |
tricks | -0.009 |
films | -0.009 |
mer | -0.009 |
Token | throwing |
Token ID | 9644 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
dives | +0.011 |
eway | +0.011 |
RO | +0.010 |
Fly | +0.010 |
films | +0.010 |
Neg logit contributions | |
checkout | -0.008 |
Johnson | -0.007 |
Gem | -0.007 |
Em | -0.007 |
groceries | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
dives | +0.039 |
eway | +0.038 |
mer | +0.036 |
villains | +0.036 |
RO | +0.035 |
Neg logit contributions | |
groceries | -0.022 |
expensive | -0.020 |
Em | -0.020 |
Gem | -0.019 |
Johnson | -0.019 |
Token | corn |
Token ID | 11676 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
dives | +0.021 |
eway | +0.019 |
tricks | +0.018 |
films | +0.018 |
mer | +0.018 |
Neg logit contributions | |
Em | -0.018 |
ama | -0.018 |
Gem | -0.018 |
Johnson | -0.017 |
groceries | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
dives | +0.019 |
eway | +0.018 |
RO | +0.018 |
films | +0.017 |
villains | +0.017 |
Neg logit contributions | |
groceries | -0.012 |
ama | -0.011 |
Johnson | -0.011 |
first | -0.011 |
Gem | -0.011 |
Token | their |
Token ID | 511 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ama | +0.041 |
Em | +0.037 |
ongo | +0.037 |
ilda | +0.036 |
infected | +0.036 |
Neg logit contributions | |
dives | -0.034 |
eway | -0.031 |
mer | -0.030 |
films | -0.029 |
tricks | -0.029 |
Token | baskets |
Token ID | 46530 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
groceries | +0.025 |
expensive | +0.023 |
grandma | +0.022 |
checkout | +0.022 |
ama | +0.021 |
Neg logit contributions | |
eway | -0.061 |
RO | -0.057 |
dives | -0.056 |
Fly | -0.055 |
ull | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Em | +0.126 |
ama | +0.125 |
Gem | +0.120 |
infected | +0.118 |
Johnson | +0.114 |
Neg logit contributions | |
dives | -0.116 |
eway | -0.103 |
mer | -0.101 |
tricks | -0.100 |
films | -0.095 |
Token |
|
Token ID | 198 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
Em | +0.003 |
ama | +0.003 |
Gem | +0.003 |
groceries | +0.003 |
checkout | +0.003 |
Neg logit contributions | |
dives | -0.003 |
eway | -0.002 |
films | -0.002 |
tricks | -0.002 |
Fly | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
dives | +0.010 |
eway | +0.009 |
tricks | +0.008 |
ull | +0.008 |
Fly | +0.008 |
Neg logit contributions | |
Em | -0.008 |
groceries | -0.008 |
Gem | -0.008 |
checkout | -0.008 |
ama | -0.008 |
Token | Soon |
Token ID | 28093 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Em | +0.004 |
Gem | +0.004 |
ama | +0.004 |
groceries | +0.004 |
Johnson | +0.004 |
Neg logit contributions | |
dives | -0.006 |
eway | -0.005 |
tricks | -0.005 |
films | -0.005 |
mer | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
dives | +0.039 |
eway | +0.036 |
tricks | +0.034 |
films | +0.034 |
mer | +0.034 |
Neg logit contributions | |
Em | -0.019 |
ama | -0.018 |
Gem | -0.018 |
Johnson | -0.017 |
groceries | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Em | +0.019 |
ama | +0.019 |
Gem | +0.018 |
Johnson | +0.017 |
groceries | +0.017 |
Neg logit contributions | |
dives | -0.033 |
eway | -0.030 |
tricks | -0.029 |
films | -0.029 |
mer | -0.029 |
Token | which |
Token ID | 543 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
expensive | +0.002 |
groceries | +0.002 |
Em | +0.002 |
Gem | +0.002 |
Johnson | +0.002 |
Neg logit contributions | |
dives | -0.004 |
eway | -0.003 |
RO | -0.003 |
tricks | -0.003 |
dances | -0.003 |
Token | are |
Token ID | 389 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ama | +0.018 |
Em | +0.017 |
expensive | +0.017 |
Gem | +0.017 |
Johnson | +0.017 |
Neg logit contributions | |
dives | -0.031 |
eway | -0.029 |
mer | -0.027 |
films | -0.027 |
tricks | -0.027 |
Token | like |
Token ID | 588 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
Em | +0.022 |
ama | +0.022 |
Gem | +0.021 |
groceries | +0.020 |
Johnson | +0.020 |
Neg logit contributions | |
dives | -0.048 |
eway | -0.045 |
films | -0.043 |
tricks | -0.043 |
mer | -0.042 |
Token | big |
Token ID | 1263 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
dives | +0.016 |
eway | +0.016 |
RO | +0.014 |
dances | +0.014 |
ag | +0.014 |
Neg logit contributions | |
expensive | -0.008 |
Em | -0.008 |
groceries | -0.008 |
Gem | -0.008 |
ama | -0.007 |
Token | bags |
Token ID | 11668 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
eway | +0.019 |
dives | +0.018 |
RO | +0.016 |
Fly | +0.016 |
ag | +0.016 |
Neg logit contributions | |
groceries | -0.011 |
expensive | -0.010 |
Em | -0.010 |
Johnson | -0.010 |
Gem | -0.010 |
Token | inside |
Token ID | 2641 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Em | +0.111 |
ama | +0.110 |
Gem | +0.106 |
checkout | +0.102 |
infected | +0.102 |
Neg logit contributions | |
dives | -0.134 |
eway | -0.119 |
tricks | -0.118 |
mer | -0.115 |
films | -0.115 |
Token | us |
Token ID | 514 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
Em | +0.036 |
ama | +0.035 |
Gem | +0.034 |
checkout | +0.033 |
Johnson | +0.033 |
Neg logit contributions | |
dives | -0.047 |
eway | -0.043 |
films | -0.041 |
tricks | -0.041 |
mer | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Em | +0.002 |
ama | +0.002 |
Gem | +0.002 |
checkout | +0.002 |
groceries | +0.001 |
Neg logit contributions | |
dives | -0.002 |
eway | -0.002 |
tricks | -0.002 |
films | -0.002 |
mer | -0.002 |
Token | We |
Token ID | 775 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
dives | +0.007 |
eway | +0.006 |
films | +0.006 |
Fly | +0.006 |
mer | +0.006 |
Neg logit contributions | |
ama | -0.006 |
Em | -0.006 |
Gem | -0.006 |
groceries | -0.006 |
checkout | -0.006 |
Token | breathe |
Token ID | 18044 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
dives | +0.003 |
eway | +0.003 |
tricks | +0.003 |
mer | +0.003 |
films | +0.003 |
Neg logit contributions | |
ama | -0.002 |
Em | -0.002 |
Gem | -0.002 |
Johnson | -0.002 |
groceries | -0.002 |
Token | put |
Token ID | 1234 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
ama | +0.022 |
Johnson | +0.021 |
groceries | +0.020 |
Em | +0.020 |
infected | +0.020 |
Neg logit contributions | |
dives | -0.025 |
mer | -0.022 |
dances | -0.021 |
swim | -0.021 |
films | -0.021 |
Token | their |
Token ID | 511 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
dives | +0.017 |
eway | +0.016 |
tricks | +0.015 |
mer | +0.015 |
films | +0.015 |
Neg logit contributions | |
Em | -0.013 |
ama | -0.012 |
Gem | -0.012 |
groceries | -0.012 |
Johnson | -0.012 |
Token | things |
Token ID | 1243 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
groceries | +0.001 |
ama | +0.001 |
Em | +0.001 |
expensive | +0.001 |
Gem | +0.001 |
Neg logit contributions | |
dives | -0.002 |
eway | -0.001 |
mer | -0.001 |
RO | -0.001 |
Fly | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ama | +0.026 |
Em | +0.025 |
Gem | +0.025 |
Johnson | +0.024 |
infected | +0.024 |
Neg logit contributions | |
dives | -0.019 |
eway | -0.016 |
mer | -0.016 |
tricks | -0.016 |
films | -0.015 |
Token | their |
Token ID | 511 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ama | +0.037 |
uch | +0.036 |
ongo | +0.034 |
mm | +0.034 |
ivery | +0.032 |
Neg logit contributions | |
films | -0.017 |
mer | -0.017 |
dives | -0.015 |
triangles | -0.015 |
eway | -0.015 |
Token | bags |
Token ID | 11668 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
groceries | +0.025 |
checkout | +0.023 |
grandma | +0.023 |
ama | +0.023 |
expensive | +0.023 |
Neg logit contributions | |
dives | -0.053 |
eway | -0.052 |
ull | -0.049 |
RO | -0.049 |
mer | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Em | +0.160 |
infected | +0.157 |
ama | +0.152 |
innie | +0.150 |
mm | +0.148 |
Neg logit contributions | |
dives | -0.068 |
eway | -0.061 |
ks | -0.060 |
ag | -0.059 |
mer | -0.057 |
Token | zip |
Token ID | 19974 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Em | +0.003 |
Gem | +0.003 |
checkout | +0.003 |
groceries | +0.003 |
ama | +0.003 |
Neg logit contributions | |
dives | -0.004 |
eway | -0.004 |
films | -0.004 |
tricks | -0.004 |
mer | -0.004 |
Token | them |
Token ID | 606 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
Em | +0.003 |
Gem | +0.003 |
ama | +0.003 |
groceries | +0.003 |
checkout | +0.003 |
Neg logit contributions | |
dives | -0.004 |
eway | -0.003 |
mer | -0.003 |
films | -0.003 |
tricks | -0.003 |
Token | up |
Token ID | 510 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
dives | +0.009 |
eway | +0.008 |
films | +0.007 |
mer | +0.007 |
RO | +0.007 |
Neg logit contributions | |
Em | -0.009 |
ama | -0.009 |
Gem | -0.009 |
groceries | -0.009 |
Johnson | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
dives | +0.037 |
eway | +0.034 |
tricks | +0.032 |
mer | +0.032 |
films | +0.032 |
Neg logit contributions | |
ama | -0.028 |
Em | -0.028 |
Gem | -0.027 |
Johnson | -0.026 |
groceries | -0.026 |
Token | s |
Token ID | 82 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Em | +0.009 |
ama | +0.009 |
Gem | +0.008 |
groceries | +0.008 |
Johnson | +0.008 |
Neg logit contributions | |
dives | -0.010 |
eway | -0.009 |
tricks | -0.009 |
films | -0.009 |
mer | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Em | +0.030 |
ama | +0.030 |
Gem | +0.029 |
groceries | +0.029 |
Johnson | +0.028 |
Neg logit contributions | |
dives | -0.034 |
eway | -0.031 |
films | -0.029 |
tricks | -0.029 |
mer | -0.029 |
Token | paper |
Token ID | 3348 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
eway | +0.007 |
dives | +0.006 |
ull | +0.006 |
RO | +0.006 |
ile | +0.006 |
Neg logit contributions | |
Em | -0.004 |
grandma | -0.004 |
groceries | -0.004 |
expensive | -0.004 |
Gem | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
dives | +0.002 |
eway | +0.002 |
RO | +0.002 |
villains | +0.002 |
Fly | +0.001 |
Neg logit contributions | |
groceries | -0.001 |
grandma | -0.001 |
ama | -0.001 |
first | -0.001 |
Em | -0.001 |
Token | their |
Token ID | 511 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ama | +0.006 |
Em | +0.006 |
Gem | +0.006 |
Johnson | +0.006 |
infected | +0.006 |
Neg logit contributions | |
dives | -0.004 |
films | -0.004 |
eway | -0.004 |
mer | -0.004 |
tricks | -0.004 |
Token | bags |
Token ID | 11668 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
grandma | +0.023 |
expensive | +0.022 |
groceries | +0.021 |
checkout | +0.020 |
mom | +0.020 |
Neg logit contributions | |
eway | -0.048 |
ull | -0.045 |
dives | -0.045 |
RO | -0.045 |
Fly | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Em | +0.138 |
ama | +0.136 |
Gem | +0.131 |
infected | +0.131 |
Johnson | +0.128 |
Neg logit contributions | |
dives | -0.100 |
eway | -0.087 |
mer | -0.085 |
tricks | -0.084 |
ks | -0.083 |
Token | They |
Token ID | 1119 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Em | +0.006 |
ama | +0.006 |
Gem | +0.006 |
Johnson | +0.006 |
groceries | +0.006 |
Neg logit contributions | |
dives | -0.007 |
eway | -0.006 |
tricks | -0.006 |
mer | -0.006 |
films | -0.006 |
Token | go |
Token ID | 467 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ama | +0.023 |
Em | +0.022 |
Gem | +0.022 |
Johnson | +0.021 |
groceries | +0.021 |
Neg logit contributions | |
dives | -0.032 |
tricks | -0.028 |
eway | -0.028 |
mer | -0.028 |
films | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
dives | +0.028 |
eway | +0.025 |
tricks | +0.024 |
mer | +0.024 |
films | +0.024 |
Neg logit contributions | |
ama | -0.025 |
Em | -0.025 |
Gem | -0.024 |
Johnson | -0.023 |
groceries | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
Em | +0.017 |
ama | +0.016 |
Gem | +0.016 |
groceries | +0.016 |
Johnson | +0.016 |
Neg logit contributions | |
dives | -0.022 |
eway | -0.020 |
tricks | -0.019 |
films | -0.019 |
mer | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ama | +0.050 |
Em | +0.049 |
Gem | +0.048 |
Johnson | +0.047 |
checkout | +0.046 |
Neg logit contributions | |
dives | -0.060 |
eway | -0.054 |
tricks | -0.052 |
films | -0.051 |
mer | -0.051 |
Token | last |
Token ID | 938 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
dives | +0.038 |
tricks | +0.034 |
eway | +0.032 |
mer | +0.032 |
dances | +0.031 |
Neg logit contributions | |
ama | -0.035 |
Em | -0.034 |
Johnson | -0.034 |
Gem | -0.033 |
infected | -0.032 |
Token | things |
Token ID | 1243 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
dives | +0.043 |
eway | +0.041 |
RO | +0.039 |
Fly | +0.039 |
films | +0.039 |
Neg logit contributions | |
groceries | -0.027 |
expensive | -0.026 |
Em | -0.026 |
Gem | -0.026 |
ama | -0.025 |
Token | into |
Token ID | 656 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
ama | +0.020 |
Em | +0.019 |
infected | +0.019 |
Gem | +0.018 |
Johnson | +0.018 |
Neg logit contributions | |
dives | -0.018 |
tricks | -0.015 |
eway | -0.015 |
mer | -0.014 |
swim | -0.014 |
Token | their |
Token ID | 511 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ama | +0.001 |
mm | +0.001 |
ongo | +0.001 |
Johnson | +0.001 |
uch | +0.001 |
Neg logit contributions | |
dives | -0.001 |
films | -0.001 |
eway | -0.001 |
tricks | -0.001 |
mer | -0.001 |
Token | bags |
Token ID | 11668 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
Em | +0.028 |
ama | +0.028 |
Gem | +0.027 |
Johnson | +0.026 |
checkout | +0.026 |
Neg logit contributions | |
dives | -0.050 |
eway | -0.045 |
tricks | -0.044 |
films | -0.044 |
mer | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Em | +0.139 |
infected | +0.137 |
ama | +0.133 |
mm | +0.132 |
innie | +0.128 |
Neg logit contributions | |
dives | -0.088 |
eway | -0.082 |
mer | -0.075 |
swim | -0.071 |
tricks | -0.071 |
Token | they |
Token ID | 484 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
dives | +0.013 |
eway | +0.012 |
films | +0.011 |
tricks | +0.011 |
mer | +0.011 |
Neg logit contributions | |
Em | -0.008 |
ama | -0.008 |
Gem | -0.008 |
groceries | -0.008 |
checkout | -0.008 |
Token | stepped |
Token ID | 10764 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
ama | +0.025 |
groceries | +0.023 |
Johnson | +0.023 |
Em | +0.023 |
mm | +0.023 |
Neg logit contributions | |
dives | -0.026 |
mer | -0.024 |
eway | -0.023 |
swim | -0.022 |
tricks | -0.022 |
Token | outside |
Token ID | 2354 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
dives | +0.013 |
eway | +0.011 |
mer | +0.011 |
films | +0.011 |
tricks | +0.011 |
Neg logit contributions | |
ama | -0.013 |
Em | -0.013 |
Gem | -0.013 |
Johnson | -0.013 |
groceries | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | +8.75e-03 |
Pos logit contributions | |
dives | +0.026 |
eway | +0.024 |
tricks | +0.023 |
films | +0.022 |
mer | +0.022 |
Neg logit contributions | |
Em | -0.016 |
ama | -0.016 |
Gem | -0.016 |
Johnson | -0.015 |
groceries | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
ama | +0.009 |
Johnson | +0.009 |
Gem | +0.009 |
groceries | +0.009 |
Em | +0.009 |
Neg logit contributions | |
dives | -0.017 |
eway | -0.016 |
RO | -0.015 |
dances | -0.015 |
tricks | -0.015 |
Token | stuff |
Token ID | 3404 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
eway | +0.030 |
dives | +0.028 |
ull | +0.027 |
tricks | +0.027 |
ile | +0.027 |
Neg logit contributions | |
groceries | -0.018 |
checkout | -0.018 |
Em | -0.018 |
Gem | -0.017 |
ama | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
Em | +0.036 |
ama | +0.035 |
Gem | +0.035 |
groceries | +0.034 |
Johnson | +0.034 |
Neg logit contributions | |
dives | -0.041 |
eway | -0.037 |
tricks | -0.035 |
films | -0.035 |
mer | -0.035 |
Token | in |
Token ID | 287 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Em | +0.004 |
ama | +0.004 |
infected | +0.004 |
Gem | +0.004 |
groceries | +0.004 |
Neg logit contributions | |
dives | -0.006 |
eway | -0.005 |
films | -0.005 |
mer | -0.005 |
villains | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
ama | +0.031 |
Em | +0.030 |
groceries | +0.029 |
Gem | +0.029 |
checkout | +0.029 |
Neg logit contributions | |
dives | -0.029 |
eway | -0.027 |
films | -0.025 |
mer | -0.025 |
Fly | -0.024 |
Token | bags |
Token ID | 11668 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
Em | +0.013 |
ama | +0.013 |
Gem | +0.013 |
Johnson | +0.012 |
groceries | +0.012 |
Neg logit contributions | |
dives | -0.015 |
eway | -0.013 |
tricks | -0.013 |
films | -0.013 |
mer | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Em | +0.124 |
ama | +0.120 |
infected | +0.118 |
Gem | +0.114 |
Johnson | +0.113 |
Neg logit contributions | |
dives | -0.114 |
eway | -0.106 |
mer | -0.098 |
ull | -0.096 |
tricks | -0.094 |
Token | Molly |
Token ID | 30236 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
Em | +0.007 |
ama | +0.006 |
Gem | +0.006 |
Johnson | +0.006 |
checkout | +0.006 |
Neg logit contributions | |
dives | -0.008 |
eway | -0.007 |
tricks | -0.007 |
mer | -0.007 |
films | -0.007 |
Token | helps |
Token ID | 5419 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ama | +0.011 |
Em | +0.011 |
Gem | +0.010 |
checkout | +0.010 |
groceries | +0.010 |
Neg logit contributions | |
dives | -0.012 |
eway | -0.012 |
mer | -0.011 |
tricks | -0.011 |
films | -0.011 |
Token | too |
Token ID | 1165 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
Em | +0.033 |
ama | +0.033 |
Gem | +0.032 |
Johnson | +0.031 |
groceries | +0.031 |
Neg logit contributions | |
dives | -0.045 |
eway | -0.041 |
films | -0.040 |
tricks | -0.039 |
mer | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Em | +0.001 |
checkout | +0.001 |
Gem | +0.001 |
bur | +0.001 |
mm | +0.001 |
Neg logit contributions | |
dives | -0.001 |
tricks | -0.001 |
ks | -0.001 |
eway | -0.001 |
warriors | -0.001 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Em | +0.019 |
ama | +0.019 |
Gem | +0.018 |
Johnson | +0.018 |
groceries | +0.018 |
Neg logit contributions | |
dives | -0.028 |
eway | -0.025 |
tricks | -0.024 |
films | -0.024 |
mer | -0.024 |
Token | Sammy |
Token ID | 44067 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
dives | +0.007 |
eway | +0.007 |
films | +0.007 |
tricks | +0.006 |
dances | +0.006 |
Neg logit contributions | |
Em | -0.004 |
ama | -0.004 |
Gem | -0.004 |
groceries | -0.003 |
infected | -0.003 |
Token | leaving |
Token ID | 4305 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Em | +0.010 |
ama | +0.010 |
Johnson | +0.010 |
Gem | +0.010 |
infected | +0.009 |
Neg logit contributions | |
dives | -0.017 |
eway | -0.016 |
films | -0.015 |
RO | -0.015 |
tricks | -0.015 |
Token | with |
Token ID | 351 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
Em | +0.034 |
Gem | +0.033 |
groceries | +0.032 |
ama | +0.032 |
Johnson | +0.032 |
Neg logit contributions | |
dives | -0.052 |
eway | -0.047 |
films | -0.045 |
RO | -0.044 |
dances | -0.044 |
Token | his |
Token ID | 465 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
dives | +0.016 |
eway | +0.015 |
films | +0.014 |
tricks | +0.014 |
mer | +0.014 |
Neg logit contributions | |
Em | -0.009 |
ama | -0.009 |
Gem | -0.009 |
groceries | -0.009 |
Johnson | -0.009 |
Token | bags |
Token ID | 11668 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
Em | +0.010 |
ama | +0.010 |
Gem | +0.010 |
checkout | +0.010 |
Johnson | +0.009 |
Neg logit contributions | |
dives | -0.017 |
eway | -0.015 |
tricks | -0.015 |
mer | -0.015 |
films | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Em | +0.127 |
ama | +0.123 |
mm | +0.119 |
Gem | +0.119 |
checkout | +0.111 |
Neg logit contributions | |
dives | -0.107 |
eway | -0.100 |
mer | -0.095 |
ag | -0.095 |
tricks | -0.092 |
Token | Benny |
Token ID | 44275 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
dives | +0.007 |
eway | +0.006 |
tricks | +0.006 |
films | +0.006 |
mer | +0.006 |
Neg logit contributions | |
Em | -0.005 |
ama | -0.005 |
Gem | -0.005 |
Johnson | -0.005 |
groceries | -0.005 |
Token | felt |
Token ID | 2936 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
Em | +0.009 |
ama | +0.009 |
Gem | +0.008 |
Johnson | +0.008 |
groceries | +0.008 |
Neg logit contributions | |
dives | -0.014 |
eway | -0.012 |
tricks | -0.012 |
films | -0.012 |
mer | -0.012 |
Token | en |
Token ID | 551 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
dives | +0.013 |
eway | +0.012 |
tricks | +0.012 |
mer | +0.011 |
films | +0.011 |
Neg logit contributions | |
ama | -0.007 |
Em | -0.006 |
Gem | -0.006 |
Johnson | -0.006 |
groceries | -0.006 |
Token | vious |
Token ID | 1442 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Em | +0.056 |
ama | +0.055 |
Gem | +0.054 |
groceries | +0.052 |
checkout | +0.052 |
Neg logit contributions | |
dives | -0.054 |
eway | -0.049 |
films | -0.045 |
tricks | -0.045 |
mer | -0.045 |
Token | they |
Token ID | 484 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ama | +0.001 |
Em | +0.001 |
Gem | +0.001 |
Johnson | +0.001 |
checkout | +0.001 |
Neg logit contributions | |
dives | -0.001 |
eway | -0.001 |
films | -0.001 |
tricks | -0.001 |
mer | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
ama | +0.040 |
Johnson | +0.035 |
Gem | +0.035 |
Em | +0.035 |
groceries | +0.034 |
Neg logit contributions | |
dives | -0.037 |
mer | -0.032 |
dances | -0.031 |
tricks | -0.031 |
swim | -0.031 |
Token | unp |
Token ID | 8593 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ama | +0.042 |
Em | +0.041 |
Gem | +0.039 |
Johnson | +0.038 |
checkout | +0.037 |
Neg logit contributions | |
dives | -0.064 |
eway | -0.057 |
tricks | -0.056 |
mer | -0.056 |
films | -0.055 |
Token | acked |
Token ID | 6021 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Em | +0.078 |
ama | +0.078 |
Gem | +0.077 |
Johnson | +0.075 |
groceries | +0.075 |
Neg logit contributions | |
dives | -0.026 |
eway | -0.021 |
films | -0.018 |
tricks | -0.018 |
mer | -0.017 |
Token | their |
Token ID | 511 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
Em | +0.006 |
Gem | +0.006 |
ama | +0.006 |
groceries | +0.006 |
checkout | +0.006 |
Neg logit contributions | |
dives | -0.008 |
eway | -0.007 |
tricks | -0.007 |
films | -0.007 |
mer | -0.007 |
Token | bags |
Token ID | 11668 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
ama | +0.015 |
Em | +0.014 |
Gem | +0.014 |
Johnson | +0.013 |
infected | +0.013 |
Neg logit contributions | |
dives | -0.022 |
tricks | -0.019 |
films | -0.019 |
eway | -0.019 |
mer | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
Em | +0.136 |
ama | +0.134 |
infected | +0.132 |
mm | +0.127 |
Gem | +0.125 |
Neg logit contributions | |
dives | -0.092 |
eway | -0.088 |
mer | -0.080 |
tricks | -0.077 |
ag | -0.075 |
Token | Tom |
Token ID | 4186 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
ama | +0.001 |
infected | +0.001 |
Em | +0.001 |
groceries | +0.001 |
Gem | +0.001 |
Neg logit contributions | |
dives | -0.001 |
eway | -0.001 |
films | -0.001 |
Fly | -0.001 |
dances | -0.001 |
Token | put |
Token ID | 1234 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
groceries | +0.019 |
ama | +0.019 |
Em | +0.019 |
Gem | +0.019 |
infected | +0.018 |
Neg logit contributions | |
dives | -0.022 |
mer | -0.018 |
tricks | -0.018 |
dances | -0.018 |
hops | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
dives | +0.006 |
eway | +0.006 |
tricks | +0.006 |
films | +0.006 |
mer | +0.006 |
Neg logit contributions | |
ama | -0.006 |
Em | -0.006 |
Gem | -0.005 |
Johnson | -0.005 |
checkout | -0.005 |
Token | card |
Token ID | 2657 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
dives | +0.001 |
tricks | +0.001 |
mer | +0.001 |
films | +0.001 |
jokes | +0.001 |
Neg logit contributions | |
ama | -0.001 |
Gem | -0.000 |
Em | -0.000 |
mm | -0.000 |
Johnson | -0.000 |
Token | again |
Token ID | 757 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
RO | +0.008 |
dives | +0.008 |
Fly | +0.007 |
eway | +0.007 |
ag | +0.007 |
Neg logit contributions | |
groceries | -0.004 |
ama | -0.004 |
first | -0.004 |
Johnson | -0.004 |
expensive | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Em | +0.004 |
ama | +0.004 |
Gem | +0.004 |
Johnson | +0.004 |
checkout | +0.004 |
Neg logit contributions | |
dives | -0.006 |
eway | -0.005 |
tricks | -0.005 |
mer | -0.005 |
films | -0.005 |
Token | saved |
Token ID | 7448 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Em | +0.019 |
Gem | +0.018 |
checkout | +0.017 |
grandma | +0.017 |
Johnson | +0.017 |
Neg logit contributions | |
dives | -0.031 |
eway | -0.030 |
films | -0.029 |
ag | -0.028 |
RO | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
Em | +0.043 |
Gem | +0.042 |
groceries | +0.041 |
Johnson | +0.041 |
expensive | +0.040 |
Neg logit contributions | |
dives | -0.062 |
eway | -0.055 |
villains | -0.054 |
RO | -0.054 |
mer | -0.054 |
Token | in |
Token ID | 287 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Em | +0.015 |
ama | +0.014 |
Gem | +0.014 |
Johnson | +0.014 |
groceries | +0.014 |
Neg logit contributions | |
dives | -0.029 |
eway | -0.026 |
films | -0.026 |
mer | -0.025 |
Fly | -0.025 |
Token | bags |
Token ID | 11668 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
ama | +0.033 |
Em | +0.031 |
Gem | +0.030 |
groceries | +0.030 |
checkout | +0.029 |
Neg logit contributions | |
dives | -0.040 |
eway | -0.036 |
films | -0.035 |
mer | -0.035 |
tricks | -0.034 |
Token | for |
Token ID | 329 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
ama | +0.112 |
Em | +0.111 |
Gem | +0.106 |
infected | +0.105 |
groceries | +0.103 |
Neg logit contributions | |
dives | -0.124 |
eway | -0.114 |
mer | -0.110 |
tricks | -0.108 |
films | -0.105 |
Token | the |
Token ID | 262 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
Em | +0.005 |
ama | +0.005 |
Gem | +0.005 |
Johnson | +0.004 |
groceries | +0.004 |
Neg logit contributions | |
dives | -0.006 |
eway | -0.005 |
tricks | -0.005 |
films | -0.005 |
mer | -0.005 |
Token | next |
Token ID | 1306 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
Em | +0.012 |
ama | +0.011 |
Gem | +0.011 |
groceries | +0.011 |
checkout | +0.011 |
Neg logit contributions | |
dives | -0.019 |
eway | -0.018 |
tricks | -0.017 |
films | -0.016 |
mer | -0.016 |
Token | day |
Token ID | 1110 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
dives | +0.019 |
eway | +0.018 |
RO | +0.018 |
hops | +0.017 |
Fly | +0.017 |
Neg logit contributions | |
grandma | -0.010 |
expensive | -0.010 |
groceries | -0.010 |
first | -0.010 |
Johnson | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
Em | +0.018 |
ama | +0.018 |
Gem | +0.018 |
Johnson | +0.017 |
groceries | +0.017 |
Neg logit contributions | |
dives | -0.033 |
eway | -0.030 |
tricks | -0.029 |
films | -0.029 |
mer | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Em | +0.001 |
ama | +0.001 |
Gem | +0.001 |
groceries | +0.001 |
checkout | +0.001 |
Neg logit contributions | |
dives | -0.001 |
eway | -0.001 |
tricks | -0.001 |
mer | -0.001 |
films | -0.001 |
Token | put |
Token ID | 1234 |
Feature activation | -9.61e-02 |
Pos logit contributions | |
eway | +0.006 |
ile | +0.006 |
dives | +0.006 |
ag | +0.005 |
films | +0.005 |
Neg logit contributions | |
Gem | -0.003 |
buy | -0.003 |
checkout | -0.003 |
Em | -0.003 |
groceries | -0.003 |
Token | them |
Token ID | 606 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
Em | +0.002 |
Gem | +0.002 |
ama | +0.002 |
groceries | +0.002 |
Johnson | +0.002 |
Neg logit contributions | |
dives | -0.002 |
eway | -0.002 |
villains | -0.002 |
tricks | -0.002 |
films | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
groceries | +0.008 |
Em | +0.008 |
ama | +0.007 |
Gem | +0.007 |
Johnson | +0.007 |
Neg logit contributions | |
dives | -0.010 |
eway | -0.010 |
films | -0.009 |
villains | -0.009 |
mer | -0.009 |
Token | their |
Token ID | 511 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ama | +0.025 |
ongo | +0.023 |
ilda | +0.023 |
uch | +0.023 |
mm | +0.022 |
Neg logit contributions | |
dives | -0.015 |
mer | -0.014 |
eway | -0.014 |
films | -0.013 |
tricks | -0.013 |
Token | baskets |
Token ID | 46530 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
groceries | +0.020 |
expensive | +0.018 |
ama | +0.017 |
grandma | +0.017 |
checkout | +0.017 |
Neg logit contributions | |
eway | -0.044 |
dives | -0.042 |
RO | -0.041 |
ull | -0.041 |
mer | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Em | +0.124 |
ama | +0.121 |
Gem | +0.116 |
infected | +0.116 |
mm | +0.114 |
Neg logit contributions | |
dives | -0.112 |
eway | -0.101 |
mer | -0.098 |
tricks | -0.095 |
fish | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
dives | +0.010 |
eway | +0.009 |
tricks | +0.009 |
mer | +0.009 |
films | +0.008 |
Neg logit contributions | |
Em | -0.006 |
ama | -0.006 |
Gem | -0.006 |
Johnson | -0.006 |
groceries | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
dives | +0.016 |
eway | +0.015 |
tricks | +0.014 |
films | +0.014 |
Fly | +0.014 |
Neg logit contributions | |
Em | -0.012 |
groceries | -0.012 |
Gem | -0.012 |
ama | -0.012 |
checkout | -0.012 |
Token | " |
Token ID | 1 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Em | +0.005 |
ama | +0.005 |
Gem | +0.005 |
groceries | +0.005 |
Johnson | +0.005 |
Neg logit contributions | |
dives | -0.008 |
eway | -0.007 |
tricks | -0.007 |
films | -0.007 |
mer | -0.007 |
Token | Look |
Token ID | 8567 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Em | +0.021 |
checkout | +0.020 |
Gem | +0.020 |
Mom | +0.019 |
groceries | +0.019 |
Neg logit contributions | |
dives | -0.034 |
eway | -0.032 |
tricks | -0.030 |
films | -0.029 |
hops | -0.029 |
Token | She |
Token ID | 1375 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
dives | +0.015 |
eway | +0.013 |
dances | +0.013 |
Fly | +0.013 |
films | +0.013 |
Neg logit contributions | |
Em | -0.009 |
ama | -0.009 |
infected | -0.009 |
groceries | -0.008 |
checkout | -0.008 |
Token | writes |
Token ID | 6797 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
eway | +0.012 |
dives | +0.011 |
films | +0.010 |
ull | +0.010 |
mer | +0.010 |
Neg logit contributions | |
Em | -0.010 |
expensive | -0.010 |
Gem | -0.009 |
ama | -0.009 |
checkout | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
dives | +0.038 |
eway | +0.034 |
tricks | +0.033 |
films | +0.032 |
mer | +0.032 |
Neg logit contributions | |
Em | -0.028 |
ama | -0.028 |
Gem | -0.027 |
Johnson | -0.026 |
groceries | -0.026 |
Token | To |
Token ID | 2514 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
ama | +0.031 |
Gem | +0.029 |
groceries | +0.029 |
Em | +0.029 |
checkout | +0.029 |
Neg logit contributions | |
dives | -0.036 |
eway | -0.033 |
RO | -0.033 |
tricks | -0.032 |
films | -0.032 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
dives | +0.024 |
eway | +0.021 |
tricks | +0.021 |
films | +0.021 |
mer | +0.021 |
Neg logit contributions | |
ama | -0.018 |
Em | -0.018 |
Johnson | -0.017 |
Gem | -0.017 |
groceries | -0.017 |
Token | " |
Token ID | 1 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
Em | +0.022 |
groceries | +0.021 |
Gem | +0.021 |
checkout | +0.020 |
ama | +0.020 |
Neg logit contributions | |
dives | -0.030 |
films | -0.028 |
tricks | -0.027 |
eway | -0.027 |
mer | -0.026 |
Token | on |
Token ID | 319 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
checkout | +0.120 |
Em | +0.119 |
ama | +0.118 |
infected | +0.118 |
groceries | +0.116 |
Neg logit contributions | |
dives | -0.109 |
eway | -0.098 |
tricks | -0.096 |
films | -0.093 |
dances | -0.092 |
Token | the |
Token ID | 262 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
dives | +0.038 |
tricks | +0.035 |
films | +0.034 |
eway | +0.034 |
dances | +0.033 |
Neg logit contributions | |
ama | -0.032 |
Em | -0.030 |
Johnson | -0.029 |
Gem | -0.029 |
infected | -0.029 |
Token | heart |
Token ID | 2612 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
dives | +0.021 |
eway | +0.019 |
tricks | +0.019 |
films | +0.019 |
mer | +0.019 |
Neg logit contributions | |
Em | -0.017 |
ama | -0.017 |
Gem | -0.016 |
Johnson | -0.016 |
infected | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
dives | +0.027 |
eway | +0.024 |
tricks | +0.023 |
films | +0.023 |
mer | +0.023 |
Neg logit contributions | |
Em | -0.019 |
ama | -0.018 |
Gem | -0.018 |
groceries | -0.017 |
Johnson | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
severe | +0.002 |
infected | +0.002 |
groceries | +0.002 |
expensive | +0.002 |
ama | +0.002 |
Neg logit contributions | |
dives | -0.002 |
Fly | -0.002 |
dances | -0.002 |
films | -0.002 |
eway | -0.002 |
Token | go |
Token ID | 467 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
Em | +0.021 |
ama | +0.021 |
Gem | +0.020 |
Johnson | +0.019 |
groceries | +0.019 |
Neg logit contributions | |
dives | -0.028 |
eway | -0.026 |
tricks | -0.024 |
films | -0.024 |
mer | -0.024 |
Token | back |
Token ID | 736 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
dives | +0.028 |
eway | +0.025 |
mer | +0.024 |
tricks | +0.024 |
films | +0.023 |
Neg logit contributions | |
Em | -0.019 |
ama | -0.019 |
Gem | -0.019 |
checkout | -0.018 |
groceries | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
dives | +0.028 |
eway | +0.025 |
tricks | +0.024 |
films | +0.024 |
mer | +0.024 |
Neg logit contributions | |
Em | -0.019 |
ama | -0.019 |
Gem | -0.019 |
checkout | -0.018 |
groceries | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Em | +0.017 |
Gem | +0.016 |
ama | +0.016 |
Johnson | +0.016 |
groceries | +0.016 |
Neg logit contributions | |
dives | -0.033 |
eway | -0.032 |
tricks | -0.030 |
mer | -0.029 |
RO | -0.029 |
Token | pool |
Token ID | 5933 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
dives | +0.037 |
eway | +0.036 |
RO | +0.033 |
Fly | +0.032 |
films | +0.032 |
Neg logit contributions | |
groceries | -0.035 |
checkout | -0.035 |
expensive | -0.034 |
ama | -0.034 |
Johnson | -0.033 |
Token | side |
Token ID | 1589 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
Em | +0.021 |
ama | +0.021 |
Gem | +0.020 |
Johnson | +0.019 |
groceries | +0.019 |
Neg logit contributions | |
dives | -0.058 |
eway | -0.054 |
tricks | -0.053 |
films | -0.052 |
mer | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ama | +0.063 |
Gem | +0.061 |
Em | +0.061 |
Johnson | +0.060 |
groceries | +0.059 |
Neg logit contributions | |
dives | -0.170 |
eway | -0.160 |
RO | -0.156 |
Fly | -0.154 |
films | -0.152 |
Token | Mia |
Token ID | 32189 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
first | +0.037 |
grandma | +0.037 |
Em | +0.037 |
Johnson | +0.036 |
ama | +0.036 |
Neg logit contributions | |
dives | -0.047 |
eway | -0.047 |
tricks | -0.043 |
films | -0.043 |
mer | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
ama | +0.011 |
Em | +0.011 |
Gem | +0.011 |
Johnson | +0.010 |
groceries | +0.010 |
Neg logit contributions | |
dives | -0.031 |
eway | -0.030 |
films | -0.028 |
tricks | -0.028 |
mer | -0.028 |
Token | Maybe |
Token ID | 6674 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
Em | +0.008 |
ama | +0.008 |
Gem | +0.007 |
Johnson | +0.007 |
groceries | +0.007 |
Neg logit contributions | |
dives | -0.010 |
eway | -0.009 |
tricks | -0.008 |
mer | -0.008 |
films | -0.008 |
Token | we |
Token ID | 356 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Em | +0.012 |
ama | +0.012 |
Gem | +0.012 |
Johnson | +0.011 |
groceries | +0.011 |
Neg logit contributions | |
dives | -0.018 |
eway | -0.017 |
tricks | -0.016 |
films | -0.016 |
mer | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Em | +0.025 |
ama | +0.025 |
Gem | +0.024 |
groceries | +0.023 |
Johnson | +0.023 |
Neg logit contributions | |
dives | -0.050 |
eway | -0.046 |
tricks | -0.044 |
films | -0.044 |
mer | -0.044 |
Token | they |
Token ID | 484 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Em | +0.036 |
ama | +0.035 |
Gem | +0.035 |
groceries | +0.034 |
Johnson | +0.034 |
Neg logit contributions | |
dives | -0.037 |
eway | -0.033 |
tricks | -0.031 |
films | -0.031 |
mer | -0.031 |
Token | checked |
Token ID | 10667 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ama | +0.052 |
Em | +0.051 |
groceries | +0.050 |
Johnson | +0.049 |
Gem | +0.049 |
Neg logit contributions | |
dives | -0.049 |
mer | -0.042 |
eway | -0.042 |
RO | -0.040 |
dances | -0.040 |
Token | in |
Token ID | 287 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
ama | +0.031 |
Em | +0.031 |
checkout | +0.030 |
Gem | +0.030 |
infected | +0.030 |
Neg logit contributions | |
dives | -0.022 |
eway | -0.020 |
films | -0.018 |
tricks | -0.018 |
mer | -0.018 |
Token | their |
Token ID | 511 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ama | +0.017 |
uch | +0.016 |
ongo | +0.016 |
mm | +0.016 |
ppa | +0.015 |
Neg logit contributions | |
dives | -0.014 |
films | -0.014 |
eway | -0.013 |
tricks | -0.013 |
mer | -0.013 |
Token | bags |
Token ID | 11668 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
ama | +0.032 |
groceries | +0.032 |
Em | +0.032 |
Gem | +0.031 |
expensive | +0.031 |
Neg logit contributions | |
dives | -0.053 |
eway | -0.051 |
mer | -0.048 |
tricks | -0.047 |
RO | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
Em | +0.142 |
infected | +0.139 |
mm | +0.134 |
ama | +0.130 |
innie | +0.130 |
Neg logit contributions | |
dives | -0.083 |
eway | -0.082 |
ag | -0.074 |
mer | -0.071 |
ull | -0.068 |
Token | got |
Token ID | 1392 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Em | +0.010 |
Gem | +0.010 |
groceries | +0.009 |
checkout | +0.009 |
ama | +0.009 |
Neg logit contributions | |
dives | -0.015 |
eway | -0.014 |
films | -0.013 |
tricks | -0.013 |
RO | -0.013 |
Token | their |
Token ID | 511 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
Em | +0.028 |
Gem | +0.027 |
ama | +0.027 |
groceries | +0.026 |
checkout | +0.026 |
Neg logit contributions | |
dives | -0.044 |
eway | -0.041 |
tricks | -0.039 |
films | -0.038 |
mer | -0.038 |
Token | tickets |
Token ID | 8587 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Em | +0.019 |
ama | +0.019 |
Gem | +0.018 |
groceries | +0.018 |
Johnson | +0.018 |
Neg logit contributions | |
dives | -0.030 |
eway | -0.027 |
tricks | -0.026 |
films | -0.026 |
mer | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Em | +0.041 |
ama | +0.041 |
Gem | +0.039 |
checkout | +0.038 |
Johnson | +0.038 |
Neg logit contributions | |
dives | -0.057 |
eway | -0.052 |
tricks | -0.050 |
mer | -0.050 |
films | -0.049 |
Token | pack |
Token ID | 2353 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
ama | +0.022 |
Em | +0.022 |
Gem | +0.021 |
Johnson | +0.021 |
groceries | +0.021 |
Neg logit contributions | |
dives | -0.031 |
eway | -0.027 |
tricks | -0.027 |
mer | -0.027 |
films | -0.027 |
Token | some |
Token ID | 617 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
ama | +0.021 |
Em | +0.021 |
Gem | +0.020 |
Johnson | +0.020 |
checkout | +0.020 |
Neg logit contributions | |
dives | -0.015 |
eway | -0.013 |
tricks | -0.013 |
films | -0.012 |
mer | -0.012 |
Token | gems |
Token ID | 23685 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
dives | +0.000 |
eway | +0.000 |
tricks | +0.000 |
films | +0.000 |
mer | +0.000 |
Neg logit contributions | |
Em | -0.000 |
ama | -0.000 |
Gem | -0.000 |
Johnson | -0.000 |
groceries | -0.000 |
Token | in |
Token ID | 287 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
Em | +0.014 |
ama | +0.014 |
Gem | +0.014 |
groceries | +0.014 |
Johnson | +0.013 |
Neg logit contributions | |
dives | -0.022 |
eway | -0.020 |
films | -0.019 |
tricks | -0.019 |
RO | -0.019 |
Token | their |
Token ID | 511 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
ama | +0.032 |
ongo | +0.030 |
uch | +0.030 |
mm | +0.029 |
ilda | +0.029 |
Neg logit contributions | |
dives | -0.011 |
mer | -0.010 |
eway | -0.010 |
films | -0.010 |
swim | -0.010 |
Token | bags |
Token ID | 11668 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
groceries | +0.025 |
ama | +0.024 |
expensive | +0.024 |
Em | +0.024 |
Gem | +0.024 |
Neg logit contributions | |
dives | -0.065 |
eway | -0.064 |
RO | -0.060 |
ull | -0.059 |
mer | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
Em | +0.143 |
infected | +0.139 |
ama | +0.133 |
severe | +0.129 |
mm | +0.128 |
Neg logit contributions | |
dives | -0.086 |
eway | -0.083 |
ag | -0.075 |
mer | -0.073 |
ull | -0.073 |
Token | They |
Token ID | 1119 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
ama | +0.016 |
Em | +0.015 |
infected | +0.015 |
Gem | +0.015 |
groceries | +0.015 |
Neg logit contributions | |
dives | -0.013 |
eway | -0.011 |
tricks | -0.010 |
films | -0.010 |
dances | -0.010 |
Token | do |
Token ID | 466 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
ama | +0.019 |
Em | +0.018 |
Johnson | +0.018 |
Gem | +0.018 |
infected | +0.017 |
Neg logit contributions | |
dives | -0.024 |
mer | -0.020 |
tricks | -0.020 |
swim | -0.020 |
dances | -0.020 |
Token | not |
Token ID | 407 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
dives | +0.118 |
eway | +0.109 |
tricks | +0.106 |
films | +0.105 |
mer | +0.105 |
Neg logit contributions | |
Em | -0.040 |
ama | -0.040 |
Gem | -0.038 |
Johnson | -0.036 |
groceries | -0.036 |
Token | see |
Token ID | 766 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
ama | +0.008 |
Em | +0.008 |
Gem | +0.008 |
Johnson | +0.008 |
groceries | +0.008 |
Neg logit contributions | |
dives | -0.014 |
eway | -0.013 |
tricks | -0.012 |
mer | -0.012 |
films | -0.012 |
Token | coats |
Token ID | 30720 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
dives | +0.002 |
eway | +0.002 |
tricks | +0.002 |
films | +0.002 |
mer | +0.002 |
Neg logit contributions | |
Em | -0.002 |
Gem | -0.002 |
groceries | -0.002 |
ama | -0.002 |
checkout | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
ama | +0.064 |
Em | +0.061 |
Gem | +0.060 |
checkout | +0.059 |
infected | +0.058 |
Neg logit contributions | |
dives | -0.066 |
eway | -0.059 |
mer | -0.058 |
tricks | -0.057 |
films | -0.055 |
Token | put |
Token ID | 1234 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
dives | +0.026 |
eway | +0.025 |
films | +0.023 |
tricks | +0.023 |
mer | +0.023 |
Neg logit contributions | |
Em | -0.020 |
Gem | -0.020 |
groceries | -0.020 |
ama | -0.019 |
expensive | -0.019 |
Token | away |
Token ID | 1497 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
dives | +0.001 |
eway | +0.001 |
villains | +0.001 |
RO | +0.001 |
mer | +0.001 |
Neg logit contributions | |
Em | -0.001 |
groceries | -0.001 |
Gem | -0.001 |
expensive | -0.001 |
ama | -0.001 |
Token | their |
Token ID | 511 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
dives | +0.014 |
eway | +0.012 |
villains | +0.012 |
RO | +0.012 |
ile | +0.012 |
Neg logit contributions | |
groceries | -0.013 |
Em | -0.013 |
Gem | -0.012 |
expensive | -0.012 |
grandma | -0.012 |
Token | bags |
Token ID | 11668 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
groceries | +0.012 |
expensive | +0.012 |
Em | +0.011 |
ama | +0.011 |
grandma | +0.011 |
Neg logit contributions | |
eway | -0.017 |
dives | -0.017 |
ull | -0.016 |
Fly | -0.016 |
RO | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
ama | +0.134 |
Em | +0.129 |
mm | +0.128 |
Gem | +0.125 |
innie | +0.122 |
Neg logit contributions | |
dives | -0.092 |
mer | -0.083 |
eway | -0.082 |
ag | -0.080 |
swim | -0.076 |
Token | They |
Token ID | 1119 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Em | +0.006 |
ama | +0.006 |
Gem | +0.006 |
Johnson | +0.005 |
checkout | +0.005 |
Neg logit contributions | |
dives | -0.007 |
eway | -0.006 |
tricks | -0.006 |
mer | -0.006 |
films | -0.006 |
Token | c |
Token ID | 269 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
ama | +0.032 |
Johnson | +0.030 |
groceries | +0.030 |
ummy | +0.030 |
mm | +0.029 |
Neg logit contributions | |
dives | -0.027 |
mer | -0.024 |
swim | -0.024 |
slit | -0.023 |
dances | -0.022 |
Token | uddled |
Token ID | 32745 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ama | +0.015 |
Em | +0.015 |
Gem | +0.014 |
groceries | +0.014 |
checkout | +0.014 |
Neg logit contributions | |
dives | -0.022 |
eway | -0.020 |
mer | -0.019 |
films | -0.019 |
tricks | -0.019 |
Token | with |
Token ID | 351 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
Em | +0.025 |
Johnson | +0.024 |
Gem | +0.023 |
groceries | +0.023 |
ama | +0.023 |
Neg logit contributions | |
dives | -0.031 |
eway | -0.028 |
villains | -0.026 |
RO | -0.026 |
igators | -0.026 |
Token | said |
Token ID | 531 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
Em | +0.022 |
ama | +0.022 |
groceries | +0.021 |
Gem | +0.021 |
checkout | +0.021 |
Neg logit contributions | |
dives | -0.029 |
mer | -0.024 |
eway | -0.024 |
tricks | -0.024 |
dances | -0.024 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Em | +0.003 |
ama | +0.003 |
Gem | +0.003 |
Johnson | +0.002 |
groceries | +0.002 |
Neg logit contributions | |
dives | -0.004 |
eway | -0.004 |
films | -0.004 |
igators | -0.003 |
RO | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Em | +0.035 |
ama | +0.034 |
Gem | +0.034 |
groceries | +0.033 |
checkout | +0.033 |
Neg logit contributions | |
dives | -0.039 |
eway | -0.035 |
tricks | -0.033 |
mer | -0.033 |
films | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
ama | +0.042 |
infected | +0.040 |
Johnson | +0.039 |
groceries | +0.039 |
Em | +0.039 |
Neg logit contributions | |
dives | -0.039 |
films | -0.034 |
tricks | -0.034 |
mer | -0.033 |
eway | -0.033 |
Token | se |
Token ID | 384 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
dives | +0.004 |
mer | +0.004 |
eway | +0.004 |
tricks | +0.004 |
films | +0.004 |
Neg logit contributions | |
Em | -0.007 |
ama | -0.007 |
Johnson | -0.006 |
Gem | -0.006 |
infected | -0.006 |
Token | ag |
Token ID | 363 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
dives | +0.047 |
warriors | +0.044 |
Fly | +0.042 |
films | +0.041 |
mer | +0.041 |
Neg logit contributions | |
ama | -0.083 |
my | -0.080 |
expensive | -0.079 |
bur | -0.079 |
Em | -0.079 |
Token | ull |
Token ID | 724 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
dives | +0.080 |
villains | +0.071 |
poses | +0.070 |
igators | +0.068 |
warriors | +0.066 |
Neg logit contributions | |
ama | -0.157 |
first | -0.145 |
Gem | -0.143 |
Em | -0.139 |
two | -0.138 |
Token | s |
Token ID | 82 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
dives | +0.044 |
eway | +0.041 |
films | +0.039 |
tricks | +0.039 |
mer | +0.038 |
Neg logit contributions | |
Em | -0.028 |
ama | -0.028 |
Gem | -0.027 |
Johnson | -0.026 |
groceries | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Em | +0.019 |
ama | +0.019 |
Gem | +0.019 |
groceries | +0.018 |
Johnson | +0.018 |
Neg logit contributions | |
dives | -0.030 |
eway | -0.027 |
tricks | -0.026 |
films | -0.026 |
mer | -0.026 |
Token | put |
Token ID | 1234 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Em | +0.007 |
Gem | +0.006 |
ama | +0.006 |
grandma | +0.006 |
checkout | +0.006 |
Neg logit contributions | |
dives | -0.009 |
eway | -0.009 |
films | -0.009 |
tricks | -0.008 |
igators | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
dives | +0.006 |
eway | +0.006 |
films | +0.005 |
villains | +0.005 |
tricks | +0.005 |
Neg logit contributions | |
Em | -0.005 |
Gem | -0.004 |
ama | -0.004 |
groceries | -0.004 |
checkout | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
dives | +0.047 |
eway | +0.044 |
films | +0.042 |
mer | +0.042 |
RO | +0.041 |
Neg logit contributions | |
Em | -0.018 |
ama | -0.018 |
Gem | -0.017 |
Johnson | -0.016 |
groceries | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
dives | +0.026 |
eway | +0.023 |
tricks | +0.023 |
mer | +0.022 |
films | +0.022 |
Neg logit contributions | |
Em | -0.018 |
ama | -0.018 |
Gem | -0.017 |
Johnson | -0.017 |
checkout | -0.016 |
Token | more |
Token ID | 517 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
dives | +0.017 |
eway | +0.015 |
tricks | +0.014 |
films | +0.014 |
mer | +0.014 |
Neg logit contributions | |
Em | -0.013 |
ama | -0.013 |
Gem | -0.012 |
groceries | -0.012 |
Johnson | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
dives | +0.081 |
eway | +0.080 |
RO | +0.079 |
mer | +0.075 |
films | +0.074 |
Neg logit contributions | |
expensive | -0.051 |
grandma | -0.047 |
first | -0.046 |
Em | -0.046 |
Gem | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
dives | +0.038 |
eway | +0.036 |
RO | +0.033 |
tricks | +0.033 |
films | +0.033 |
Neg logit contributions | |
Em | -0.021 |
Gem | -0.021 |
expensive | -0.020 |
groceries | -0.020 |
ama | -0.020 |
Token | mer |
Token ID | 4017 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
dives | +0.011 |
eway | +0.010 |
films | +0.009 |
tricks | +0.009 |
mer | +0.009 |
Neg logit contributions | |
Em | -0.007 |
ama | -0.006 |
Gem | -0.006 |
groceries | -0.006 |
checkout | -0.006 |
Token | rier |
Token ID | 5277 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
RO | +0.140 |
slit | +0.137 |
Skip | +0.135 |
igators | +0.134 |
Ro | +0.132 |
Neg logit contributions | |
first | -0.069 |
ama | -0.069 |
biggest | -0.066 |
ummy | -0.063 |
grandma | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
dives | +0.070 |
eway | +0.065 |
films | +0.065 |
RO | +0.063 |
Fly | +0.062 |
Neg logit contributions | |
ama | -0.029 |
Em | -0.027 |
first | -0.027 |
Gem | -0.027 |
already | -0.027 |
Token | Come |
Token ID | 7911 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
dives | +0.009 |
eway | +0.009 |
tricks | +0.008 |
films | +0.008 |
mer | +0.008 |
Neg logit contributions | |
Em | -0.008 |
ama | -0.007 |
Gem | -0.007 |
Johnson | -0.007 |
groceries | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
Em | +0.007 |
Gem | +0.007 |
ama | +0.007 |
infected | +0.007 |
groceries | +0.007 |
Neg logit contributions | |
dives | -0.008 |
eway | -0.007 |
mer | -0.006 |
tricks | -0.006 |
Fly | -0.006 |
Token | my |
Token ID | 616 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
dives | +0.001 |
eway | +0.001 |
tricks | +0.001 |
poses | +0.001 |
films | +0.001 |
Neg logit contributions | |
Em | -0.001 |
Gem | -0.001 |
ama | -0.001 |
grandma | -0.001 |
checkout | -0.001 |
Token | |
Token ID | 220 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Em | +0.000 |
ama | +0.000 |
Gem | +0.000 |
Johnson | +0.000 |
checkout | +0.000 |
Neg logit contributions | |
dives | -0.001 |
eway | -0.000 |
mer | -0.000 |
tricks | -0.000 |
films | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +7.73e-03 |
Pos logit contributions | |
checkout | +0.032 |
Em | +0.032 |
Gem | +0.032 |
groceries | +0.032 |
ama | +0.031 |
Neg logit contributions | |
dives | -0.043 |
eway | -0.041 |
tricks | -0.038 |
Fly | -0.037 |
films | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
dives | +0.000 |
eway | +0.000 |
tricks | +0.000 |
Fly | +0.000 |
ull | +0.000 |
Neg logit contributions | |
groceries | -0.000 |
Em | -0.000 |
checkout | -0.000 |
Gem | -0.000 |
ama | -0.000 |
Token | The |
Token ID | 464 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Em | +0.014 |
ama | +0.014 |
Gem | +0.013 |
groceries | +0.013 |
Johnson | +0.013 |
Neg logit contributions | |
dives | -0.021 |
eway | -0.019 |
tricks | -0.018 |
films | -0.018 |
mer | -0.018 |
Token | big |
Token ID | 1263 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
first | +0.003 |
expensive | +0.003 |
ama | +0.003 |
checkout | +0.003 |
groceries | +0.002 |
Neg logit contributions | |
eway | -0.007 |
dives | -0.007 |
igators | -0.006 |
ull | -0.006 |
films | -0.006 |
Token | do |
Token ID | 466 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
eway | +0.059 |
dives | +0.058 |
mer | +0.054 |
RO | +0.053 |
ull | +0.052 |
Neg logit contributions | |
ama | -0.039 |
expensive | -0.039 |
Johnson | -0.038 |
first | -0.038 |
checkout | -0.038 |
Token | ggy |
Token ID | 19970 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
igators | +0.123 |
dives | +0.122 |
films | +0.118 |
mer | +0.114 |
dances | +0.109 |
Neg logit contributions | |
ama | -0.114 |
already | -0.100 |
't | -0.095 |
first | -0.094 |
no | -0.089 |
Token | got |
Token ID | 1392 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
dives | +0.078 |
eway | +0.073 |
films | +0.068 |
mer | +0.068 |
tricks | +0.068 |
Neg logit contributions | |
Em | -0.050 |
ama | -0.050 |
Gem | -0.048 |
checkout | -0.047 |
Johnson | -0.047 |
Token | sick |
Token ID | 6639 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Em | +0.020 |
ama | +0.019 |
Gem | +0.019 |
groceries | +0.018 |
Johnson | +0.018 |
Neg logit contributions | |
dives | -0.042 |
eway | -0.039 |
tricks | -0.038 |
films | -0.038 |
mer | -0.037 |
Token | er |
Token ID | 263 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
groceries | +0.006 |
Em | +0.006 |
Johnson | +0.006 |
ama | +0.006 |
Gem | +0.006 |
Neg logit contributions | |
dives | -0.014 |
eway | -0.013 |
RO | -0.013 |
films | -0.012 |
dances | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Em | +0.025 |
ama | +0.025 |
Gem | +0.024 |
Johnson | +0.024 |
groceries | +0.023 |
Neg logit contributions | |
dives | -0.039 |
eway | -0.035 |
tricks | -0.034 |
films | -0.034 |
mer | -0.033 |
Token | morning |
Token ID | 3329 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
ama | +0.013 |
Em | +0.013 |
expensive | +0.013 |
Gem | +0.012 |
Johnson | +0.012 |
Neg logit contributions | |
dives | -0.021 |
eway | -0.020 |
films | -0.019 |
tricks | -0.019 |
mer | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
dives | +0.030 |
films | +0.030 |
igators | +0.029 |
poses | +0.029 |
tricks | +0.029 |
Neg logit contributions | |
ama | -0.006 |
Em | -0.005 |
Johnson | -0.005 |
Gem | -0.005 |
already | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Em | +0.002 |
Gem | +0.002 |
Johnson | +0.002 |
ama | +0.002 |
expensive | +0.002 |
Neg logit contributions | |
dives | -0.003 |
films | -0.003 |
eway | -0.003 |
igators | -0.003 |
dances | -0.003 |
Token | found |
Token ID | 1043 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
dives | +0.005 |
eway | +0.004 |
films | +0.004 |
tricks | +0.004 |
mer | +0.004 |
Neg logit contributions | |
Em | -0.003 |
ama | -0.003 |
Gem | -0.003 |
Johnson | -0.003 |
groceries | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
Em | +0.003 |
ama | +0.003 |
Gem | +0.003 |
Johnson | +0.003 |
checkout | +0.003 |
Neg logit contributions | |
dives | -0.005 |
eway | -0.005 |
tricks | -0.004 |
mer | -0.004 |
films | -0.004 |
Token | pe |
Token ID | 613 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
dives | +0.026 |
eway | +0.024 |
tricks | +0.024 |
mer | +0.023 |
films | +0.023 |
Neg logit contributions | |
Em | -0.012 |
ama | -0.012 |
Gem | -0.012 |
groceries | -0.011 |
Johnson | -0.011 |
Token | b |
Token ID | 65 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
dives | +0.112 |
eway | +0.099 |
tricks | +0.095 |
mer | +0.091 |
films | +0.088 |
Neg logit contributions | |
Em | -0.150 |
ama | -0.147 |
Gem | -0.146 |
Johnson | -0.145 |
checkout | -0.143 |
Token | ble |
Token ID | 903 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
dives | +0.083 |
eway | +0.080 |
tricks | +0.077 |
ull | +0.075 |
mer | +0.073 |
Neg logit contributions | |
checkout | -0.069 |
Em | -0.068 |
groceries | -0.067 |
Johnson | -0.065 |
Gem | -0.064 |
Token | sitting |
Token ID | 5586 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
dives | +0.046 |
eway | +0.043 |
films | +0.042 |
RO | +0.041 |
dances | +0.041 |
Neg logit contributions | |
ama | -0.029 |
already | -0.028 |
expensive | -0.028 |
Em | -0.028 |
first | -0.028 |
Token | on |
Token ID | 319 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
dives | +0.019 |
mer | +0.018 |
eway | +0.017 |
ull | +0.016 |
tricks | +0.016 |
Neg logit contributions | |
Em | -0.037 |
Gem | -0.036 |
ama | -0.035 |
checkout | -0.034 |
Johnson | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
dives | +0.012 |
eway | +0.011 |
tricks | +0.011 |
mer | +0.011 |
films | +0.011 |
Neg logit contributions | |
Em | -0.006 |
ama | -0.006 |
Gem | -0.006 |
Johnson | -0.006 |
groceries | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
dives | +0.008 |
eway | +0.008 |
RO | +0.008 |
films | +0.008 |
igators | +0.008 |
Neg logit contributions | |
Em | -0.002 |
first | -0.002 |
ama | -0.001 |
tired | -0.001 |
infected | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
dives | +0.027 |
eway | +0.027 |
igators | +0.025 |
tunes | +0.025 |
dances | +0.025 |
Neg logit contributions | |
Em | -0.009 |
Johnson | -0.009 |
ama | -0.008 |
Mom | -0.008 |
mom | -0.008 |
Token | showed |
Token ID | 3751 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
already | +0.000 |
Em | +0.000 |
checkout | +0.000 |
still | +0.000 |
expensive | +0.000 |
Neg logit contributions | |
eway | -0.001 |
films | -0.001 |
dives | -0.001 |
igators | -0.001 |
ag | -0.001 |
Token | Lily |
Token ID | 20037 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
Em | +0.008 |
grandma | +0.007 |
Gem | +0.007 |
groceries | +0.007 |
expensive | +0.007 |
Neg logit contributions | |
dives | -0.016 |
eway | -0.015 |
films | -0.015 |
sym | -0.014 |
RO | -0.014 |
Token | his |
Token ID | 465 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Em | +0.017 |
Gem | +0.016 |
expensive | +0.016 |
ama | +0.016 |
groceries | +0.016 |
Neg logit contributions | |
dives | -0.026 |
eway | -0.024 |
RO | -0.023 |
villains | -0.023 |
films | -0.023 |
Token | pe |
Token ID | 613 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
dives | +0.026 |
tricks | +0.023 |
eway | +0.022 |
mer | +0.022 |
hops | +0.021 |
Neg logit contributions | |
Em | -0.028 |
ama | -0.028 |
Johnson | -0.027 |
checkout | -0.027 |
Gem | -0.027 |
Token | b |
Token ID | 65 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
dives | +0.103 |
eway | +0.090 |
tricks | +0.085 |
films | +0.084 |
mer | +0.084 |
Neg logit contributions | |
Em | -0.127 |
ama | -0.127 |
Gem | -0.124 |
Johnson | -0.121 |
groceries | -0.121 |
Token | ble |
Token ID | 903 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
dives | +0.066 |
eway | +0.061 |
tricks | +0.059 |
mer | +0.058 |
ull | +0.057 |
Neg logit contributions | |
Em | -0.044 |
checkout | -0.042 |
groceries | -0.041 |
Gem | -0.041 |
ama | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
dives | +0.017 |
eway | +0.016 |
films | +0.015 |
mer | +0.015 |
tricks | +0.015 |
Neg logit contributions | |
ama | -0.010 |
Em | -0.010 |
Gem | -0.009 |
groceries | -0.009 |
Johnson | -0.009 |
Token | It |
Token ID | 632 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
dives | +0.023 |
eway | +0.021 |
igators | +0.021 |
films | +0.020 |
tricks | +0.020 |
Neg logit contributions | |
Em | -0.010 |
ama | -0.009 |
Gem | -0.009 |
Johnson | -0.009 |
expensive | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
dives | +0.017 |
eway | +0.017 |
films | +0.016 |
villains | +0.015 |
mer | +0.015 |
Neg logit contributions | |
Em | -0.008 |
expensive | -0.008 |
infected | -0.007 |
already | -0.007 |
Gem | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
dives | +0.089 |
tricks | +0.081 |
films | +0.080 |
dances | +0.078 |
mer | +0.078 |
Neg logit contributions | |
ama | -0.035 |
Em | -0.034 |
Gem | -0.032 |
Mom | -0.031 |
Johnson | -0.030 |
Token | " |
Token ID | 1 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
dives | +0.052 |
tricks | +0.046 |
films | +0.046 |
eway | +0.045 |
dances | +0.045 |
Neg logit contributions | |
ama | -0.023 |
Em | -0.023 |
Gem | -0.022 |
Johnson | -0.020 |
checkout | -0.020 |
Token | We |
Token ID | 1135 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Em | +0.009 |
Gem | +0.009 |
Johnson | +0.008 |
ama | +0.008 |
checkout | +0.008 |
Neg logit contributions | |
dives | -0.017 |
eway | -0.015 |
films | -0.015 |
tricks | -0.015 |
dances | -0.014 |
Token | didn |
Token ID | 1422 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
dives | +0.045 |
eway | +0.041 |
tricks | +0.040 |
mer | +0.040 |
films | +0.040 |
Neg logit contributions | |
ama | -0.022 |
Em | -0.021 |
Gem | -0.021 |
Johnson | -0.020 |
groceries | -0.020 |
Token | 't |
Token ID | 470 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
dives | +0.013 |
eway | +0.012 |
tricks | +0.012 |
films | +0.012 |
Fly | +0.012 |
Neg logit contributions | |
ama | -0.004 |
Gem | -0.004 |
Em | -0.004 |
checkout | -0.004 |
groceries | -0.004 |
Token | know |
Token ID | 760 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
dives | +0.031 |
tricks | +0.028 |
eway | +0.028 |
mer | +0.027 |
films | +0.026 |
Neg logit contributions | |
ama | -0.019 |
Em | -0.018 |
groceries | -0.018 |
checkout | -0.017 |
Gem | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
dives | +0.080 |
eway | +0.073 |
tricks | +0.070 |
films | +0.070 |
mer | +0.070 |
Neg logit contributions | |
Em | -0.040 |
ama | -0.039 |
Gem | -0.038 |
groceries | -0.037 |
Johnson | -0.037 |
Token | was |
Token ID | 373 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
dives | +0.041 |
eway | +0.037 |
tricks | +0.036 |
films | +0.036 |
mer | +0.035 |
Neg logit contributions | |
Em | -0.028 |
ama | -0.028 |
Gem | -0.027 |
Johnson | -0.026 |
groceries | -0.026 |
Token | your |
Token ID | 534 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
dives | +0.008 |
eway | +0.007 |
films | +0.007 |
mer | +0.007 |
tricks | +0.007 |
Neg logit contributions | |
Em | -0.004 |
Gem | -0.004 |
expensive | -0.004 |
ama | -0.004 |
Johnson | -0.004 |
Token | plane |
Token ID | 6614 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Em | +0.013 |
ama | +0.013 |
Gem | +0.013 |
checkout | +0.012 |
Johnson | +0.012 |
Neg logit contributions | |
dives | -0.027 |
eway | -0.024 |
tricks | -0.024 |
films | -0.023 |
mer | -0.023 |
Token | ," |
Token ID | 553 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
Em | +0.020 |
ama | +0.020 |
Gem | +0.019 |
checkout | +0.018 |
groceries | +0.018 |
Neg logit contributions | |
dives | -0.040 |
eway | -0.037 |
tricks | -0.036 |
films | -0.035 |
mer | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
Em | +0.005 |
ama | +0.005 |
Gem | +0.005 |
groceries | +0.005 |
Johnson | +0.005 |
Neg logit contributions | |
dives | -0.008 |
eway | -0.007 |
tricks | -0.007 |
films | -0.007 |
mer | -0.007 |
Token | They |
Token ID | 1119 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
dives | +0.005 |
eway | +0.005 |
tricks | +0.005 |
mer | +0.005 |
films | +0.005 |
Neg logit contributions | |
Em | -0.003 |
ama | -0.003 |
Gem | -0.003 |
Johnson | -0.003 |
groceries | -0.003 |
Token | knocked |
Token ID | 13642 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ama | +0.035 |
ummy | +0.033 |
groceries | +0.033 |
mm | +0.033 |
Johnson | +0.032 |
Neg logit contributions | |
dives | -0.021 |
slit | -0.019 |
ks | -0.018 |
swim | -0.018 |
RO | -0.017 |
Token | again |
Token ID | 757 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ama | +0.048 |
Em | +0.048 |
Gem | +0.047 |
checkout | +0.046 |
expensive | +0.046 |
Neg logit contributions | |
dives | -0.034 |
eway | -0.030 |
films | -0.027 |
igators | -0.027 |
ull | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
dives | +0.028 |
eway | +0.025 |
films | +0.023 |
tricks | +0.023 |
dances | +0.022 |
Neg logit contributions | |
Em | -0.030 |
ama | -0.030 |
checkout | -0.030 |
infected | -0.030 |
Gem | -0.029 |
Token | louder |
Token ID | 27089 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ama | +0.016 |
Em | +0.015 |
Gem | +0.015 |
checkout | +0.014 |
Johnson | +0.014 |
Neg logit contributions | |
dives | -0.016 |
films | -0.014 |
mer | -0.013 |
eway | -0.013 |
dances | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
dives | +0.055 |
eway | +0.052 |
igators | +0.051 |
RO | +0.050 |
Fly | +0.049 |
Neg logit contributions | |
ama | -0.023 |
Em | -0.022 |
Gem | -0.022 |
grandma | -0.021 |
Johnson | -0.021 |
Token | but |
Token ID | 475 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
ama | +0.009 |
Em | +0.008 |
Gem | +0.008 |
groceries | +0.008 |
Johnson | +0.008 |
Neg logit contributions | |
dives | -0.010 |
eway | -0.009 |
mer | -0.009 |
films | -0.009 |
tricks | -0.009 |
Token | still |
Token ID | 991 |
Feature activation | -7.36e-02 |
Pos logit contributions | |
Em | +0.012 |
ama | +0.012 |
Gem | +0.012 |
groceries | +0.011 |
Johnson | +0.011 |
Neg logit contributions | |
dives | -0.022 |
eway | -0.020 |
tricks | -0.019 |
mer | -0.019 |
films | -0.019 |
Token | no |
Token ID | 645 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
Em | +0.001 |
ama | +0.001 |
Gem | +0.001 |
Johnson | +0.001 |
expensive | +0.001 |
Neg logit contributions | |
dives | -0.002 |
eway | -0.002 |
films | -0.002 |
tricks | -0.002 |
mer | -0.002 |
Token | one |
Token ID | 530 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Em | +0.001 |
groceries | +0.001 |
expensive | +0.001 |
Johnson | +0.001 |
ama | +0.001 |
Neg logit contributions | |
dives | -0.002 |
eway | -0.002 |
mer | -0.001 |
films | -0.001 |
RO | -0.001 |
Token | were |
Token ID | 547 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
Em | +0.002 |
Gem | +0.002 |
ama | +0.002 |
expensive | +0.002 |
Johnson | +0.002 |
Neg logit contributions | |
dives | -0.003 |
eway | -0.003 |
films | -0.002 |
tricks | -0.002 |
RO | -0.002 |
Token | glad |
Token ID | 9675 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
Em | +0.012 |
ama | +0.012 |
Gem | +0.012 |
Johnson | +0.011 |
expensive | +0.011 |
Neg logit contributions | |
dives | -0.028 |
eway | -0.026 |
films | -0.025 |
tricks | -0.025 |
mer | -0.024 |
Token | that |
Token ID | 326 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
Em | +0.015 |
Gem | +0.014 |
grandma | +0.014 |
already | +0.013 |
Johnson | +0.013 |
Neg logit contributions | |
dives | -0.028 |
eway | -0.027 |
RO | -0.026 |
igators | -0.025 |
films | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
Em | +0.011 |
Gem | +0.011 |
ama | +0.010 |
Johnson | +0.010 |
expensive | +0.010 |
Neg logit contributions | |
dives | -0.015 |
eway | -0.014 |
films | -0.013 |
mer | -0.013 |
tricks | -0.013 |
Token | z |
Token ID | 1976 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Em | +0.012 |
ama | +0.012 |
Gem | +0.012 |
Johnson | +0.011 |
groceries | +0.011 |
Neg logit contributions | |
dives | -0.014 |
eway | -0.013 |
films | -0.012 |
tricks | -0.012 |
mer | -0.012 |
Token | ebra |
Token ID | 37052 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
dives | +0.051 |
films | +0.047 |
eway | +0.046 |
igators | +0.044 |
mer | +0.043 |
Neg logit contributions | |
ama | -0.055 |
first | -0.046 |
mm | -0.045 |
bur | -0.044 |
already | -0.044 |
Token | had |
Token ID | 550 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
dives | +0.043 |
eway | +0.040 |
films | +0.038 |
mer | +0.038 |
tricks | +0.037 |
Neg logit contributions | |
ama | -0.023 |
Em | -0.023 |
Gem | -0.021 |
Johnson | -0.021 |
already | -0.021 |
Token | changed |
Token ID | 3421 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Em | +0.031 |
Gem | +0.030 |
ama | +0.029 |
groceries | +0.028 |
expensive | +0.028 |
Neg logit contributions | |
dives | -0.051 |
eway | -0.048 |
films | -0.045 |
mer | -0.044 |
tricks | -0.044 |
Token | his |
Token ID | 465 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
Em | +0.033 |
Gem | +0.032 |
ama | +0.031 |
expensive | +0.031 |
groceries | +0.031 |
Neg logit contributions | |
dives | -0.050 |
eway | -0.046 |
RO | -0.045 |
films | -0.044 |
Fly | -0.043 |
Token | ways |
Token ID | 2842 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Em | +0.016 |
ama | +0.016 |
Gem | +0.016 |
groceries | +0.015 |
Johnson | +0.015 |
Neg logit contributions | |
dives | -0.027 |
eway | -0.025 |
films | -0.024 |
tricks | -0.024 |
mer | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Em | +0.025 |
ama | +0.025 |
Gem | +0.024 |
groceries | +0.023 |
Johnson | +0.023 |
Neg logit contributions | |
dives | -0.036 |
eway | -0.033 |
tricks | -0.032 |
mer | -0.031 |
films | -0.031 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ama | +0.030 |
Em | +0.029 |
checkout | +0.028 |
groceries | +0.028 |
Gem | +0.028 |
Neg logit contributions | |
dives | -0.042 |
eway | -0.038 |
films | -0.037 |
tricks | -0.037 |
mer | -0.037 |
Token | are |
Token ID | 389 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ama | +0.036 |
groceries | +0.033 |
Em | +0.033 |
Gem | +0.033 |
infected | +0.032 |
Neg logit contributions | |
dives | -0.042 |
mer | -0.036 |
dances | -0.036 |
RO | -0.035 |
tricks | -0.035 |
Token | twins |
Token ID | 20345 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Em | +0.036 |
Gem | +0.034 |
checkout | +0.034 |
Johnson | +0.034 |
infected | +0.034 |
Neg logit contributions | |
dives | -0.037 |
films | -0.033 |
mer | -0.031 |
dances | -0.031 |
tricks | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ama | +0.033 |
groceries | +0.032 |
Gem | +0.032 |
infected | +0.031 |
Em | +0.031 |
Neg logit contributions | |
dives | -0.031 |
mer | -0.028 |
tricks | -0.028 |
films | -0.028 |
dances | -0.027 |
Token | They |
Token ID | 1119 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Em | +0.025 |
ama | +0.025 |
Gem | +0.024 |
Johnson | +0.024 |
groceries | +0.023 |
Neg logit contributions | |
dives | -0.028 |
eway | -0.025 |
tricks | -0.024 |
mer | -0.023 |
films | -0.023 |
Token | like |
Token ID | 588 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ama | +0.035 |
Em | +0.033 |
groceries | +0.033 |
Johnson | +0.032 |
infected | +0.032 |
Neg logit contributions | |
dives | -0.041 |
tricks | -0.036 |
mer | -0.036 |
dances | -0.035 |
eway | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
dives | +0.045 |
eway | +0.045 |
ile | +0.040 |
RO | +0.040 |
mer | +0.040 |
Neg logit contributions | |
groceries | -0.024 |
expensive | -0.023 |
Gem | -0.023 |
grandma | -0.023 |
Em | -0.022 |
Token | play |
Token ID | 711 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
dives | +0.023 |
eway | +0.021 |
mer | +0.020 |
films | +0.020 |
tricks | +0.020 |
Neg logit contributions | |
Em | -0.020 |
ama | -0.020 |
Gem | -0.019 |
groceries | -0.019 |
Johnson | -0.019 |
Token | together |
Token ID | 1978 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
eway | +0.018 |
dives | +0.017 |
aids | +0.016 |
anne | +0.016 |
ived | +0.016 |
Neg logit contributions | |
first | -0.009 |
groceries | -0.009 |
still | -0.008 |
two | -0.008 |
top | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
first | +0.004 |
ama | +0.004 |
checkout | +0.004 |
Em | +0.003 |
expensive | +0.003 |
Neg logit contributions | |
dives | -0.010 |
eway | -0.010 |
RO | -0.009 |
mer | -0.009 |
villains | -0.009 |
Token | but |
Token ID | 475 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
dives | +0.005 |
eway | +0.005 |
RO | +0.005 |
ull | +0.005 |
ile | +0.005 |
Neg logit contributions | |
Johnson | -0.002 |
expensive | -0.002 |
already | -0.002 |
buy | -0.002 |
Em | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
dives | +0.058 |
eway | +0.053 |
films | +0.051 |
tricks | +0.051 |
mer | +0.050 |
Neg logit contributions | |
Em | -0.034 |
ama | -0.033 |
Gem | -0.033 |
Johnson | -0.032 |
groceries | -0.031 |
Token | mom |
Token ID | 1995 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
dives | +0.036 |
eway | +0.033 |
tricks | +0.033 |
mer | +0.033 |
films | +0.033 |
Neg logit contributions | |
Em | -0.011 |
ama | -0.011 |
Gem | -0.011 |
checkout | -0.010 |
groceries | -0.010 |
Token | my |
Token ID | 1820 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
dives | +0.014 |
tricks | +0.013 |
mer | +0.012 |
jokes | +0.012 |
dances | +0.012 |
Neg logit contributions | |
groceries | -0.009 |
ama | -0.008 |
Em | -0.008 |
Gem | -0.008 |
expensive | -0.008 |
Token | told |
Token ID | 1297 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
dives | +0.007 |
tricks | +0.006 |
mer | +0.006 |
dances | +0.006 |
jokes | +0.006 |
Neg logit contributions | |
groceries | -0.006 |
Em | -0.005 |
ama | -0.005 |
Gem | -0.005 |
Johnson | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Em | +0.004 |
Gem | +0.004 |
ama | +0.004 |
groceries | +0.004 |
Johnson | +0.004 |
Neg logit contributions | |
dives | -0.009 |
eway | -0.008 |
mer | -0.008 |
tricks | -0.008 |
RO | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
dives | +0.056 |
eway | +0.051 |
tricks | +0.049 |
films | +0.048 |
mer | +0.048 |
Neg logit contributions | |
Em | -0.040 |
ama | -0.040 |
Gem | -0.039 |
checkout | -0.038 |
Johnson | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
dives | +0.042 |
tricks | +0.037 |
eway | +0.037 |
dances | +0.035 |
jokes | +0.034 |
Neg logit contributions | |
ama | -0.041 |
Gem | -0.041 |
Em | -0.041 |
checkout | -0.040 |
groceries | -0.040 |
Token | fake |
Token ID | 8390 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
dives | +0.018 |
tricks | +0.016 |
films | +0.016 |
eway | +0.016 |
mer | +0.015 |
Neg logit contributions | |
ama | -0.017 |
Em | -0.017 |
Gem | -0.017 |
checkout | -0.017 |
mm | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
dives | +0.027 |
eway | +0.025 |
RO | +0.024 |
mer | +0.024 |
films | +0.024 |
Neg logit contributions | |
Em | -0.014 |
ama | -0.014 |
groceries | -0.014 |
Gem | -0.014 |
Johnson | -0.014 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
dives | +0.037 |
eway | +0.034 |
films | +0.033 |
tricks | +0.032 |
mer | +0.032 |
Neg logit contributions | |
ama | -0.023 |
Em | -0.023 |
Gem | -0.023 |
groceries | -0.022 |
Johnson | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
dives | +0.006 |
eway | +0.005 |
tricks | +0.005 |
mer | +0.005 |
dances | +0.005 |
Neg logit contributions | |
ama | -0.004 |
Em | -0.004 |
Gem | -0.004 |
groceries | -0.004 |
Johnson | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
films | +0.023 |
dives | +0.023 |
eway | +0.023 |
villains | +0.022 |
aids | +0.021 |
Neg logit contributions | |
already | -0.009 |
Em | -0.009 |
still | -0.009 |
first | -0.009 |
expensive | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Em | +0.008 |
ama | +0.008 |
Gem | +0.008 |
groceries | +0.007 |
Johnson | +0.007 |
Neg logit contributions | |
dives | -0.016 |
eway | -0.015 |
tricks | -0.014 |
films | -0.014 |
mer | -0.014 |
Token | best |
Token ID | 1266 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Em | +0.014 |
ama | +0.013 |
Gem | +0.013 |
Johnson | +0.012 |
groceries | +0.012 |
Neg logit contributions | |
dives | -0.054 |
eway | -0.050 |
tricks | -0.049 |
mer | -0.049 |
films | -0.049 |
Token | day |
Token ID | 1110 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
expensive | +0.002 |
ama | +0.002 |
grandma | +0.002 |
Gem | +0.002 |
groceries | +0.002 |
Neg logit contributions | |
RO | -0.005 |
igators | -0.005 |
dives | -0.005 |
films | -0.005 |
aids | -0.005 |
Token | ever |
Token ID | 1683 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
dives | +0.019 |
eway | +0.018 |
films | +0.018 |
tricks | +0.018 |
poses | +0.017 |
Neg logit contributions | |
Gem | -0.009 |
ama | -0.009 |
Em | -0.009 |
already | -0.008 |
Johnson | -0.008 |
Token | ! |
Token ID | 0 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
dives | +0.040 |
eway | +0.038 |
films | +0.037 |
tricks | +0.037 |
villains | +0.036 |
Neg logit contributions | |
Em | -0.015 |
ama | -0.015 |
Gem | -0.014 |
Johnson | -0.014 |
expensive | -0.013 |
Token | |
Token ID | 220 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
dives | +0.039 |
eway | +0.036 |
tricks | +0.035 |
films | +0.035 |
mer | +0.035 |
Neg logit contributions | |
Em | -0.020 |
ama | -0.020 |
Gem | -0.019 |
groceries | -0.018 |
Johnson | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
Em | +0.036 |
ama | +0.036 |
Gem | +0.035 |
Johnson | +0.034 |
groceries | +0.033 |
Neg logit contributions | |
dives | -0.071 |
eway | -0.065 |
tricks | -0.063 |
films | -0.063 |
mer | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
dives | +0.016 |
eway | +0.014 |
films | +0.014 |
mer | +0.014 |
tricks | +0.014 |
Neg logit contributions | |
ama | -0.009 |
Em | -0.009 |
Gem | -0.009 |
Johnson | -0.009 |
groceries | -0.008 |
Token | When |
Token ID | 2215 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
dives | +0.001 |
films | +0.001 |
dances | +0.001 |
mer | +0.001 |
tricks | +0.001 |
Neg logit contributions | |
ama | -0.001 |
Em | -0.001 |
Gem | -0.001 |
Johnson | -0.001 |
checkout | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
dives | +0.018 |
eway | +0.017 |
tricks | +0.016 |
films | +0.016 |
mer | +0.016 |
Neg logit contributions | |
Em | -0.014 |
ama | -0.014 |
Gem | -0.013 |
Johnson | -0.013 |
groceries | -0.013 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Em | +0.017 |
ama | +0.016 |
Gem | +0.016 |
checkout | +0.016 |
groceries | +0.016 |
Neg logit contributions | |
dives | -0.033 |
eway | -0.030 |
tricks | -0.029 |
films | -0.029 |
mer | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ama | +0.028 |
Em | +0.027 |
infected | +0.026 |
checkout | +0.026 |
groceries | +0.026 |
Neg logit contributions | |
dives | -0.039 |
films | -0.037 |
mer | -0.036 |
eway | -0.036 |
tricks | -0.036 |
Token | But |
Token ID | 887 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
ama | +0.019 |
Em | +0.018 |
infected | +0.018 |
groceries | +0.018 |
Gem | +0.017 |
Neg logit contributions | |
dives | -0.040 |
eway | -0.036 |
films | -0.035 |
dances | -0.035 |
mer | -0.035 |
Token | when |
Token ID | 618 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ama | +0.013 |
Em | +0.013 |
infected | +0.013 |
groceries | +0.013 |
ongo | +0.013 |
Neg logit contributions | |
dives | -0.016 |
mer | -0.015 |
eway | -0.015 |
Fly | -0.015 |
films | -0.014 |
Token | she |
Token ID | 673 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ama | +0.004 |
Em | +0.004 |
Gem | +0.004 |
groceries | +0.004 |
infected | +0.004 |
Neg logit contributions | |
dives | -0.007 |
mer | -0.007 |
eway | -0.007 |
Fly | -0.007 |
dances | -0.006 |
Token | went |
Token ID | 1816 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Em | +0.021 |
ama | +0.021 |
Gem | +0.020 |
checkout | +0.020 |
Johnson | +0.019 |
Neg logit contributions | |
dives | -0.029 |
eway | -0.027 |
films | -0.026 |
tricks | -0.026 |
villains | -0.025 |
Token | back |
Token ID | 736 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
ama | +0.019 |
groceries | +0.019 |
Em | +0.019 |
Johnson | +0.019 |
Gem | +0.018 |
Neg logit contributions | |
dives | -0.032 |
eway | -0.030 |
RO | -0.029 |
films | -0.029 |
villains | -0.029 |
Token | inside |
Token ID | 2641 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
dives | +0.017 |
eway | +0.015 |
mer | +0.014 |
tricks | +0.014 |
films | +0.014 |
Neg logit contributions | |
Em | -0.014 |
ama | -0.013 |
Gem | -0.013 |
checkout | -0.013 |
infected | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
infected | +0.027 |
Em | +0.027 |
ama | +0.027 |
checkout | +0.027 |
groceries | +0.026 |
Neg logit contributions | |
dives | -0.039 |
eway | -0.034 |
mer | -0.034 |
dances | -0.033 |
Fly | -0.033 |
Token | get |
Token ID | 651 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ama | +0.035 |
Em | +0.034 |
Johnson | +0.033 |
Gem | +0.033 |
groceries | +0.033 |
Neg logit contributions | |
dives | -0.050 |
eway | -0.044 |
mer | -0.044 |
dances | -0.043 |
tricks | -0.043 |
Token | her |
Token ID | 607 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
ama | +0.028 |
Johnson | +0.028 |
ongo | +0.027 |
mm | +0.027 |
checkout | +0.027 |
Neg logit contributions | |
dives | -0.030 |
mer | -0.027 |
dances | -0.025 |
Fly | -0.024 |
ull | -0.024 |
Token | put |
Token ID | 1234 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
dives | +0.009 |
eway | +0.008 |
films | +0.008 |
tricks | +0.008 |
mer | +0.007 |
Neg logit contributions | |
Em | -0.006 |
ama | -0.006 |
Gem | -0.006 |
groceries | -0.006 |
checkout | -0.006 |
Token | them |
Token ID | 606 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
dives | +0.004 |
eway | +0.003 |
tricks | +0.003 |
films | +0.003 |
mer | +0.003 |
Neg logit contributions | |
Em | -0.005 |
ama | -0.005 |
Gem | -0.004 |
groceries | -0.004 |
Johnson | -0.004 |
Token | on |
Token ID | 319 |
Feature activation | +6.89e-02 |
Pos logit contributions | |
dives | +0.000 |
eway | +0.000 |
films | +0.000 |
RO | +0.000 |
tricks | +0.000 |
Neg logit contributions | |
Em | -0.000 |
Gem | -0.000 |
groceries | -0.000 |
ama | -0.000 |
expensive | -0.000 |
Token | her |
Token ID | 607 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
dives | +0.002 |
eway | +0.002 |
tricks | +0.002 |
films | +0.002 |
mer | +0.002 |
Neg logit contributions | |
ama | -0.002 |
infected | -0.002 |
mm | -0.001 |
ongo | -0.001 |
Johnson | -0.001 |
Token | desk |
Token ID | 6915 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
dives | +0.001 |
tricks | +0.001 |
eway | +0.001 |
films | +0.001 |
mer | +0.001 |
Neg logit contributions | |
Em | -0.001 |
ama | -0.001 |
Gem | -0.001 |
Johnson | -0.001 |
infected | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
ama | +0.030 |
Em | +0.030 |
Gem | +0.029 |
Johnson | +0.029 |
groceries | +0.028 |
Neg logit contributions | |
dives | -0.044 |
eway | -0.040 |
tricks | -0.039 |
films | -0.038 |
mer | -0.038 |
Token | She |
Token ID | 1375 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
dives | +0.011 |
eway | +0.010 |
Fly | +0.010 |
dances | +0.010 |
films | +0.010 |
Neg logit contributions | |
expensive | -0.008 |
groceries | -0.007 |
infected | -0.007 |
checkout | -0.007 |
severe | -0.007 |
Token | named |
Token ID | 3706 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
dives | +0.009 |
eway | +0.008 |
tricks | +0.008 |
films | +0.008 |
mer | +0.007 |
Neg logit contributions | |
Em | -0.007 |
ama | -0.006 |
Gem | -0.006 |
Johnson | -0.006 |
groceries | -0.006 |
Token | each |
Token ID | 1123 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
Em | +0.038 |
Gem | +0.035 |
groceries | +0.034 |
ama | +0.033 |
Johnson | +0.033 |
Neg logit contributions | |
dives | -0.069 |
eway | -0.063 |
mer | -0.060 |
RO | -0.060 |
tricks | -0.059 |
Token | color |
Token ID | 3124 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
dives | +0.010 |
eway | +0.009 |
tricks | +0.009 |
films | +0.009 |
mer | +0.009 |
Neg logit contributions | |
Em | -0.008 |
ama | -0.008 |
Gem | -0.007 |
Johnson | -0.007 |
groceries | -0.007 |
Token | out |
Token ID | 503 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Em | +0.002 |
ama | +0.002 |
Gem | +0.002 |
groceries | +0.002 |
Johnson | +0.002 |
Neg logit contributions | |
dives | -0.004 |
eway | -0.004 |
films | -0.003 |
RO | -0.003 |
mer | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Em | +0.001 |
Gem | +0.001 |
ama | +0.001 |
checkout | +0.000 |
Johnson | +0.000 |
Neg logit contributions | |
dives | -0.001 |
eway | -0.001 |
films | -0.001 |
tricks | -0.001 |
mer | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
Em | +0.002 |
ama | +0.002 |
Gem | +0.002 |
Johnson | +0.002 |
groceries | +0.002 |
Neg logit contributions | |
dives | -0.005 |
eway | -0.004 |
films | -0.004 |
tricks | -0.004 |
RO | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
dives | +0.018 |
eway | +0.016 |
mer | +0.016 |
tricks | +0.016 |
films | +0.015 |
Neg logit contributions | |
ama | -0.021 |
Em | -0.021 |
groceries | -0.020 |
Gem | -0.020 |
checkout | -0.020 |
Token | I |
Token ID | 40 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
ama | +0.021 |
groceries | +0.020 |
Em | +0.020 |
Gem | +0.020 |
expensive | +0.019 |
Neg logit contributions | |
dives | -0.035 |
eway | -0.032 |
RO | -0.031 |
mer | -0.031 |
Fly | -0.031 |
Token | want |
Token ID | 765 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
dives | +0.025 |
mer | +0.022 |
eway | +0.022 |
hops | +0.022 |
tricks | +0.021 |
Neg logit contributions | |
Em | -0.014 |
Gem | -0.014 |
ama | -0.014 |
groceries | -0.014 |
checkout | -0.014 |
Token | something |
Token ID | 1223 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
dives | +0.029 |
tricks | +0.025 |
eway | +0.025 |
mer | +0.024 |
films | +0.024 |
Neg logit contributions | |
Em | -0.026 |
ama | -0.026 |
Gem | -0.025 |
checkout | -0.024 |
Johnson | -0.024 |
Token | else |
Token ID | 2073 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
dives | +0.018 |
eway | +0.017 |
films | +0.016 |
tricks | +0.016 |
mer | +0.016 |
Neg logit contributions | |
Em | -0.013 |
ama | -0.013 |
Gem | -0.012 |
groceries | -0.012 |
Johnson | -0.012 |
Token | that |
Token ID | 326 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
dives | +0.023 |
eway | +0.021 |
tricks | +0.020 |
films | +0.020 |
mer | +0.020 |
Neg logit contributions | |
Em | -0.016 |
ama | -0.016 |
Gem | -0.016 |
Johnson | -0.015 |
groceries | -0.015 |
Token | 's |
Token ID | 338 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
expensive | +0.015 |
Em | +0.014 |
first | +0.014 |
ama | +0.014 |
groceries | +0.014 |
Neg logit contributions | |
eway | -0.028 |
dives | -0.027 |
films | -0.027 |
villains | -0.026 |
mer | -0.026 |
Token | delicious |
Token ID | 12625 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Em | +0.015 |
ama | +0.014 |
Gem | +0.014 |
Johnson | +0.014 |
groceries | +0.014 |
Neg logit contributions | |
dives | -0.031 |
eway | -0.028 |
tricks | -0.027 |
films | -0.027 |
mer | -0.027 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
dives | +0.025 |
eway | +0.024 |
RO | +0.024 |
films | +0.024 |
villains | +0.024 |
Neg logit contributions | |
Johnson | -0.008 |
groceries | -0.008 |
ama | -0.008 |
Em | -0.007 |
Gem | -0.007 |
Token | Pam |
Token ID | 24497 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ama | +0.025 |
Em | +0.025 |
Gem | +0.024 |
groceries | +0.023 |
checkout | +0.023 |
Neg logit contributions | |
dives | -0.041 |
eway | -0.037 |
tricks | -0.036 |
films | -0.036 |
mer | -0.036 |
Token | says |
Token ID | 1139 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
dives | +0.026 |
eway | +0.024 |
films | +0.022 |
mer | +0.022 |
tricks | +0.022 |
Neg logit contributions | |
Em | -0.028 |
ama | -0.027 |
Gem | -0.027 |
Johnson | -0.026 |
groceries | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
dives | +0.032 |
eway | +0.030 |
RO | +0.029 |
films | +0.029 |
igators | +0.029 |
Neg logit contributions | |
ama | -0.012 |
Em | -0.012 |
Gem | -0.010 |
Johnson | -0.010 |
infected | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
dives | +0.048 |
eway | +0.044 |
tricks | +0.044 |
films | +0.043 |
igators | +0.042 |
Neg logit contributions | |
Em | -0.018 |
ama | -0.017 |
Gem | -0.017 |
Johnson | -0.017 |
groceries | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
Em | +0.002 |
checkout | +0.002 |
groceries | +0.002 |
Gem | +0.002 |
ama | +0.002 |
Neg logit contributions | |
dives | -0.002 |
eway | -0.002 |
Fly | -0.002 |
tricks | -0.002 |
films | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Em | +0.008 |
ama | +0.008 |
Gem | +0.008 |
Johnson | +0.008 |
groceries | +0.008 |
Neg logit contributions | |
dives | -0.014 |
eway | -0.012 |
tricks | -0.012 |
films | -0.012 |
mer | -0.012 |
Token | Rot |
Token ID | 24864 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
ama | +0.020 |
Em | +0.020 |
Gem | +0.019 |
groceries | +0.019 |
Johnson | +0.018 |
Neg logit contributions | |
dives | -0.030 |
eway | -0.027 |
tricks | -0.027 |
mer | -0.027 |
films | -0.026 |
Token | ? |
Token ID | 30 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Em | +0.018 |
ama | +0.018 |
checkout | +0.018 |
Gem | +0.018 |
Johnson | +0.017 |
Neg logit contributions | |
dives | -0.015 |
tricks | -0.014 |
eway | -0.014 |
ile | -0.013 |
films | -0.013 |
Token | What |
Token ID | 1867 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
dives | +0.003 |
Fly | +0.003 |
films | +0.003 |
RO | +0.003 |
eway | +0.003 |
Neg logit contributions | |
groceries | -0.004 |
checkout | -0.004 |
bur | -0.003 |
severe | -0.003 |
ama | -0.003 |
Token | is |
Token ID | 318 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
dives | +0.069 |
eway | +0.061 |
tricks | +0.060 |
films | +0.059 |
mer | +0.058 |
Neg logit contributions | |
Em | -0.054 |
ama | -0.054 |
Gem | -0.053 |
checkout | -0.052 |
Johnson | -0.051 |
Token | rot |
Token ID | 5724 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ama | +0.039 |
Em | +0.039 |
Gem | +0.038 |
Johnson | +0.037 |
checkout | +0.037 |
Neg logit contributions | |
dives | -0.058 |
eway | -0.052 |
tricks | -0.051 |
films | -0.050 |
mer | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Em | +0.012 |
ama | +0.012 |
Gem | +0.012 |
Johnson | +0.011 |
groceries | +0.011 |
Neg logit contributions | |
dives | -0.018 |
eway | -0.017 |
films | -0.016 |
mer | -0.016 |
tricks | -0.016 |
Token | slides |
Token ID | 19392 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
eway | +0.011 |
ull | +0.011 |
ile | +0.011 |
villains | +0.010 |
ag | +0.010 |
Neg logit contributions | |
first | -0.007 |
Em | -0.007 |
Grand | -0.007 |
grandma | -0.007 |
tired | -0.007 |
Token | down |
Token ID | 866 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
dives | +0.016 |
eway | +0.015 |
films | +0.015 |
villains | +0.015 |
mer | +0.014 |
Neg logit contributions | |
Em | -0.010 |
Gem | -0.010 |
Johnson | -0.010 |
groceries | -0.010 |
ama | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
dives | +0.010 |
eway | +0.010 |
films | +0.009 |
tricks | +0.009 |
dances | +0.009 |
Neg logit contributions | |
Em | -0.006 |
Johnson | -0.006 |
Gem | -0.006 |
ama | -0.006 |
checkout | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
dives | +0.002 |
eway | +0.002 |
mer | +0.002 |
films | +0.002 |
tricks | +0.002 |
Neg logit contributions | |
Em | -0.001 |
ama | -0.001 |
Gem | -0.001 |
Johnson | -0.001 |
checkout | -0.001 |
Token | Y |
Token ID | 56 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
Em | +0.007 |
Gem | +0.006 |
checkout | +0.006 |
Johnson | +0.006 |
ama | +0.006 |
Neg logit contributions | |
dives | -0.011 |
eway | -0.010 |
films | -0.010 |
tricks | -0.010 |
mer | -0.010 |
Token | ay |
Token ID | 323 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Em | +0.059 |
Gem | +0.059 |
severe | +0.058 |
groceries | +0.058 |
infected | +0.058 |
Neg logit contributions | |
dives | -0.076 |
eway | -0.066 |
ived | -0.064 |
tricks | -0.064 |
RO | -0.063 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
dives | +0.077 |
eway | +0.072 |
films | +0.069 |
mer | +0.069 |
tricks | +0.069 |
Neg logit contributions | |
ama | -0.032 |
Em | -0.032 |
Gem | -0.030 |
Johnson | -0.029 |
groceries | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Em | +0.012 |
ama | +0.012 |
Gem | +0.012 |
groceries | +0.012 |
Johnson | +0.012 |
Neg logit contributions | |
dives | -0.024 |
eway | -0.023 |
mer | -0.022 |
films | -0.022 |
igators | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
dives | +0.005 |
eway | +0.005 |
tricks | +0.004 |
films | +0.004 |
mer | +0.004 |
Neg logit contributions | |
Em | -0.003 |
ama | -0.003 |
Gem | -0.003 |
groceries | -0.003 |
checkout | -0.003 |
Token | They |
Token ID | 2990 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
ama | +0.010 |
Em | +0.010 |
Gem | +0.009 |
checkout | +0.009 |
Johnson | +0.009 |
Neg logit contributions | |
dives | -0.014 |
eway | -0.013 |
films | -0.013 |
tricks | -0.012 |
mer | -0.012 |
Token | my |
Token ID | 1820 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Em | +0.028 |
ama | +0.028 |
mm | +0.027 |
groceries | +0.027 |
Gem | +0.027 |
Neg logit contributions | |
dives | -0.072 |
mer | -0.069 |
ull | -0.067 |
films | -0.066 |
swim | -0.065 |
Token | decided |
Token ID | 3066 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
ama | +0.037 |
Em | +0.037 |
groceries | +0.036 |
Gem | +0.035 |
expensive | +0.035 |
Neg logit contributions | |
dives | -0.032 |
mer | -0.029 |
films | -0.027 |
swim | -0.026 |
eway | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
ama | +0.055 |
Em | +0.054 |
Gem | +0.053 |
Johnson | +0.052 |
checkout | +0.051 |
Neg logit contributions | |
dives | -0.059 |
eway | -0.053 |
tricks | -0.051 |
mer | -0.050 |
films | -0.050 |
Token | cook |
Token ID | 4255 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
dives | +0.024 |
eway | +0.022 |
tricks | +0.021 |
mer | +0.021 |
films | +0.021 |
Neg logit contributions | |
Em | -0.019 |
ama | -0.019 |
Gem | -0.018 |
Johnson | -0.018 |
groceries | -0.018 |
Token | something |
Token ID | 1223 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
groceries | +0.012 |
ama | +0.011 |
Em | +0.011 |
Gem | +0.011 |
checkout | +0.011 |
Neg logit contributions | |
dives | -0.023 |
eway | -0.022 |
villains | -0.021 |
RO | -0.021 |
mer | -0.021 |
Token | y |
Token ID | 331 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
dives | +0.008 |
eway | +0.007 |
villains | +0.007 |
RO | +0.007 |
Fly | +0.007 |
Neg logit contributions | |
expensive | -0.004 |
Em | -0.004 |
groceries | -0.004 |
ama | -0.004 |
Gem | -0.004 |
Token | ummy |
Token ID | 13513 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
Em | +0.029 |
Gem | +0.025 |
infected | +0.024 |
Johnson | +0.024 |
checkout | +0.023 |
Neg logit contributions | |
dives | -0.108 |
eway | -0.099 |
films | -0.097 |
tricks | -0.097 |
mer | -0.096 |
Token | to |
Token ID | 284 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
dives | +0.023 |
eway | +0.022 |
RO | +0.022 |
villains | +0.021 |
Fly | +0.021 |
Neg logit contributions | |
groceries | -0.012 |
Gem | -0.011 |
expensive | -0.011 |
Em | -0.011 |
ama | -0.010 |
Token | eat |
Token ID | 4483 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ama | +0.025 |
Em | +0.024 |
Gem | +0.023 |
Johnson | +0.023 |
infected | +0.022 |
Neg logit contributions | |
dives | -0.027 |
tricks | -0.024 |
films | -0.023 |
eway | -0.023 |
mer | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
Em | +0.025 |
ama | +0.025 |
Gem | +0.024 |
Johnson | +0.023 |
checkout | +0.023 |
Neg logit contributions | |
dives | -0.039 |
eway | -0.035 |
tricks | -0.034 |
films | -0.034 |
mer | -0.034 |
Token | They |
Token ID | 1119 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
ama | +0.002 |
Em | +0.002 |
Gem | +0.002 |
groceries | +0.002 |
infected | +0.002 |
Neg logit contributions | |
dives | -0.003 |
eway | -0.002 |
films | -0.002 |
tricks | -0.002 |
dances | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
dives | +0.007 |
eway | +0.006 |
tricks | +0.006 |
films | +0.006 |
mer | +0.006 |
Neg logit contributions | |
Em | -0.005 |
ama | -0.005 |
Gem | -0.005 |
Johnson | -0.005 |
groceries | -0.005 |
Token | blew |
Token ID | 17948 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
dives | +0.014 |
eway | +0.014 |
films | +0.014 |
tricks | +0.013 |
villains | +0.013 |
Neg logit contributions | |
Em | -0.009 |
ama | -0.009 |
Gem | -0.009 |
checkout | -0.009 |
expensive | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Em | +0.001 |
Gem | +0.001 |
groceries | +0.001 |
expensive | +0.001 |
infected | +0.001 |
Neg logit contributions | |
dives | -0.002 |
eway | -0.002 |
villains | -0.002 |
films | -0.002 |
RO | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
dives | +0.033 |
eway | +0.031 |
films | +0.029 |
mer | +0.029 |
RO | +0.029 |
Neg logit contributions | |
Em | -0.019 |
Gem | -0.018 |
groceries | -0.018 |
ama | -0.018 |
checkout | -0.018 |
Token | sticks |
Token ID | 16461 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
dives | +0.017 |
tricks | +0.015 |
eway | +0.014 |
mer | +0.014 |
films | +0.014 |
Neg logit contributions | |
ama | -0.017 |
Em | -0.016 |
Gem | -0.016 |
Johnson | -0.016 |
checkout | -0.015 |
Token | until |
Token ID | 1566 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Em | +0.000 |
ama | +0.000 |
Gem | +0.000 |
Johnson | +0.000 |
groceries | +0.000 |
Neg logit contributions | |
dives | -0.001 |
eway | -0.001 |
films | -0.001 |
RO | -0.001 |
villains | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Em | +0.043 |
Gem | +0.042 |
ama | +0.041 |
groceries | +0.041 |
checkout | +0.040 |
Neg logit contributions | |
dives | -0.067 |
eway | -0.064 |
films | -0.061 |
tricks | -0.061 |
dances | -0.059 |
Token | sun |
Token ID | 4252 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
Em | +0.006 |
ama | +0.006 |
Gem | +0.006 |
groceries | +0.006 |
Johnson | +0.006 |
Neg logit contributions | |
dives | -0.008 |
eway | -0.007 |
films | -0.007 |
tricks | -0.007 |
mer | -0.007 |
Token | got |
Token ID | 1392 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
dives | +0.003 |
eway | +0.002 |
films | +0.002 |
villains | +0.002 |
tricks | +0.002 |
Neg logit contributions | |
Em | -0.002 |
ama | -0.002 |
Gem | -0.002 |
Johnson | -0.001 |
checkout | -0.001 |
Token | hot |
Token ID | 3024 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
ama | +0.090 |
mm | +0.082 |
Em | +0.082 |
Gem | +0.080 |
checkout | +0.078 |
Neg logit contributions | |
dives | -0.095 |
mer | -0.087 |
ull | -0.082 |
eway | -0.081 |
RO | -0.080 |
Token | and |
Token ID | 290 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
Em | +0.012 |
ama | +0.011 |
Gem | +0.011 |
groceries | +0.011 |
Johnson | +0.011 |
Neg logit contributions | |
dives | -0.018 |
eway | -0.017 |
tricks | -0.016 |
films | -0.016 |
mer | -0.016 |
Token | might |
Token ID | 1244 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Em | +0.000 |
ama | +0.000 |
Gem | +0.000 |
Johnson | +0.000 |
groceries | +0.000 |
Neg logit contributions | |
dives | -0.001 |
eway | -0.001 |
tricks | -0.000 |
mer | -0.000 |
dances | -0.000 |
Token | find |
Token ID | 1064 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Em | +0.019 |
Gem | +0.019 |
ama | +0.019 |
expensive | +0.018 |
Johnson | +0.018 |
Neg logit contributions | |
dives | -0.036 |
eway | -0.033 |
films | -0.033 |
mer | -0.032 |
tricks | -0.032 |
Token | next |
Token ID | 1306 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
ama | +0.026 |
Em | +0.026 |
Gem | +0.025 |
checkout | +0.025 |
Johnson | +0.024 |
Neg logit contributions | |
dives | -0.038 |
eway | -0.035 |
tricks | -0.034 |
mer | -0.033 |
films | -0.033 |
Token | ? |
Token ID | 30 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Em | +0.007 |
ama | +0.007 |
Gem | +0.006 |
checkout | +0.006 |
groceries | +0.006 |
Neg logit contributions | |
dives | -0.010 |
eway | -0.009 |
tricks | -0.008 |
mer | -0.008 |
films | -0.008 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
dives | +0.008 |
eway | +0.008 |
Fly | +0.007 |
RO | +0.007 |
mer | +0.007 |
Neg logit contributions | |
groceries | -0.006 |
expensive | -0.005 |
checkout | -0.005 |
ama | -0.005 |
infected | -0.005 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
dives | +0.007 |
eway | +0.007 |
tricks | +0.007 |
films | +0.007 |
mer | +0.007 |
Neg logit contributions | |
Em | -0.004 |
ama | -0.004 |
Gem | -0.004 |
Johnson | -0.004 |
groceries | -0.004 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
checkout | +0.054 |
groceries | +0.051 |
Em | +0.050 |
infected | +0.049 |
Gem | +0.049 |
Neg logit contributions | |
dives | -0.069 |
eway | -0.064 |
dances | -0.058 |
ull | -0.058 |
Fly | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
dives | +0.037 |
eway | +0.034 |
films | +0.033 |
tricks | +0.033 |
mer | +0.033 |
Neg logit contributions | |
Em | -0.017 |
ama | -0.016 |
Gem | -0.016 |
groceries | -0.015 |
Johnson | -0.015 |
Token | time |
Token ID | 640 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
dives | +0.016 |
eway | +0.015 |
mer | +0.014 |
tricks | +0.014 |
films | +0.014 |
Neg logit contributions | |
ama | -0.013 |
Em | -0.012 |
expensive | -0.012 |
Johnson | -0.012 |
Gem | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Em | +0.008 |
ama | +0.008 |
Gem | +0.008 |
Johnson | +0.008 |
groceries | +0.007 |
Neg logit contributions | |
dives | -0.020 |
eway | -0.019 |
films | -0.018 |
tricks | -0.018 |
mer | -0.018 |
Token | there |
Token ID | 612 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Em | +0.031 |
ama | +0.030 |
Gem | +0.029 |
Johnson | +0.029 |
expensive | +0.027 |
Neg logit contributions | |
dives | -0.056 |
eway | -0.051 |
tricks | -0.050 |
films | -0.050 |
mer | -0.049 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ama | +0.026 |
Em | +0.026 |
Gem | +0.025 |
checkout | +0.025 |
groceries | +0.025 |
Neg logit contributions | |
dives | -0.042 |
eway | -0.038 |
tricks | -0.036 |
films | -0.036 |
mer | -0.036 |
Token | were |
Token ID | 547 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ama | +0.029 |
Em | +0.027 |
groceries | +0.027 |
Gem | +0.027 |
Johnson | +0.026 |
Neg logit contributions | |
dives | -0.034 |
mer | -0.029 |
dances | -0.029 |
RO | -0.028 |
eway | -0.028 |
Token | playing |
Token ID | 2712 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
Em | +0.021 |
ama | +0.020 |
Gem | +0.020 |
Johnson | +0.019 |
groceries | +0.019 |
Neg logit contributions | |
dives | -0.050 |
eway | -0.046 |
films | -0.045 |
tricks | -0.044 |
mer | -0.044 |
Token | with |
Token ID | 351 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
anne | +0.030 |
aids | +0.029 |
eway | +0.028 |
igators | +0.028 |
dives | +0.028 |
Neg logit contributions | |
first | -0.011 |
top | -0.010 |
two | -0.010 |
still | -0.009 |
all | -0.009 |
Token | their |
Token ID | 511 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Em | +0.033 |
groceries | +0.032 |
Gem | +0.032 |
expensive | +0.031 |
Johnson | +0.031 |
Neg logit contributions | |
dives | -0.037 |
eway | -0.034 |
RO | -0.031 |
tricks | -0.030 |
villains | -0.030 |
Token | toys |
Token ID | 14958 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
groceries | +0.023 |
ama | +0.022 |
expensive | +0.022 |
Em | +0.022 |
Johnson | +0.021 |
Neg logit contributions | |
dives | -0.045 |
eway | -0.043 |
RO | -0.040 |
mer | -0.040 |
Fly | -0.039 |
Token | in |
Token ID | 287 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Em | +0.052 |
ama | +0.051 |
Gem | +0.050 |
groceries | +0.049 |
Johnson | +0.049 |
Neg logit contributions | |
dives | -0.076 |
eway | -0.069 |
tricks | -0.065 |
films | -0.065 |
mer | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Em | +0.025 |
ama | +0.024 |
Gem | +0.024 |
Johnson | +0.023 |
groceries | +0.023 |
Neg logit contributions | |
dives | -0.038 |
eway | -0.034 |
tricks | -0.033 |
mer | -0.033 |
films | -0.033 |
Token | garden |
Token ID | 11376 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
groceries | +0.019 |
checkout | +0.019 |
Gem | +0.019 |
Em | +0.019 |
expensive | +0.019 |
Neg logit contributions | |
dives | -0.038 |
eway | -0.037 |
RO | -0.034 |
tricks | -0.034 |
villains | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Em | +0.046 |
ama | +0.046 |
Gem | +0.045 |
Johnson | +0.043 |
groceries | +0.043 |
Neg logit contributions | |
dives | -0.079 |
eway | -0.072 |
tricks | -0.069 |
films | -0.069 |
mer | -0.068 |
Token | Lily |
Token ID | 20037 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
Em | +0.003 |
Gem | +0.003 |
checkout | +0.003 |
Johnson | +0.003 |
ama | +0.003 |
Neg logit contributions | |
dives | -0.005 |
eway | -0.004 |
tricks | -0.004 |
mer | -0.004 |
villains | -0.004 |