TOP ACTIVATIONS
MAX = 0.496

helpful , bright girl named Pen elope . One day ,
bedroom . The next day Pen elope went outside to pick
flowers in her garden , Pen elope heard a whisper coming
Once home , Pen elope tucked the cloth bird
her mom and dad , Pen elope was able to fix
. Now Pen elope 's special lamp works
a very long time . Pen elope was always thankful for
was a little girl named Pen elope . She loved to
That 's so cool , Pen elope ! I think that
at this weird owl !" Pen elope 's mom came over
. One day , when Pen elope was exploring , she
" Hello !" said Pen elope in a cautious voice
a kind of answer . Pen elope knew there must be
fuss was about . When Pen elope 's mom looked at
home . So Pen elope and her mom started
special pink lamp that makes Pen elope feel so lucky .
the bird began to tell Pen elope it 's story .
was a little girl named Pen elope who was 3 years
safe place to stay . Pen elope was so moved by
the owl flew away and Pen elope and her mom never

MIN ACTIVATIONS
MIN = -0.388

too . He knew that accidents happen sometimes .
But he also learned that accidents can happen and it 's
, but she knew that accidents happen . She told Lily
" It 's OK , accidents happen . We all make
lot . She learned that accidents can happen , but it
Tim my learned that sometimes accidents happen , and we can
the truth . She says accidents happen and they can fix
said it was okay , accidents happen . They cleaned up
this time she understood that accidents can happen and sometimes things
She also learned that sometimes accidents happen and it 's okay
€ ™ s ok , accidents happen . Let â €
her and told her that accidents happen , but it 's
" It 's alright , accidents happen . Let 's get
it was okay and that accidents happen . They cleaned up
need it , and that accidents happen . Ho pper learned
with the chores can prevent accidents and save things we love
house and told her that accidents happen . Lily felt better
that it was okay and accidents happen to everyone .
mistakes . We all have accidents sometimes ." Lily felt better
sad but she knew that accidents happen sometimes . She cleaned

INTERVAL 0.275 - 0.496
CONTAINS 0.137%

After meals , Annie would take the car outside
Her mom my said yes , and she went up
y ummy meal . Little May smiled and thanked them for
girl who loved pink . Everywhere she went she looked for
his mom 's phone , keys , compact and lipstick all

INTERVAL 0.054 - 0.275
CONTAINS 18.317%

her gear in hand , Jessie walked towards it until she
lesson . She said they should always respect and share their
Dad ." " If we all come together ,"
uffy was not sure at first , but she decided to
not good for your hair ." Anna nodded and

INTERVAL -0.167 - 0.054
CONTAINS 79.294%

Everyone was very surprised ! <|endoftext|> The sun was high in
With the smooth pieces of cel ery , she printed a
ily and Tom were best friends . They liked to play
". Spot w agged his tail and bark ed happily when
for a long time and wanted to rest for a bit

INTERVAL -0.388 - -0.167
CONTAINS 2.252%

After they were finished playing , Tim my felt guilty
that they had found out more about the world , thanks
. She was shrinking very quickly and soon she
" Me !" Sam says . " L ion
They were happy . The end . <|endoftext|> L ila was
Token helpful
Token ID7613
Feature activation-1.14e-01

Pos logit contributions
 accidents+0.008
ead+0.007
Time+0.007
aping+0.007
ounds+0.007
Neg logit contributions
 Pen-0.008
nes-0.007
igator-0.007
Pen-0.007
den-0.006
Token,
Token ID11
Feature activation+9.38e-04

Pos logit contributions
 accidents+0.153
ead+0.145
Time+0.144
 working+0.143
 End+0.138
Neg logit contributions
nes-0.200
 Pen-0.198
den-0.184
nam-0.184
Pen-0.180
Token bright
Token ID6016
Feature activation-6.85e-02

Pos logit contributions
 Pen+0.002
igator+0.002
nes+0.001
nam+0.001
Pen+0.001
Neg logit contributions
 accidents-0.001
ead-0.001
Time-0.001
aping-0.001
ucking-0.001
Token girl
Token ID2576
Feature activation+1.91e-02

Pos logit contributions
 accidents+0.092
Time+0.086
ead+0.085
 working+0.082
 End+0.081
Neg logit contributions
 Pen-0.125
nes-0.120
den-0.114
igator-0.113
Pen-0.112
Token named
Token ID3706
Feature activation+7.26e-02

Pos logit contributions
 Pen+0.031
nes+0.029
igator+0.028
den+0.028
Pen+0.027
Neg logit contributions
 accidents-0.029
Time-0.028
ead-0.028
 working-0.027
 End-0.026
Token Pen
Token ID7507
Feature activation+4.96e-01

Pos logit contributions
 Pen+0.136
nes+0.128
igator+0.123
den+0.121
Pen+0.120
Neg logit contributions
 accidents-0.097
Time-0.091
ead-0.089
 working-0.086
aping-0.085
Tokenelope
Token ID47329
Feature activation+1.27e-01

Pos logit contributions
igator+0.862
nam+0.838
nes+0.821
 Pen+0.809
 tant+0.804
Neg logit contributions
Time-0.650
 End-0.632
 working-0.619
 accidents-0.619
ead-0.618
Token.
Token ID13
Feature activation-7.41e-03

Pos logit contributions
 Pen+0.234
nes+0.223
igator+0.216
den+0.213
Pen+0.208
Neg logit contributions
 accidents-0.166
Time-0.156
ead-0.155
 working-0.151
 End-0.149
Token One
Token ID1881
Feature activation+5.37e-02

Pos logit contributions
Time+0.006
 Good+0.006
ead+0.005
 accidents+0.005
 End+0.005
Neg logit contributions
nes-0.017
igator-0.017
nam-0.016
 tant-0.016
den-0.016
Token day
Token ID1110
Feature activation+2.67e-02

Pos logit contributions
 Pen+0.078
igator+0.073
nes+0.068
den+0.065
Pen+0.065
Neg logit contributions
 accidents-0.095
ead-0.090
aping-0.089
rou-0.087
ucking-0.087
Token,
Token ID11
Feature activation-1.96e-04

Pos logit contributions
nes+0.061
igator+0.058
den+0.057
 tant+0.056
nam+0.056
Neg logit contributions
 accidents-0.024
Time-0.023
uck-0.021
 End-0.021
 Good-0.021
Token bedroom
Token ID14043
Feature activation-1.44e-03

Pos logit contributions
 Pen+0.132
nes+0.126
igator+0.122
den+0.121
Pen+0.119
Neg logit contributions
 accidents-0.078
Time-0.072
ead-0.071
 working-0.069
 End-0.068
Token.
Token ID13
Feature activation-6.40e-03

Pos logit contributions
 accidents+0.002
Time+0.002
ead+0.002
 working+0.002
 End+0.002
Neg logit contributions
 Pen-0.003
nes-0.002
igator-0.002
den-0.002
Pen-0.002
Token The
Token ID383
Feature activation-1.87e-02

Pos logit contributions
 accidents+0.008
Time+0.007
ead+0.007
 working+0.007
 End+0.007
Neg logit contributions
 Pen-0.012
nes-0.012
igator-0.011
den-0.011
Pen-0.011
Token next
Token ID1306
Feature activation-1.42e-01

Pos logit contributions
ead+0.023
 accidents+0.023
aping+0.022
anging+0.022
ucking+0.022
Neg logit contributions
 Pen-0.035
igator-0.033
nes-0.032
Pen-0.031
nam-0.031
Token day
Token ID1110
Feature activation+2.68e-02

Pos logit contributions
 accidents+0.221
ead+0.212
aping+0.207
ounds+0.204
ucking+0.203
Neg logit contributions
 Pen-0.233
nes-0.210
igator-0.209
den-0.204
Pen-0.200
Token Pen
Token ID7507
Feature activation+4.95e-01

Pos logit contributions
 Pen+0.047
nes+0.046
igator+0.044
den+0.043
nam+0.042
Neg logit contributions
 accidents-0.037
Time-0.035
ead-0.034
 working-0.033
 End-0.033
Tokenelope
Token ID47329
Feature activation+1.27e-01

Pos logit contributions
 Pen+0.678
nes+0.639
igator+0.617
den+0.595
nam+0.585
Neg logit contributions
 accidents-0.881
Time-0.847
ead-0.835
 working-0.815
 End-0.814
Token went
Token ID1816
Feature activation-9.99e-02

Pos logit contributions
 Pen+0.239
nes+0.226
igator+0.219
den+0.216
Pen+0.212
Neg logit contributions
 accidents-0.163
Time-0.152
ead-0.150
 working-0.143
 End-0.142
Token outside
Token ID2354
Feature activation-1.67e-02

Pos logit contributions
 accidents+0.176
icious+0.171
ead+0.168
aping+0.168
ounds+0.166
Neg logit contributions
 Pen-0.146
nes-0.132
 Sunshine-0.122
igator-0.122
den-0.120
Token to
Token ID284
Feature activation+2.90e-02

Pos logit contributions
 accidents+0.025
Time+0.024
ead+0.024
 End+0.023
aping+0.023
Neg logit contributions
 Pen-0.028
nes-0.026
igator-0.025
den-0.024
Pen-0.024
Token pick
Token ID2298
Feature activation-6.13e-02

Pos logit contributions
 Pen+0.052
igator+0.047
nes+0.047
Pen+0.044
 Sunny+0.044
Neg logit contributions
 accidents-0.043
ead-0.040
ucking-0.040
Time-0.039
aping-0.039
Token flowers
Token ID12734
Feature activation-9.60e-02

Pos logit contributions
 accidents+0.254
Time+0.253
rou+0.246
 End+0.241
ead+0.238
Neg logit contributions
 Pen-0.310
igator-0.279
nes-0.266
nam-0.265
Pen-0.265
Token in
Token ID287
Feature activation+1.42e-01

Pos logit contributions
 accidents+0.147
Time+0.139
ead+0.137
 working+0.133
 End+0.131
Neg logit contributions
 Pen-0.158
nes-0.148
igator-0.142
den-0.141
Pen-0.138
Token her
Token ID607
Feature activation+6.86e-02

Pos logit contributions
 Pen+0.213
igator+0.183
nam+0.183
nes+0.179
Pen+0.178
Neg logit contributions
 accidents-0.238
ead-0.233
rou-0.226
Time-0.226
ucking-0.226
Token garden
Token ID11376
Feature activation-1.45e-01

Pos logit contributions
 Pen+0.127
nes+0.110
Pen+0.109
 Sunny+0.107
nam+0.107
Neg logit contributions
 accidents-0.093
Time-0.091
ucking-0.087
icious-0.087
Nothing-0.085
Token,
Token ID11
Feature activation-6.21e-04

Pos logit contributions
Time+0.252
 accidents+0.246
ead+0.240
rou+0.234
 End+0.231
Neg logit contributions
 Pen-0.213
igator-0.181
nes-0.178
nam-0.175
 Sunny-0.173
Token Pen
Token ID7507
Feature activation+4.95e-01

Pos logit contributions
 accidents+0.001
Time+0.001
 End+0.001
 Good+0.001
Are+0.001
Neg logit contributions
nes-0.001
igator-0.001
 tant-0.001
den-0.001
 contain-0.001
Tokenelope
Token ID47329
Feature activation+1.26e-01

Pos logit contributions
 Pen+0.644
nes+0.581
den+0.542
Pen+0.534
igator+0.533
Neg logit contributions
 accidents-0.954
Time-0.900
ead-0.892
 working-0.863
aping-0.856
Token heard
Token ID2982
Feature activation-4.44e-02

Pos logit contributions
 Pen+0.206
nes+0.180
sie+0.170
den+0.168
igator+0.168
Neg logit contributions
 accidents-0.202
icious-0.195
Time-0.191
ead-0.185
rou-0.176
Token a
Token ID257
Feature activation-5.48e-03

Pos logit contributions
 accidents+0.063
ead+0.062
Time+0.061
aping+0.060
 End+0.059
Neg logit contributions
 Pen-0.077
nes-0.069
igator-0.068
den-0.067
Pen-0.066
Token whisper
Token ID31992
Feature activation+6.68e-02

Pos logit contributions
ead+0.008
aping+0.008
 accidents+0.008
eared+0.007
anging+0.007
Neg logit contributions
 Pen-0.009
igator-0.008
Pen-0.008
den-0.008
nes-0.008
Token coming
Token ID2406
Feature activation-2.18e-01

Pos logit contributions
 Pen+0.115
igator+0.107
den+0.104
nes+0.103
 contain+0.100
Neg logit contributions
 accidents-0.094
ead-0.093
aping-0.090
Time-0.088
rou-0.086
Token
Token ID198
Feature activation+2.11e-02

Pos logit contributions
 Pen+0.161
nes+0.155
igator+0.154
den+0.152
icity+0.149
Neg logit contributions
 accidents-0.094
Time-0.092
ead-0.090
aping-0.087
 End-0.085
Token
Token ID198
Feature activation+2.16e-02

Pos logit contributions
 Pen+0.040
nes+0.038
igator+0.038
den+0.038
nam+0.038
Neg logit contributions
Time-0.025
 accidents-0.024
 End-0.023
ead-0.023
aping-0.022
TokenOnce
Token ID7454
Feature activation+6.35e-02

Pos logit contributions
 Pen+0.041
nes+0.039
igator+0.037
den+0.037
Pen+0.037
Neg logit contributions
 accidents-0.028
ead-0.026
Time-0.025
 working-0.025
aping-0.024
Token home
Token ID1363
Feature activation-5.18e-02

Pos logit contributions
 Pen+0.118
nes+0.113
igator+0.110
den+0.109
Pen+0.108
Neg logit contributions
 accidents-0.080
Time-0.073
 working-0.071
ead-0.071
 End-0.071
Token,
Token ID11
Feature activation-5.21e-03

Pos logit contributions
 accidents+0.077
ead+0.076
Time+0.075
rou+0.071
ounds+0.071
Neg logit contributions
 Pen-0.088
nes-0.080
igator-0.078
den-0.076
Pen-0.073
Token Pen
Token ID7507
Feature activation+4.94e-01

Pos logit contributions
 accidents+0.007
Time+0.006
 End+0.006
 working+0.006
 Good+0.006
Neg logit contributions
nes-0.009
 Pen-0.009
den-0.009
igator-0.009
Pen-0.009
Tokenelope
Token ID47329
Feature activation+1.25e-01

Pos logit contributions
 Pen+0.732
igator+0.724
nes+0.718
nam+0.699
den+0.665
Neg logit contributions
 accidents-0.785
Time-0.763
 End-0.759
ead-0.739
 working-0.733
Token tucked
Token ID29779
Feature activation-5.09e-02

Pos logit contributions
 Pen+0.226
nes+0.209
igator+0.201
den+0.201
Pen+0.195
Neg logit contributions
 accidents-0.173
Time-0.162
ead-0.160
aping-0.150
 End-0.148
Token the
Token ID262
Feature activation+1.85e-02

Pos logit contributions
 accidents+0.052
 End+0.044
uck+0.043
 revealing+0.042
 working+0.041
Neg logit contributions
nes-0.112
den-0.107
igator-0.106
 Pen-0.102
icity-0.100
Token cloth
Token ID16270
Feature activation+1.09e-01

Pos logit contributions
 Pen+0.033
nes+0.032
den+0.030
Pen+0.030
icity+0.029
Neg logit contributions
 accidents-0.026
Time-0.024
 working-0.023
 End-0.023
ead-0.022
Token bird
Token ID6512
Feature activation-1.96e-02

Pos logit contributions
 Pen+0.194
nes+0.177
Pen+0.175
icity+0.172
den+0.172
Neg logit contributions
 accidents-0.150
 working-0.148
ead-0.140
uck-0.135
rou-0.134
Token her
Token ID607
Feature activation+6.50e-02

Pos logit contributions
nes+0.254
igator+0.231
 Pen+0.224
den+0.224
 tant+0.216
Neg logit contributions
 accidents-0.161
 End-0.149
 working-0.148
Time-0.141
 pouring-0.139
Token mom
Token ID1995
Feature activation+2.94e-02

Pos logit contributions
 Pen+0.115
nes+0.108
igator+0.105
den+0.103
Pen+0.101
Neg logit contributions
 accidents-0.092
Time-0.087
ead-0.086
 working-0.082
 End-0.081
Token and
Token ID290
Feature activation+1.17e-02

Pos logit contributions
 Pen+0.053
nes+0.050
igator+0.049
den+0.048
Pen+0.047
Neg logit contributions
 accidents-0.040
Time-0.037
ead-0.037
 working-0.035
 End-0.035
Token dad
Token ID9955
Feature activation+6.97e-02

Pos logit contributions
 Pen+0.020
nes+0.020
igator+0.019
den+0.018
Pen+0.018
Neg logit contributions
 accidents-0.017
Time-0.015
ead-0.015
 working-0.015
aping-0.015
Token,
Token ID11
Feature activation-3.00e-03

Pos logit contributions
 Pen+0.123
nes+0.116
igator+0.112
den+0.111
Pen+0.108
Neg logit contributions
 accidents-0.098
Time-0.093
ead-0.091
 End-0.087
 working-0.087
Token Pen
Token ID7507
Feature activation+4.94e-01

Pos logit contributions
 accidents+0.005
Time+0.005
 working+0.005
 pouring+0.004
 Good+0.004
Neg logit contributions
nes-0.005
igator-0.004
 tant-0.004
icity-0.004
nam-0.004
Tokenelope
Token ID47329
Feature activation+1.25e-01

Pos logit contributions
nam+0.765
igator+0.762
nes+0.747
 Pen+0.712
 tant+0.705
Neg logit contributions
 End-0.746
Time-0.727
 accidents-0.719
 working-0.700
ead-0.688
Token was
Token ID373
Feature activation-2.69e-02

Pos logit contributions
 Pen+0.204
nes+0.181
den+0.177
igator+0.171
Pen+0.162
Neg logit contributions
Time-0.195
 accidents-0.193
icious-0.185
ead-0.182
ores-0.173
Token able
Token ID1498
Feature activation-1.21e-01

Pos logit contributions
 accidents+0.041
Time+0.040
ead+0.039
ounds+0.038
 Good+0.038
Neg logit contributions
 Pen-0.045
nes-0.041
igator-0.038
nam-0.038
den-0.037
Token to
Token ID284
Feature activation+2.62e-02

Pos logit contributions
icious+0.241
 End+0.236
Time+0.234
 Good+0.229
ucking+0.229
Neg logit contributions
 Pen-0.141
nam-0.118
nes-0.115
 Sunshine-0.106
igator-0.104
Token fix
Token ID4259
Feature activation-5.22e-02

Pos logit contributions
 Pen+0.042
nes+0.040
igator+0.038
 contain+0.037
den+0.037
Neg logit contributions
 accidents-0.041
Time-0.040
joy-0.038
 End-0.038
ead-0.038
Token.
Token ID13
Feature activation-8.15e-03

Pos logit contributions
 Pen+0.197
nes+0.186
igator+0.180
den+0.178
Pen+0.176
Neg logit contributions
 accidents-0.138
Time-0.128
ead-0.127
 working-0.124
aping-0.120
Token
Token ID220
Feature activation+9.01e-02

Pos logit contributions
 Good+0.009
Time+0.009
ead+0.008
 accidents+0.008
 End+0.008
Neg logit contributions
igator-0.016
nam-0.016
nes-0.016
 tant-0.015
den-0.015
Token
Token ID198
Feature activation+2.64e-02

Pos logit contributions
 Pen+0.162
nes+0.155
igator+0.154
den+0.150
nam+0.146
Neg logit contributions
 accidents-0.119
Time-0.113
ead-0.112
 working-0.107
aping-0.107
Token
Token ID198
Feature activation+2.63e-02

Pos logit contributions
nam+0.064
igator+0.063
 tant+0.061
den+0.058
nes+0.058
Neg logit contributions
Time-0.023
 End-0.018
 Good-0.018
Are-0.017
Nothing-0.017
TokenNow
Token ID3844
Feature activation-1.25e-01

Pos logit contributions
nam+0.037
igator+0.036
 tant+0.035
den+0.034
nes+0.034
Neg logit contributions
Time-0.047
 End-0.042
Nothing-0.041
 accidents-0.041
ucking-0.040
Token Pen
Token ID7507
Feature activation+4.93e-01

Pos logit contributions
 accidents+0.202
Time+0.193
 Good+0.188
 End+0.184
uck+0.178
Neg logit contributions
nam-0.193
igator-0.188
 tant-0.179
nes-0.176
den-0.163
Tokenelope
Token ID47329
Feature activation+1.25e-01

Pos logit contributions
nam+0.795
igator+0.772
nes+0.771
 Pen+0.719
 tant+0.696
Neg logit contributions
 End-0.746
Time-0.739
 accidents-0.726
 Good-0.693
 working-0.686
Token's
Token ID338
Feature activation-4.48e-03

Pos logit contributions
 Pen+0.218
nes+0.204
igator+0.197
den+0.195
Pen+0.189
Neg logit contributions
 accidents-0.178
Time-0.169
ead-0.166
 End-0.156
aping-0.155
Token special
Token ID2041
Feature activation+2.25e-02

Pos logit contributions
Time+0.008
 accidents+0.008
ead+0.008
ucking+0.007
aping+0.007
Neg logit contributions
 Pen-0.006
nes-0.006
igator-0.005
den-0.005
Pen-0.005
Token lamp
Token ID20450
Feature activation+1.05e-01

Pos logit contributions
 Pen+0.031
nes+0.028
igator+0.027
den+0.027
Pen+0.026
Neg logit contributions
 accidents-0.040
Time-0.039
ead-0.038
ucking-0.037
aping-0.037
Token works
Token ID2499
Feature activation+1.60e-02

Pos logit contributions
 Pen+0.185
nes+0.174
igator+0.168
den+0.166
Pen+0.162
Neg logit contributions
 accidents-0.147
Time-0.139
ead-0.137
 working-0.132
 End-0.131
Token a
Token ID257
Feature activation-6.49e-03

Pos logit contributions
 accidents+0.178
 working+0.167
Time+0.167
 End+0.160
ead+0.147
Neg logit contributions
igator-0.304
nes-0.303
 Pen-0.301
den-0.291
nam-0.277
Token very
Token ID845
Feature activation+1.12e-01

Pos logit contributions
 accidents+0.008
 working+0.008
Time+0.008
 End+0.007
ead+0.007
Neg logit contributions
 Pen-0.012
igator-0.012
nes-0.011
den-0.011
nam-0.011
Token long
Token ID890
Feature activation+4.59e-02

Pos logit contributions
 Pen+0.178
nes+0.169
igator+0.161
den+0.159
icity+0.155
Neg logit contributions
 accidents-0.179
ead-0.168
Time-0.168
aping-0.162
 working-0.160
Token time
Token ID640
Feature activation+1.06e-01

Pos logit contributions
 Pen+0.087
nam+0.086
nes+0.086
igator+0.084
Pen+0.082
Neg logit contributions
Time-0.054
 working-0.053
 End-0.053
 accidents-0.052
joy-0.048
Token.
Token ID13
Feature activation-7.99e-03

Pos logit contributions
 Pen+0.182
nes+0.169
den+0.159
igator+0.156
icity+0.154
Neg logit contributions
 accidents-0.155
Time-0.150
ead-0.145
aping-0.139
 End-0.138
Token Pen
Token ID7507
Feature activation+4.93e-01

Pos logit contributions
Time+0.008
 Good+0.008
ead+0.008
 End+0.007
 accidents+0.007
Neg logit contributions
igator-0.017
nes-0.016
nam-0.016
 tant-0.016
den-0.016
Tokenelope
Token ID47329
Feature activation+1.24e-01

Pos logit contributions
nes+0.746
igator+0.734
nam+0.732
 Pen+0.729
den+0.684
Neg logit contributions
 accidents-0.765
 End-0.761
Time-0.748
ead-0.722
aping-0.719
Token was
Token ID373
Feature activation-2.57e-02

Pos logit contributions
 Pen+0.232
nes+0.222
igator+0.216
den+0.211
nam+0.210
Neg logit contributions
 accidents-0.156
Time-0.146
ead-0.144
 working-0.141
 End-0.139
Token always
Token ID1464
Feature activation+9.08e-02

Pos logit contributions
 accidents+0.041
Time+0.039
ead+0.039
 working+0.038
aping+0.037
Neg logit contributions
 Pen-0.040
nes-0.038
igator-0.036
den-0.035
Pen-0.035
Token thankful
Token ID25535
Feature activation-1.38e-01

Pos logit contributions
 Pen+0.153
nes+0.139
den+0.133
igator+0.133
nam+0.133
Neg logit contributions
 accidents-0.137
ead-0.131
Time-0.128
ounds-0.127
aping-0.125
Token for
Token ID329
Feature activation-1.54e-01

Pos logit contributions
 accidents+0.127
Time+0.109
 working+0.106
ead+0.105
 End+0.101
Neg logit contributions
 Pen-0.315
nes-0.307
igator-0.300
den-0.293
Pen-0.291
Token was
Token ID373
Feature activation-2.78e-02

Pos logit contributions
 Pen+0.059
nes+0.058
igator+0.055
den+0.055
nam+0.054
Neg logit contributions
 accidents-0.034
Time-0.032
ead-0.030
 End-0.030
 working-0.030
Token a
Token ID257
Feature activation-7.64e-03

Pos logit contributions
 accidents+0.035
Time+0.033
ead+0.032
 working+0.031
 End+0.031
Neg logit contributions
 Pen-0.053
nes-0.052
den-0.050
igator-0.049
icity-0.048
Token little
Token ID1310
Feature activation+4.43e-02

Pos logit contributions
 accidents+0.013
aping+0.012
ead+0.012
Time+0.012
ounds+0.012
Neg logit contributions
 Pen-0.012
igator-0.010
nes-0.010
Pen-0.010
nam-0.010
Token girl
Token ID2576
Feature activation+1.62e-02

Pos logit contributions
 Pen+0.073
nes+0.068
igator+0.067
den+0.065
Pen+0.064
Neg logit contributions
 accidents-0.067
Time-0.063
ead-0.063
 working-0.060
 End-0.060
Token named
Token ID3706
Feature activation+6.81e-02

Pos logit contributions
 Pen+0.025
nes+0.023
igator+0.022
den+0.022
Pen+0.021
Neg logit contributions
 accidents-0.027
Time-0.026
ead-0.025
 working-0.024
 End-0.024
Token Pen
Token ID7507
Feature activation+4.92e-01

Pos logit contributions
 Pen+0.123
nes+0.115
igator+0.108
Pen+0.107
nam+0.106
Neg logit contributions
 accidents-0.098
ead-0.091
Time-0.090
aping-0.088
ucking-0.087
Tokenelope
Token ID47329
Feature activation+1.25e-01

Pos logit contributions
igator+0.855
nam+0.842
nes+0.810
 Pen+0.800
 tant+0.792
Neg logit contributions
Time-0.658
 End-0.631
 accidents-0.613
 working-0.612
ucking-0.606
Token.
Token ID13
Feature activation-8.52e-03

Pos logit contributions
 Pen+0.231
nes+0.222
igator+0.213
den+0.211
Pen+0.206
Neg logit contributions
 accidents-0.160
ead-0.150
Time-0.149
 working-0.148
 End-0.144
Token She
Token ID1375
Feature activation-3.19e-02

Pos logit contributions
 Good+0.006
Time+0.006
ead+0.005
 accidents+0.005
 End+0.005
Neg logit contributions
nes-0.021
igator-0.020
nam-0.019
 tant-0.019
den-0.019
Token loved
Token ID6151
Feature activation+4.68e-02

Pos logit contributions
Time+0.036
 accidents+0.036
 working+0.036
 End+0.034
ead+0.033
Neg logit contributions
 Pen-0.062
nes-0.059
igator-0.058
den-0.057
 tant-0.057
Token to
Token ID284
Feature activation+2.69e-02

Pos logit contributions
 Pen+0.082
nes+0.076
igator+0.074
den+0.073
Pen+0.072
Neg logit contributions
 accidents-0.066
Time-0.062
ead-0.061
 End-0.060
aping-0.059
TokenThat
Token ID2504
Feature activation-5.79e-02

Pos logit contributions
 accidents+0.109
Time+0.109
ead+0.099
Nothing+0.094
 End+0.094
Neg logit contributions
 Pen-0.216
nes-0.211
igator-0.205
icity-0.199
den-0.199
Token's
Token ID338
Feature activation-6.33e-03

Pos logit contributions
 accidents+0.075
Time+0.069
ead+0.068
 working+0.067
 End+0.064
Neg logit contributions
 Pen-0.109
nes-0.105
igator-0.099
den-0.099
Pen-0.098
Token so
Token ID523
Feature activation+1.60e-01

Pos logit contributions
 accidents+0.009
Time+0.008
ead+0.008
aping+0.008
 working+0.008
Neg logit contributions
 Pen-0.011
nes-0.010
igator-0.010
den-0.010
Pen-0.010
Token cool
Token ID3608
Feature activation-3.55e-02

Pos logit contributions
 Pen+0.284
igator+0.272
nes+0.264
den+0.253
nam+0.250
Neg logit contributions
 accidents-0.220
ead-0.216
Time-0.210
ucking-0.204
aping-0.204
Token,
Token ID11
Feature activation-4.34e-03

Pos logit contributions
 accidents+0.042
Time+0.039
ead+0.038
 working+0.037
 End+0.036
Neg logit contributions
 Pen-0.070
nes-0.067
igator-0.065
den-0.064
Pen-0.063
Token Pen
Token ID7507
Feature activation+4.92e-01

Pos logit contributions
 accidents+0.009
Time+0.009
 Good+0.009
 End+0.008
 working+0.008
Neg logit contributions
nes-0.005
nam-0.004
 tant-0.004
igator-0.004
rob-0.004
Tokenelope
Token ID47329
Feature activation+1.23e-01

Pos logit contributions
 Pen+0.701
nes+0.686
igator+0.657
nam+0.652
den+0.627
Neg logit contributions
 accidents-0.824
Time-0.791
ead-0.776
 End-0.771
 working-0.770
Token!
Token ID0
Feature activation-1.62e-01

Pos logit contributions
 Pen+0.212
nes+0.193
igator+0.188
den+0.186
Pen+0.180
Neg logit contributions
 accidents-0.180
Time-0.174
ead-0.169
 End-0.160
aping-0.160
Token I
Token ID314
Feature activation-1.56e-02

Pos logit contributions
 accidents+0.195
Time+0.180
ead+0.177
 working+0.172
 End+0.169
Neg logit contributions
 Pen-0.322
nes-0.301
igator-0.293
den-0.290
Pen-0.286
Token think
Token ID892
Feature activation+1.10e-01

Pos logit contributions
 accidents+0.021
Time+0.020
ead+0.020
 working+0.019
 End+0.019
Neg logit contributions
 Pen-0.028
nes-0.026
igator-0.025
den-0.025
Pen-0.025
Token that
Token ID326
Feature activation-1.69e-02

Pos logit contributions
nes+0.223
 Pen+0.215
igator+0.211
den+0.209
 tant+0.207
Neg logit contributions
 accidents-0.132
 working-0.110
Time-0.104
 Good-0.099
ead-0.098
Token at
Token ID379
Feature activation-6.95e-02

Pos logit contributions
 accidents+0.140
ead+0.120
 working+0.118
uck+0.117
rou+0.114
Neg logit contributions
 Pen-0.296
nes-0.291
igator-0.290
nam-0.279
Pen-0.277
Token this
Token ID428
Feature activation+3.85e-02

Pos logit contributions
 accidents+0.090
 working+0.080
Time+0.077
ead+0.076
 pouring+0.073
Neg logit contributions
 Pen-0.131
nes-0.130
den-0.125
nam-0.122
Pen-0.120
Token weird
Token ID7650
Feature activation-2.43e-02

Pos logit contributions
 Pen+0.064
nes+0.062
den+0.058
igator+0.058
Pen+0.057
Neg logit contributions
 accidents-0.058
Time-0.054
ead-0.053
 working-0.053
 End-0.051
Token owl
Token ID39610
Feature activation+8.06e-02

Pos logit contributions
 accidents+0.040
Time+0.039
ead+0.038
aping+0.037
 End+0.037
Neg logit contributions
 Pen-0.037
nes-0.033
igator-0.033
den-0.032
Pen-0.031
Token!"
Token ID2474
Feature activation+3.71e-02

Pos logit contributions
 Pen+0.134
nes+0.126
igator+0.121
den+0.119
Pen+0.117
Neg logit contributions
 accidents-0.121
Time-0.114
ead-0.113
 working-0.110
 End-0.108
Token Pen
Token ID7507
Feature activation+4.92e-01

Pos logit contributions
igator+0.075
nes+0.073
nam+0.072
robat+0.071
rob+0.071
Neg logit contributions
uck-0.037
Time-0.036
 accidents-0.035
Nothing-0.032
ead-0.032
Tokenelope
Token ID47329
Feature activation+1.22e-01

Pos logit contributions
nes+0.814
nam+0.814
igator+0.812
 tant+0.741
 contain+0.732
Neg logit contributions
 End-0.688
 accidents-0.662
Time-0.654
uck-0.653
ead-0.645
Token's
Token ID338
Feature activation-5.85e-03

Pos logit contributions
 Pen+0.219
nes+0.209
igator+0.202
den+0.198
Pen+0.195
Neg logit contributions
 accidents-0.166
Time-0.155
ead-0.155
 working-0.150
aping-0.147
Token mom
Token ID1995
Feature activation+2.88e-02

Pos logit contributions
Time+0.010
 accidents+0.010
ead+0.009
ores+0.009
ucking+0.009
Neg logit contributions
 Pen-0.009
nes-0.008
nam-0.008
den-0.008
igator-0.008
Token came
Token ID1625
Feature activation-1.66e-01

Pos logit contributions
 Pen+0.047
nes+0.043
den+0.041
igator+0.041
Pen+0.040
Neg logit contributions
 accidents-0.046
Time-0.044
ead-0.043
 End-0.041
 working-0.041
Token over
Token ID625
Feature activation-7.19e-02

Pos logit contributions
 accidents+0.241
Time+0.225
 End+0.220
ead+0.217
icious+0.216
Neg logit contributions
 Pen-0.294
nes-0.268
den-0.261
igator-0.254
Pen-0.252
Token.
Token ID13
Feature activation-7.66e-03

Pos logit contributions
 Pen+0.155
nes+0.149
igator+0.144
Pen+0.143
icity+0.141
Neg logit contributions
 working-0.088
 accidents-0.084
ead-0.082
Time-0.078
aping-0.076
Token One
Token ID1881
Feature activation+4.69e-02

Pos logit contributions
 Good+0.007
Time+0.007
ead+0.007
 End+0.006
 pouring+0.006
Neg logit contributions
nes-0.017
igator-0.016
nam-0.016
 tant-0.015
den-0.015
Token day
Token ID1110
Feature activation+2.30e-02

Pos logit contributions
 Pen+0.072
igator+0.067
nes+0.064
den+0.062
Pen+0.061
Neg logit contributions
 accidents-0.078
ead-0.074
aping-0.072
Time-0.071
rou-0.071
Token,
Token ID11
Feature activation-2.80e-03

Pos logit contributions
nes+0.052
igator+0.051
nam+0.049
den+0.049
 tant+0.047
Neg logit contributions
 accidents-0.020
Time-0.019
uck-0.019
 pouring-0.018
 working-0.017
Token when
Token ID618
Feature activation-5.42e-02

Pos logit contributions
Time+0.003
 accidents+0.003
 pouring+0.003
 Good+0.003
uck+0.003
Neg logit contributions
nes-0.006
igator-0.005
 tant-0.005
den-0.005
robat-0.005
Token Pen
Token ID7507
Feature activation+4.92e-01

Pos logit contributions
 accidents+0.074
Time+0.074
 End+0.067
 Good+0.065
 pouring+0.065
Neg logit contributions
nes-0.099
igator-0.097
den-0.093
 tant-0.093
nam-0.090
Tokenelope
Token ID47329
Feature activation+1.24e-01

Pos logit contributions
 Pen+0.880
nes+0.850
igator+0.841
nam+0.825
den+0.806
Neg logit contributions
 accidents-0.650
Time-0.633
ead-0.608
 End-0.596
 working-0.589
Token was
Token ID373
Feature activation-2.83e-02

Pos logit contributions
 Pen+0.251
nes+0.241
igator+0.234
nam+0.231
den+0.231
Neg logit contributions
 accidents-0.138
Time-0.130
ead-0.126
 working-0.121
 End-0.119
Token exploring
Token ID13504
Feature activation-1.55e-01

Pos logit contributions
 accidents+0.043
icious+0.042
aping+0.042
Time+0.041
Nothing+0.040
Neg logit contributions
 Pen-0.048
nes-0.043
nam-0.041
igator-0.040
icity-0.039
Token,
Token ID11
Feature activation-2.94e-03

Pos logit contributions
 accidents+0.222
Time+0.211
ead+0.209
 working+0.200
aping+0.199
Neg logit contributions
 Pen-0.269
nes-0.252
igator-0.244
den-0.240
Pen-0.236
Token she
Token ID673
Feature activation-2.64e-02

Pos logit contributions
 accidents+0.003
Time+0.002
 End+0.002
 working+0.002
 pouring+0.002
Neg logit contributions
nes-0.007
igator-0.006
 tant-0.006
den-0.006
icity-0.006
Token
Token ID198
Feature activation+2.57e-02

Pos logit contributions
nam+0.072
igator+0.070
 tant+0.068
nes+0.064
den+0.063
Neg logit contributions
Time-0.015
Are-0.009
It-0.009
Next-0.009
 Good-0.008
Token"
Token ID1
Feature activation-1.17e-01

Pos logit contributions
nam+0.036
igator+0.035
 tant+0.035
nes+0.034
den+0.033
Neg logit contributions
Time-0.046
Are-0.040
 End-0.040
Nothing-0.040
ucking-0.039
TokenHello
Token ID15496
Feature activation+6.34e-02

Pos logit contributions
 accidents+0.154
Time+0.149
ead+0.144
 End+0.137
 working+0.137
Neg logit contributions
 Pen-0.216
nes-0.206
igator-0.199
den-0.197
icity-0.192
Token!"
Token ID2474
Feature activation+3.60e-02

Pos logit contributions
nes+0.117
igator+0.110
den+0.109
 Pen+0.108
nam+0.107
Neg logit contributions
 accidents-0.086
Time-0.075
 working-0.074
ead-0.072
 Good-0.072
Token said
Token ID531
Feature activation+1.03e-01

Pos logit contributions
nes+0.059
 tant+0.055
nam+0.054
igator+0.050
robat+0.049
Neg logit contributions
 accidents-0.048
Time-0.048
 Good-0.046
uck-0.045
 r-0.044
Token Pen
Token ID7507
Feature activation+4.92e-01

Pos logit contributions
nes+0.147
 tant+0.137
nam+0.127
robat+0.126
den+0.124
Neg logit contributions
 accidents-0.168
 louder-0.165
 End-0.161
uck-0.160
Time-0.158
Tokenelope
Token ID47329
Feature activation+1.23e-01

Pos logit contributions
nam+0.869
igator+0.858
nes+0.835
 tant+0.809
 contain+0.792
Neg logit contributions
 accidents-0.611
Time-0.610
ead-0.603
 End-0.602
uck-0.599
Token in
Token ID287
Feature activation+1.39e-01

Pos logit contributions
 Pen+0.206
nes+0.186
den+0.179
igator+0.177
Pen+0.173
Neg logit contributions
 accidents-0.193
Time-0.191
 End-0.174
ead-0.173
icious-0.172
Token a
Token ID257
Feature activation-7.93e-03

Pos logit contributions
 Pen+0.243
nes+0.220
igator+0.217
den+0.213
Pen+0.211
Neg logit contributions
 accidents-0.202
ead-0.192
Time-0.187
aping-0.186
rou-0.183
Token cautious
Token ID21205
Feature activation-5.95e-02

Pos logit contributions
 accidents+0.012
ead+0.011
aping+0.011
Time+0.011
ucking+0.011
Neg logit contributions
 Pen-0.014
igator-0.012
nes-0.012
Pen-0.012
den-0.012
Token voice
Token ID3809
Feature activation+4.55e-02

Pos logit contributions
 accidents+0.073
 working+0.071
Time+0.069
ead+0.068
 End+0.067
Neg logit contributions
 Pen-0.109
nes-0.108
nam-0.103
Pen-0.102
igator-0.100
Token a
Token ID257
Feature activation-8.12e-03

Pos logit contributions
 accidents+0.061
 working+0.056
 louder+0.053
Time+0.052
 End+0.051
Neg logit contributions
nes-0.103
 tant-0.099
den-0.094
igator-0.091
icity-0.091
Token kind
Token ID1611
Feature activation-7.40e-02

Pos logit contributions
 accidents+0.013
aping+0.012
ead+0.012
ucking+0.012
Time+0.012
Neg logit contributions
 Pen-0.013
igator-0.012
nes-0.012
den-0.011
Pen-0.011
Token of
Token ID286
Feature activation-7.31e-02

Pos logit contributions
 accidents+0.095
Time+0.087
ead+0.087
 working+0.085
 End+0.082
Neg logit contributions
 Pen-0.139
nes-0.135
nam-0.128
Pen-0.127
icity-0.126
Token answer
Token ID3280
Feature activation+1.24e-01

Pos logit contributions
 accidents+0.095
ead+0.091
aping+0.088
Time+0.087
ucking+0.086
Neg logit contributions
 Pen-0.136
igator-0.127
nes-0.123
den-0.120
Pen-0.119
Token.
Token ID13
Feature activation-1.02e-02

Pos logit contributions
 Pen+0.231
nes+0.223
igator+0.214
den+0.209
Pen+0.208
Neg logit contributions
 accidents-0.159
Time-0.147
ead-0.146
 working-0.144
 End-0.138
Token Pen
Token ID7507
Feature activation+4.92e-01

Pos logit contributions
 Good+0.013
Time+0.013
ead+0.012
 accidents+0.012
 End+0.012
Neg logit contributions
nes-0.018
igator-0.018
 tant-0.017
nam-0.017
den-0.017
Tokenelope
Token ID47329
Feature activation+1.23e-01

Pos logit contributions
nam+0.766
igator+0.763
nes+0.760
 Pen+0.729
 tant+0.695
Neg logit contributions
 accidents-0.726
Time-0.724
 End-0.714
ead-0.696
aping-0.687
Token knew
Token ID2993
Feature activation-2.59e-02

Pos logit contributions
 Pen+0.221
nes+0.210
igator+0.203
den+0.199
Pen+0.196
Neg logit contributions
 accidents-0.166
Time-0.156
ead-0.155
 working-0.149
 End-0.147
Token there
Token ID612
Feature activation+3.19e-02

Pos logit contributions
 accidents+0.032
 working+0.028
Time+0.028
 End+0.026
rou+0.026
Neg logit contributions
nes-0.050
 Pen-0.050
igator-0.049
den-0.048
 tant-0.047
Token must
Token ID1276
Feature activation+1.88e-01

Pos logit contributions
nes+0.063
 Pen+0.062
den+0.059
Pen+0.059
icity+0.058
Neg logit contributions
 accidents-0.038
 working-0.035
Time-0.034
 End-0.031
 pouring-0.031
Token be
Token ID307
Feature activation-1.71e-01

Pos logit contributions
 Pen+0.370
nes+0.349
igator+0.344
 Sunshine+0.324
icity+0.321
Neg logit contributions
ead-0.226
 accidents-0.224
rou-0.211
joy-0.209
Time-0.206
Token fuss
Token ID34297
Feature activation-3.05e-02

Pos logit contributions
nes+0.039
 Pen+0.039
igator+0.036
den+0.036
Pen+0.035
Neg logit contributions
 accidents-0.031
 working-0.029
Time-0.029
 End-0.028
ead-0.028
Token was
Token ID373
Feature activation-2.82e-02

Pos logit contributions
 accidents+0.044
Time+0.042
ead+0.041
 End+0.040
 working+0.040
Neg logit contributions
 Pen-0.052
nes-0.049
igator-0.047
den-0.047
Pen-0.045
Token about
Token ID546
Feature activation+3.91e-03

Pos logit contributions
 accidents+0.039
Time+0.037
ead+0.036
 End+0.035
aping+0.034
Neg logit contributions
 Pen-0.050
nes-0.048
igator-0.046
den-0.046
icity-0.044
Token.
Token ID13
Feature activation-1.11e-02

Pos logit contributions
 Pen+0.007
nes+0.006
den+0.006
igator+0.006
nam+0.006
Neg logit contributions
 accidents-0.006
Time-0.006
ead-0.005
 End-0.005
aping-0.005
Token When
Token ID1649
Feature activation-4.97e-02

Pos logit contributions
ead+0.011
Time+0.011
 accidents+0.011
 Good+0.011
uck+0.010
Neg logit contributions
nes-0.023
igator-0.022
nam-0.021
den-0.021
 tant-0.021
Token Pen
Token ID7507
Feature activation+4.92e-01

Pos logit contributions
 accidents+0.068
Time+0.065
 End+0.061
 working+0.060
 Good+0.058
Neg logit contributions
nes-0.089
igator-0.086
den-0.083
 tant-0.083
nam-0.081
Tokenelope
Token ID47329
Feature activation+1.22e-01

Pos logit contributions
nam+0.752
nes+0.750
igator+0.734
 Pen+0.700
 tant+0.666
Neg logit contributions
Time-0.757
 accidents-0.753
 End-0.741
ead-0.718
uck-0.713
Token's
Token ID338
Feature activation-6.18e-03

Pos logit contributions
 Pen+0.228
nes+0.215
igator+0.208
den+0.206
Pen+0.201
Neg logit contributions
 accidents-0.159
Time-0.149
ead-0.147
 working-0.141
 End-0.140
Token mom
Token ID1995
Feature activation+2.84e-02

Pos logit contributions
Time+0.011
icious+0.010
 accidents+0.010
ead+0.010
ucking+0.010
Neg logit contributions
 Pen-0.009
igator-0.007
nam-0.007
nes-0.007
 tant-0.007
Token looked
Token ID3114
Feature activation+5.03e-02

Pos logit contributions
 Pen+0.050
nes+0.045
den+0.044
igator+0.043
Pen+0.042
Neg logit contributions
 accidents-0.041
ead-0.039
Time-0.039
 End-0.038
ores-0.036
Token at
Token ID379
Feature activation-6.86e-02

Pos logit contributions
 Pen+0.096
nes+0.092
igator+0.088
den+0.087
Pen+0.087
Neg logit contributions
 accidents-0.064
Time-0.059
ead-0.058
 working-0.057
 End-0.056
Token home
Token ID1363
Feature activation-4.58e-02

Pos logit contributions
 Pen+0.302
nes+0.283
den+0.274
igator+0.273
Pen+0.270
Neg logit contributions
 accidents-0.183
Time-0.167
ead-0.165
 working-0.163
 End-0.157
Token.
Token ID13
Feature activation-1.28e-02

Pos logit contributions
 accidents+0.072
 working+0.068
Time+0.065
ead+0.065
rou+0.064
Neg logit contributions
 Pen-0.072
nes-0.065
den-0.065
igator-0.065
Pen-0.064
Token
Token ID198
Feature activation+2.43e-02

Pos logit contributions
 accidents+0.015
Time+0.015
ead+0.014
 working+0.014
 Good+0.013
Neg logit contributions
 Pen-0.024
nes-0.024
igator-0.023
den-0.023
icity-0.022
Token
Token ID198
Feature activation+2.44e-02

Pos logit contributions
nam+0.058
igator+0.055
nes+0.054
 tant+0.053
den+0.053
Neg logit contributions
Time-0.022
 End-0.019
 accidents-0.018
 Good-0.017
ores-0.017
TokenSo
Token ID2396
Feature activation+1.84e-01

Pos logit contributions
nam+0.038
igator+0.038
 tant+0.037
den+0.034
nes+0.034
Neg logit contributions
Time-0.042
 End-0.036
Nothing-0.036
icious-0.036
 accidents-0.035
Token Pen
Token ID7507
Feature activation+4.91e-01

Pos logit contributions
nam+0.277
nes+0.271
igator+0.271
 tant+0.269
den+0.242
Neg logit contributions
 accidents-0.299
Time-0.285
 End-0.284
 Good-0.278
uck-0.265
Tokenelope
Token ID47329
Feature activation+1.21e-01

Pos logit contributions
nam+0.844
nes+0.817
igator+0.796
 tant+0.749
 contain+0.730
Neg logit contributions
 End-0.719
Time-0.693
 accidents-0.684
 Good-0.651
uck-0.651
Token and
Token ID290
Feature activation+1.00e-02

Pos logit contributions
 Pen+0.209
nes+0.195
igator+0.188
den+0.186
Pen+0.181
Neg logit contributions
 accidents-0.176
Time-0.166
ead-0.162
 End-0.156
 working-0.155
Token her
Token ID607
Feature activation+6.52e-02

Pos logit contributions
nes+0.021
den+0.020
igator+0.019
sie+0.019
icity+0.018
Neg logit contributions
 accidents-0.012
 End-0.010
 working-0.010
Time-0.009
ead-0.009
Token mom
Token ID1995
Feature activation+2.71e-02

Pos logit contributions
 Pen+0.119
nes+0.115
den+0.110
igator+0.109
Pen+0.106
Neg logit contributions
 accidents-0.090
ead-0.082
Time-0.081
 working-0.080
 End-0.080
Token started
Token ID2067
Feature activation-1.33e-01

Pos logit contributions
 Pen+0.047
nes+0.044
den+0.043
igator+0.043
icity+0.040
Neg logit contributions
 accidents-0.041
Time-0.038
ead-0.036
 End-0.035
joy-0.035
Token special
Token ID2041
Feature activation+2.14e-02

Pos logit contributions
 Pen+0.125
nes+0.123
den+0.118
igator+0.118
Pen+0.116
Neg logit contributions
 accidents-0.088
 working-0.082
 End-0.079
rou-0.075
ead-0.074
Token pink
Token ID11398
Feature activation-2.18e-02

Pos logit contributions
 Pen+0.034
nes+0.031
igator+0.030
den+0.030
Pen+0.029
Neg logit contributions
 accidents-0.034
Time-0.032
ead-0.032
aping-0.031
ucking-0.031
Token lamp
Token ID20450
Feature activation+1.04e-01

Pos logit contributions
 accidents+0.039
Time+0.038
ead+0.037
aping+0.036
ucking+0.036
Neg logit contributions
 Pen-0.030
nes-0.027
igator-0.026
den-0.025
Pen-0.025
Token that
Token ID326
Feature activation-1.59e-02

Pos logit contributions
 Pen+0.192
nes+0.181
igator+0.175
den+0.173
Pen+0.171
Neg logit contributions
 accidents-0.137
Time-0.127
ead-0.126
 working-0.123
 End-0.120
Token makes
Token ID1838
Feature activation-6.53e-02

Pos logit contributions
 accidents+0.020
Time+0.019
 working+0.018
 Good+0.017
 End+0.016
Neg logit contributions
nes-0.030
 Pen-0.028
den-0.028
icity-0.027
nam-0.027
Token Pen
Token ID7507
Feature activation+4.91e-01

Pos logit contributions
 accidents+0.096
Time+0.090
 working+0.087
ead+0.085
 End+0.083
Neg logit contributions
 Pen-0.110
nes-0.106
igator-0.103
den-0.101
nam-0.100
Tokenelope
Token ID47329
Feature activation+1.20e-01

Pos logit contributions
 Pen+0.768
nes+0.736
igator+0.715
den+0.692
nam+0.688
Neg logit contributions
 accidents-0.770
Time-0.728
ead-0.723
 working-0.714
 End-0.709
Token feel
Token ID1254
Feature activation-1.96e-02

Pos logit contributions
 Pen+0.198
nes+0.187
igator+0.182
nam+0.180
den+0.177
Neg logit contributions
Time-0.175
 accidents-0.170
ead-0.168
aping-0.160
ucking-0.158
Token so
Token ID523
Feature activation+1.60e-01

Pos logit contributions
ead+0.029
aping+0.028
ounds+0.028
 accidents+0.028
Time+0.028
Neg logit contributions
 Pen-0.030
nes-0.029
igator-0.029
nam-0.028
 contain-0.026
Token lucky
Token ID9670
Feature activation-8.20e-02

Pos logit contributions
nam+0.231
nes+0.226
 contain+0.216
igator+0.215
 Pen+0.214
Neg logit contributions
Time-0.253
ead-0.250
joy-0.229
phony-0.229
icious-0.228
Token.
Token ID13
Feature activation-1.07e-02

Pos logit contributions
 accidents+0.108
Time+0.101
ead+0.099
 working+0.096
 End+0.094
Neg logit contributions
 Pen-0.152
nes-0.144
igator-0.139
den-0.137
Pen-0.135
Token the
Token ID262
Feature activation+1.94e-02

Pos logit contributions
 accidents+0.104
Time+0.089
 working+0.086
 End+0.085
uck+0.079
Neg logit contributions
nes-0.218
igator-0.205
nam-0.202
den-0.199
 tant-0.198
Token bird
Token ID6512
Feature activation-2.20e-02

Pos logit contributions
 Pen+0.031
igator+0.028
nes+0.027
Pen+0.026
den+0.025
Neg logit contributions
 accidents-0.031
ead-0.030
aping-0.029
Time-0.029
anging-0.029
Token began
Token ID2540
Feature activation-1.46e-01

Pos logit contributions
 accidents+0.032
ead+0.031
Time+0.030
 End+0.029
ores+0.029
Neg logit contributions
 Pen-0.038
igator-0.034
nes-0.034
den-0.034
Pen-0.033
Token to
Token ID284
Feature activation+2.50e-02

Pos logit contributions
icious+0.252
 accidents+0.251
 End+0.249
Time+0.247
 Good+0.236
Neg logit contributions
 Pen-0.212
den-0.177
nes-0.170
 Sunshine-0.166
igator-0.165
Token tell
Token ID1560
Feature activation+1.32e-02

Pos logit contributions
 Pen+0.042
igator+0.038
nes+0.037
den+0.036
Pen+0.036
Neg logit contributions
 accidents-0.038
ead-0.036
Time-0.036
aping-0.035
 End-0.035
Token Pen
Token ID7507
Feature activation+4.90e-01

Pos logit contributions
nes+0.026
nam+0.025
igator+0.024
den+0.023
 tant+0.023
Neg logit contributions
 accidents-0.016
 louder-0.015
Time-0.015
 End-0.014
 Good-0.014
Tokenelope
Token ID47329
Feature activation+1.21e-01

Pos logit contributions
nam+0.866
igator+0.851
 tant+0.816
nes+0.812
 contain+0.764
Neg logit contributions
Time-0.639
 accidents-0.636
 End-0.633
 working-0.624
joy-0.619
Token it
Token ID340
Feature activation-4.71e-02

Pos logit contributions
 Pen+0.222
nes+0.200
igator+0.196
den+0.195
Pen+0.191
Neg logit contributions
 accidents-0.165
Time-0.161
ead-0.157
aping-0.149
 End-0.148
Token's
Token ID338
Feature activation-7.15e-03

Pos logit contributions
 accidents+0.068
ead+0.067
Time+0.065
aping+0.062
 End+0.062
Neg logit contributions
 Pen-0.082
nes-0.073
den-0.072
igator-0.072
icity-0.069
Token story
Token ID1621
Feature activation+3.79e-02

Pos logit contributions
 accidents+0.011
Time+0.011
ead+0.011
aping+0.010
ucking+0.010
Neg logit contributions
 Pen-0.011
nes-0.010
den-0.010
igator-0.010
icity-0.010
Token.
Token ID13
Feature activation-1.01e-02

Pos logit contributions
 Pen+0.072
nes+0.068
igator+0.067
nam+0.066
Pen+0.065
Neg logit contributions
 accidents-0.047
Time-0.045
 working-0.043
ead-0.042
 End-0.041
Token was
Token ID373
Feature activation-2.86e-02

Pos logit contributions
nes+0.059
 Pen+0.059
nam+0.056
igator+0.056
den+0.056
Neg logit contributions
 accidents-0.029
Time-0.028
 End-0.026
 working-0.025
aping-0.025
Token a
Token ID257
Feature activation-9.49e-03

Pos logit contributions
 accidents+0.036
Time+0.034
ead+0.033
 working+0.032
 End+0.032
Neg logit contributions
 Pen-0.054
nes-0.052
igator-0.050
den-0.050
icity-0.048
Token little
Token ID1310
Feature activation+4.26e-02

Pos logit contributions
 accidents+0.016
ead+0.015
aping+0.015
Time+0.015
ounds+0.015
Neg logit contributions
 Pen-0.014
igator-0.013
nes-0.012
Pen-0.012
nam-0.012
Token girl
Token ID2576
Feature activation+1.38e-02

Pos logit contributions
 Pen+0.069
nes+0.063
igator+0.062
den+0.060
Pen+0.060
Neg logit contributions
 accidents-0.066
Time-0.063
ead-0.062
aping-0.060
 working-0.060
Token named
Token ID3706
Feature activation+6.55e-02

Pos logit contributions
 Pen+0.021
nes+0.019
igator+0.019
den+0.018
Pen+0.018
Neg logit contributions
 accidents-0.023
Time-0.022
ead-0.022
 End-0.021
 working-0.021
Token Pen
Token ID7507
Feature activation+4.90e-01

Pos logit contributions
 Pen+0.127
nes+0.120
igator+0.117
den+0.116
Pen+0.113
Neg logit contributions
 accidents-0.081
Time-0.076
ead-0.075
 working-0.072
 End-0.071
Tokenelope
Token ID47329
Feature activation+1.20e-01

Pos logit contributions
igator+0.834
nam+0.821
nes+0.814
 Pen+0.799
 tant+0.775
Neg logit contributions
Time-0.657
 End-0.627
 working-0.621
 accidents-0.618
ucking-0.604
Token who
Token ID508
Feature activation+1.80e-01

Pos logit contributions
 Pen+0.221
nes+0.212
igator+0.203
den+0.201
Pen+0.198
Neg logit contributions
 accidents-0.156
ead-0.146
Time-0.146
 working-0.144
 End-0.141
Token was
Token ID373
Feature activation-2.92e-02

Pos logit contributions
 Pen+0.256
igator+0.233
nes+0.230
den+0.217
Pen+0.216
Neg logit contributions
 accidents-0.318
ead-0.305
ucking-0.297
aping-0.295
ounds-0.288
Token 3
Token ID513
Feature activation+4.04e-02

Pos logit contributions
 accidents+0.050
Time+0.047
ead+0.047
 working+0.045
 End+0.045
Neg logit contributions
 Pen-0.043
nes-0.040
igator-0.039
den-0.038
Pen-0.037
Token years
Token ID812
Feature activation+9.14e-02

Pos logit contributions
 Pen+0.072
nes+0.070
den+0.065
igator+0.065
Pen+0.064
Neg logit contributions
 accidents-0.057
ead-0.052
Time-0.051
 working-0.051
aping-0.050
Token safe
Token ID3338
Feature activation-6.94e-03

Pos logit contributions
 accidents+0.013
Time+0.012
ead+0.012
 working+0.012
 End+0.012
Neg logit contributions
 Pen-0.017
nes-0.016
igator-0.015
den-0.015
Pen-0.015
Token place
Token ID1295
Feature activation+4.68e-02

Pos logit contributions
 accidents+0.010
Time+0.010
ead+0.009
 working+0.009
 End+0.009
Neg logit contributions
 Pen-0.012
nes-0.011
den-0.011
igator-0.011
Pen-0.011
Token to
Token ID284
Feature activation+2.45e-02

Pos logit contributions
 Pen+0.094
Pen+0.088
nes+0.088
icity+0.086
den+0.085
Neg logit contributions
 accidents-0.053
 working-0.051
rou-0.046
ead-0.046
Time-0.046
Token stay
Token ID2652
Feature activation+6.73e-02

Pos logit contributions
 Pen+0.043
nes+0.039
igator+0.038
Pen+0.037
den+0.036
Neg logit contributions
 accidents-0.036
ead-0.035
Time-0.034
aping-0.034
rou-0.033
Token.
Token ID13
Feature activation-1.12e-02

Pos logit contributions
 Pen+0.107
nes+0.102
igator+0.096
den+0.095
nam+0.094
Neg logit contributions
 accidents-0.104
Time-0.101
ead-0.100
aping-0.094
ounds-0.094
Token Pen
Token ID7507
Feature activation+4.90e-01

Pos logit contributions
 Good+0.025
Time+0.024
 accidents+0.024
ead+0.023
 End+0.023
Neg logit contributions
nes-0.010
igator-0.009
nam-0.009
 tant-0.009
den-0.008
Tokenelope
Token ID47329
Feature activation+1.21e-01

Pos logit contributions
nam+0.800
nes+0.792
igator+0.785
 Pen+0.734
den+0.710
Neg logit contributions
 End-0.710
 accidents-0.708
Time-0.699
aping-0.667
ucking-0.664
Token was
Token ID373
Feature activation-2.93e-02

Pos logit contributions
 Pen+0.221
nes+0.210
igator+0.203
den+0.199
Pen+0.197
Neg logit contributions
 accidents-0.159
Time-0.149
ead-0.147
 working-0.143
 End-0.141
Token so
Token ID523
Feature activation+1.60e-01

Pos logit contributions
 accidents+0.048
ead+0.045
Time+0.045
aping+0.043
ounds+0.043
Neg logit contributions
 Pen-0.047
nes-0.043
igator-0.041
den-0.039
Pen-0.039
Token moved
Token ID3888
Feature activation-5.89e-02

Pos logit contributions
 Pen+0.313
nes+0.295
igator+0.287
den+0.282
Pen+0.278
Neg logit contributions
 accidents-0.195
ead-0.181
Time-0.181
aping-0.170
 working-0.170
Token by
Token ID416
Feature activation+1.88e-02

Pos logit contributions
 accidents+0.090
Time+0.085
ead+0.084
 working+0.082
 End+0.081
Neg logit contributions
 Pen-0.097
nes-0.092
igator-0.088
den-0.086
Pen-0.085
Token the
Token ID262
Feature activation+1.91e-02

Pos logit contributions
 accidents+0.009
Time+0.009
 End+0.008
 Good+0.008
 pouring+0.008
Neg logit contributions
nes-0.011
igator-0.011
nam-0.011
 tant-0.011
den-0.010
Token owl
Token ID39610
Feature activation+7.75e-02

Pos logit contributions
 Pen+0.025
igator+0.022
nam+0.021
den+0.020
nes+0.020
Neg logit contributions
 accidents-0.035
ead-0.035
Time-0.034
ucking-0.034
ores-0.034
Token flew
Token ID13112
Feature activation-3.64e-02

Pos logit contributions
 Pen+0.141
nes+0.133
igator+0.128
den+0.127
Pen+0.124
Neg logit contributions
 accidents-0.105
Time-0.098
ead-0.097
 working-0.093
 End-0.093
Token away
Token ID1497
Feature activation+1.59e-01

Pos logit contributions
 accidents+0.061
Time+0.058
ead+0.057
 working+0.056
 End+0.054
Neg logit contributions
 Pen-0.054
nes-0.051
den-0.048
igator-0.047
Pen-0.047
Token and
Token ID290
Feature activation+8.43e-03

Pos logit contributions
 Pen+0.274
nes+0.255
igator+0.246
den+0.242
Pen+0.236
Neg logit contributions
 accidents-0.231
Time-0.221
ead-0.218
 End-0.208
aping-0.208
Token Pen
Token ID7507
Feature activation+4.90e-01

Pos logit contributions
nam+0.008
nes+0.008
 tant+0.008
den+0.007
igator+0.007
Neg logit contributions
Time-0.017
 accidents-0.017
 Good-0.017
 End-0.016
 pouring-0.016
Tokenelope
Token ID47329
Feature activation+1.20e-01

Pos logit contributions
nam+0.823
nes+0.805
igator+0.793
 contain+0.726
 Pen+0.719
Neg logit contributions
 End-0.699
Time-0.691
 accidents-0.677
ucking-0.658
 Good-0.656
Token and
Token ID290
Feature activation+8.03e-03

Pos logit contributions
 Pen+0.225
nes+0.215
igator+0.210
den+0.205
Pen+0.202
Neg logit contributions
 accidents-0.152
Time-0.141
ead-0.140
 working-0.136
aping-0.134
Token her
Token ID607
Feature activation+6.32e-02

Pos logit contributions
nes+0.016
den+0.014
nam+0.014
igator+0.014
 tant+0.014
Neg logit contributions
 accidents-0.010
Time-0.009
 End-0.009
 Good-0.008
 working-0.008
Token mom
Token ID1995
Feature activation+2.48e-02

Pos logit contributions
 Pen+0.100
igator+0.089
nam+0.087
nes+0.086
Pen+0.083
Neg logit contributions
Time-0.100
 accidents-0.100
ead-0.097
ucking-0.096
aping-0.094
Token never
Token ID1239
Feature activation+8.66e-02

Pos logit contributions
 Pen+0.041
nes+0.038
igator+0.036
den+0.036
Pen+0.035
Neg logit contributions
 accidents-0.038
Time-0.036
ead-0.036
 End-0.034
 working-0.034
Token too
Token ID1165
Feature activation-1.28e-01

Pos logit contributions
 Pen+0.005
nes+0.004
Pen+0.004
den+0.004
igator+0.004
Neg logit contributions
 accidents-0.003
 working-0.003
Time-0.003
ead-0.003
 End-0.003
Token.
Token ID13
Feature activation-2.08e-02

Pos logit contributions
 accidents+0.150
Time+0.140
 working+0.139
ead+0.137
rou+0.130
Neg logit contributions
 Pen-0.254
nes-0.245
igator-0.238
den-0.233
Pen-0.229
Token He
Token ID679
Feature activation-3.02e-02

Pos logit contributions
 accidents+0.024
Time+0.023
ead+0.023
 Good+0.021
 End+0.021
Neg logit contributions
 Pen-0.040
nes-0.040
igator-0.038
den-0.038
icity-0.037
Token knew
Token ID2993
Feature activation-3.40e-02

Pos logit contributions
 working+0.028
rou+0.028
Time+0.028
 accidents+0.026
 End+0.026
Neg logit contributions
 Pen-0.061
nes-0.059
nam-0.059
igator-0.057
Pen-0.057
Token that
Token ID326
Feature activation-2.58e-02

Pos logit contributions
 accidents+0.040
 working+0.034
Time+0.032
Nothing+0.030
rou+0.030
Neg logit contributions
nes-0.070
 Pen-0.069
igator-0.067
den-0.066
Pen-0.065
Token accidents
Token ID17390
Feature activation-3.74e-01

Pos logit contributions
 accidents+0.035
 working+0.032
Time+0.031
 Good+0.028
ead+0.028
Neg logit contributions
nes-0.049
 Pen-0.047
icity-0.046
den-0.046
igator-0.045
Token happen
Token ID1645
Feature activation+5.65e-02

Pos logit contributions
 accidents+0.546
 working+0.469
Time+0.443
 pouring+0.410
ores+0.392
Neg logit contributions
 Pen-0.710
nes-0.672
Pen-0.670
den-0.667
nam-0.651
Token sometimes
Token ID3360
Feature activation+8.58e-02

Pos logit contributions
 Pen+0.106
nes+0.100
igator+0.097
den+0.095
Pen+0.095
Neg logit contributions
 accidents-0.076
Time-0.069
 working-0.068
ead-0.066
 End-0.065
Token.
Token ID13
Feature activation-1.81e-02

Pos logit contributions
 Pen+0.152
nes+0.143
igator+0.138
den+0.136
Pen+0.133
Neg logit contributions
 accidents-0.119
Time-0.113
ead-0.112
aping-0.107
 working-0.106
Token
Token ID198
Feature activation+1.84e-02

Pos logit contributions
 accidents+0.020
Time+0.019
 Good+0.018
ead+0.018
 End+0.017
Neg logit contributions
 Pen-0.036
nes-0.036
igator-0.034
icity-0.034
den-0.034
Token
Token ID198
Feature activation+1.94e-02

Pos logit contributions
 Pen+0.037
nes+0.036
igator+0.034
den+0.034
nam+0.034
Neg logit contributions
Time-0.021
 accidents-0.021
 End-0.019
 working-0.019
ead-0.019
Token But
Token ID887
Feature activation+1.33e-01

Pos logit contributions
 accidents+0.031
Time+0.030
ead+0.029
 Good+0.028
 End+0.028
Neg logit contributions
 Pen-0.053
nes-0.052
igator-0.051
den-0.050
icity-0.050
Token he
Token ID339
Feature activation-2.43e-02

Pos logit contributions
 Pen+0.242
nes+0.230
igator+0.221
den+0.219
Pen+0.215
Neg logit contributions
 accidents-0.179
Time-0.167
ead-0.164
 working-0.160
 End-0.158
Token also
Token ID635
Feature activation+6.47e-02

Pos logit contributions
 accidents+0.034
Time+0.031
 working+0.031
ead+0.031
 End+0.030
Neg logit contributions
 Pen-0.043
nes-0.041
nam-0.039
den-0.039
Pen-0.038
Token learned
Token ID4499
Feature activation-6.42e-02

Pos logit contributions
 Pen+0.114
nes+0.107
igator+0.105
den+0.102
nam+0.099
Neg logit contributions
 accidents-0.091
Time-0.086
ead-0.085
aping-0.081
ucking-0.080
Token that
Token ID326
Feature activation-2.98e-02

Pos logit contributions
 accidents+0.077
 working+0.064
rou+0.063
Time+0.061
ead+0.060
Neg logit contributions
nes-0.134
 Pen-0.134
igator-0.125
Pen-0.125
den-0.125
Token accidents
Token ID17390
Feature activation-3.74e-01

Pos logit contributions
 accidents+0.038
Time+0.036
ead+0.036
aping+0.034
 End+0.034
Neg logit contributions
 Pen-0.055
nes-0.052
igator-0.051
den-0.050
Pen-0.049
Token can
Token ID460
Feature activation+3.81e-02

Pos logit contributions
 accidents+0.576
 working+0.510
Time+0.500
ead+0.466
 pouring+0.457
Neg logit contributions
 Pen-0.655
nes-0.616
den-0.597
Pen-0.596
nam-0.580
Token happen
Token ID1645
Feature activation+5.85e-02

Pos logit contributions
 Pen+0.063
nes+0.061
igator+0.059
icity+0.055
den+0.055
Neg logit contributions
 accidents-0.054
ead-0.054
Time-0.053
joy-0.052
rou-0.051
Token and
Token ID290
Feature activation+3.86e-03

Pos logit contributions
 Pen+0.099
nes+0.093
igator+0.090
den+0.089
icity+0.086
Neg logit contributions
 accidents-0.084
Time-0.081
ead-0.081
 End-0.076
aping-0.076
Token it
Token ID340
Feature activation-5.33e-02

Pos logit contributions
 Pen+0.006
nam+0.006
igator+0.006
nes+0.005
den+0.005
Neg logit contributions
ead-0.006
ucking-0.006
Time-0.006
joy-0.006
icious-0.006
Token's
Token ID338
Feature activation-1.02e-02

Pos logit contributions
 accidents+0.079
ead+0.078
Time+0.078
ucking+0.074
 End+0.074
Neg logit contributions
 Pen-0.086
nes-0.081
igator-0.079
den-0.076
Pen-0.074
Token,
Token ID11
Feature activation-2.92e-03

Pos logit contributions
 accidents+0.076
Time+0.075
ead+0.073
 End+0.071
aping+0.071
Neg logit contributions
 Pen-0.091
nes-0.085
igator-0.082
den-0.081
nam-0.078
Token but
Token ID475
Feature activation+1.98e-01

Pos logit contributions
 accidents+0.005
Time+0.005
 working+0.005
ead+0.005
 End+0.005
Neg logit contributions
 Pen-0.004
nes-0.004
den-0.004
igator-0.004
Pen-0.004
Token she
Token ID673
Feature activation-3.05e-02

Pos logit contributions
 Pen+0.337
igator+0.300
nam+0.299
nes+0.297
den+0.285
Neg logit contributions
ead-0.292
 accidents-0.287
Time-0.284
ucking-0.276
ounds-0.275
Token knew
Token ID2993
Feature activation-2.58e-02

Pos logit contributions
 accidents+0.037
Time+0.035
ead+0.034
 working+0.034
 End+0.033
Neg logit contributions
 Pen-0.059
nes-0.056
igator-0.054
den-0.053
Pen-0.053
Token that
Token ID326
Feature activation-1.99e-02

Pos logit contributions
 accidents+0.032
 working+0.027
Time+0.027
rou+0.025
 End+0.025
Neg logit contributions
nes-0.051
 Pen-0.051
igator-0.048
den-0.048
Pen-0.047
Token accidents
Token ID17390
Feature activation-3.71e-01

Pos logit contributions
 accidents+0.027
Time+0.024
 working+0.024
ead+0.024
 End+0.023
Neg logit contributions
 Pen-0.037
nes-0.036
igator-0.034
den-0.034
Pen-0.033
Token happen
Token ID1645
Feature activation+5.90e-02

Pos logit contributions
 accidents+0.563
 working+0.490
Time+0.481
 pouring+0.443
ores+0.432
Neg logit contributions
 Pen-0.663
nes-0.626
den-0.614
Pen-0.612
nam-0.596
Token.
Token ID13
Feature activation-1.15e-02

Pos logit contributions
 Pen+0.106
nes+0.100
igator+0.097
den+0.096
Pen+0.094
Neg logit contributions
 accidents-0.081
Time-0.076
ead-0.075
 working-0.072
 End-0.071
Token She
Token ID1375
Feature activation-3.14e-02

Pos logit contributions
 accidents+0.013
Time+0.013
ead+0.012
 Good+0.012
 End+0.012
Neg logit contributions
 Pen-0.023
nes-0.022
igator-0.022
den-0.021
icity-0.021
Token told
Token ID1297
Feature activation+3.45e-02

Pos logit contributions
 accidents+0.039
Time+0.036
 working+0.035
ead+0.035
 End+0.035
Neg logit contributions
 Pen-0.060
nes-0.057
igator-0.055
Pen-0.054
den-0.054
Token Lily
Token ID20037
Feature activation-3.04e-02

Pos logit contributions
nes+0.062
 Pen+0.062
den+0.059
igator+0.059
Pen+0.057
Neg logit contributions
 accidents-0.049
ead-0.042
 working-0.042
Time-0.041
 End-0.041
Token "
Token ID366
Feature activation-1.17e-01

Pos logit contributions
 accidents+0.022
Time+0.020
aping+0.020
ead+0.019
 End+0.019
Neg logit contributions
 Pen-0.035
nes-0.032
den-0.031
igator-0.031
Pen-0.031
TokenIt
Token ID1026
Feature activation-2.00e-01

Pos logit contributions
 accidents+0.167
 working+0.150
ead+0.149
ounds+0.145
Time+0.145
Neg logit contributions
 Pen-0.209
nes-0.198
igator-0.189
Pen-0.188
den-0.188
Token's
Token ID338
Feature activation-1.57e-02

Pos logit contributions
 accidents+0.313
ead+0.309
Time+0.307
joy+0.294
 End+0.293
Neg logit contributions
 Pen-0.320
nes-0.289
igator-0.289
den-0.273
Pen-0.265
Token OK
Token ID7477
Feature activation-1.28e-01

Pos logit contributions
ead+0.021
 accidents+0.021
ucking+0.020
aping+0.020
Time+0.020
Neg logit contributions
 Pen-0.029
nes-0.026
igator-0.026
nam-0.025
Pen-0.025
Token,
Token ID11
Feature activation-1.43e-02

Pos logit contributions
ead+0.198
Time+0.196
 accidents+0.194
aping+0.193
ounds+0.189
Neg logit contributions
 Pen-0.206
nes-0.179
igator-0.172
den-0.171
Pen-0.171
Token accidents
Token ID17390
Feature activation-3.70e-01

Pos logit contributions
 accidents+0.019
ead+0.019
Time+0.019
aping+0.018
 working+0.018
Neg logit contributions
 Pen-0.026
nes-0.024
igator-0.023
den-0.023
Pen-0.022
Token happen
Token ID1645
Feature activation+6.26e-02

Pos logit contributions
 accidents+0.577
Time+0.516
 working+0.515
ead+0.488
 End+0.480
Neg logit contributions
 Pen-0.619
nes-0.581
den-0.568
nam-0.557
Pen-0.554
Token.
Token ID13
Feature activation-2.12e-02

Pos logit contributions
 Pen+0.090
nes+0.083
igator+0.077
den+0.076
icity+0.074
Neg logit contributions
ead-0.105
Time-0.104
 accidents-0.103
aping-0.099
ounds-0.098
Token We
Token ID775
Feature activation-1.49e-01

Pos logit contributions
 accidents+0.028
Time+0.026
ead+0.025
 working+0.025
aping+0.024
Neg logit contributions
 Pen-0.041
nes-0.037
igator-0.036
Pen-0.036
den-0.035
Token all
Token ID477
Feature activation+7.04e-02

Pos logit contributions
 accidents+0.216
 working+0.203
Time+0.201
ead+0.199
 End+0.196
Neg logit contributions
 Pen-0.254
nes-0.232
den-0.230
Pen-0.226
nam-0.225
Token make
Token ID787
Feature activation-2.15e-02

Pos logit contributions
 Pen+0.116
igator+0.114
nes+0.110
den+0.100
 contain+0.100
Neg logit contributions
 accidents-0.102
ead-0.101
Time-0.100
joy-0.097
aping-0.096
Token lot
Token ID1256
Feature activation+5.25e-02

Pos logit contributions
 accidents+0.016
Time+0.016
 working+0.015
ead+0.015
 End+0.015
Neg logit contributions
 Pen-0.021
nes-0.021
igator-0.019
den-0.019
nam-0.019
Token.
Token ID13
Feature activation-9.97e-03

Pos logit contributions
 Pen+0.116
nes+0.114
nam+0.112
Pen+0.110
den+0.108
Neg logit contributions
 accidents-0.055
 working-0.048
Time-0.045
ores-0.043
 louder-0.042
Token She
Token ID1375
Feature activation-2.95e-02

Pos logit contributions
 accidents+0.012
ead+0.011
Time+0.011
 working+0.010
 End+0.010
Neg logit contributions
 Pen-0.020
nes-0.019
igator-0.019
den-0.019
Pen-0.018
Token learned
Token ID4499
Feature activation-5.70e-02

Pos logit contributions
 accidents+0.035
Time+0.033
 working+0.032
 End+0.031
rou+0.030
Neg logit contributions
 Pen-0.058
nes-0.055
igator-0.055
Pen-0.052
den-0.052
Token that
Token ID326
Feature activation-1.78e-02

Pos logit contributions
 accidents+0.071
 working+0.059
Time+0.058
ead+0.055
rou+0.054
Neg logit contributions
 Pen-0.119
nes-0.116
den-0.112
igator-0.112
Pen-0.109
Token accidents
Token ID17390
Feature activation-3.68e-01

Pos logit contributions
 accidents+0.023
ead+0.023
Time+0.022
aping+0.022
ucking+0.021
Neg logit contributions
 Pen-0.033
nes-0.030
igator-0.029
nam-0.029
den-0.028
Token can
Token ID460
Feature activation+4.36e-02

Pos logit contributions
 accidents+0.566
 working+0.490
Time+0.479
 pouring+0.440
ead+0.433
Neg logit contributions
 Pen-0.667
nes-0.632
den-0.618
Pen-0.614
nam-0.592
Token happen
Token ID1645
Feature activation+6.18e-02

Pos logit contributions
 Pen+0.074
nes+0.071
igator+0.069
icity+0.065
den+0.065
Neg logit contributions
 accidents-0.059
ead-0.059
Time-0.059
joy-0.057
rou-0.057
Token,
Token ID11
Feature activation-2.17e-03

Pos logit contributions
 Pen+0.098
nes+0.091
igator+0.087
den+0.086
icity+0.084
Neg logit contributions
ead-0.093
 accidents-0.092
Time-0.091
rou-0.086
ounds-0.086
Token but
Token ID475
Feature activation+2.02e-01

Pos logit contributions
 accidents+0.004
Time+0.004
 working+0.004
ead+0.004
 End+0.003
Neg logit contributions
 Pen-0.003
nes-0.003
den-0.003
igator-0.003
Pen-0.003
Token it
Token ID340
Feature activation-4.92e-02

Pos logit contributions
 Pen+0.334
nam+0.299
nes+0.298
igator+0.296
 Sunny+0.280
Neg logit contributions
ead-0.297
Time-0.287
ucking-0.284
icious-0.278
ounds-0.278
Token Tim
Token ID5045
Feature activation-6.41e-02

Pos logit contributions
 accidents+0.008
 Good+0.008
Time+0.008
Nothing+0.007
ead+0.007
Neg logit contributions
 Pen-0.020
nes-0.020
den-0.020
icity-0.020
sie-0.020
Tokenmy
Token ID1820
Feature activation-1.29e-01

Pos logit contributions
 accidents+0.045
 working+0.043
 End+0.040
rou+0.040
Time+0.039
Neg logit contributions
 Pen-0.157
nes-0.152
nam-0.148
Pen-0.146
den-0.143
Token learned
Token ID4499
Feature activation-5.70e-02

Pos logit contributions
 accidents+0.120
 working+0.114
 End+0.108
Time+0.104
rou+0.102
Neg logit contributions
 Pen-0.283
nes-0.273
Pen-0.268
nam-0.267
igator-0.265
Token that
Token ID326
Feature activation-1.74e-02

Pos logit contributions
 accidents+0.069
 working+0.059
Time+0.058
ead+0.056
rou+0.056
Neg logit contributions
 Pen-0.121
nes-0.115
Pen-0.111
den-0.111
igator-0.111
Token sometimes
Token ID3360
Feature activation+9.21e-02

Pos logit contributions
ead+0.023
 accidents+0.023
Time+0.023
ucking+0.022
aping+0.022
Neg logit contributions
 Pen-0.030
nes-0.028
igator-0.028
nam-0.027
den-0.026
Token accidents
Token ID17390
Feature activation-3.68e-01

Pos logit contributions
 Pen+0.156
nes+0.144
igator+0.141
nam+0.138
den+0.136
Neg logit contributions
ead-0.130
Time-0.125
rou-0.124
 accidents-0.124
ucking-0.124
Token happen
Token ID1645
Feature activation+5.98e-02

Pos logit contributions
 accidents+0.568
 working+0.499
Time+0.484
ead+0.460
aping+0.448
Neg logit contributions
 Pen-0.660
nes-0.613
Pen-0.599
den-0.598
icity-0.570
Token,
Token ID11
Feature activation-1.26e-03

Pos logit contributions
 Pen+0.096
nes+0.091
igator+0.087
den+0.086
icity+0.083
Neg logit contributions
 accidents-0.088
ead-0.087
Time-0.087
 End-0.081
ucking-0.081
Token and
Token ID290
Feature activation+1.42e-02

Pos logit contributions
 accidents+0.002
 working+0.002
Time+0.002
ead+0.002
aping+0.002
Neg logit contributions
 Pen-0.002
nes-0.002
Pen-0.002
den-0.002
igator-0.002
Token we
Token ID356
Feature activation-3.97e-02

Pos logit contributions
 Pen+0.022
nes+0.020
igator+0.020
nam+0.020
den+0.019
Neg logit contributions
ead-0.022
Time-0.021
 accidents-0.021
ucking-0.021
icious-0.020
Token can
Token ID460
Feature activation+4.38e-02

Pos logit contributions
 accidents+0.060
Time+0.056
ead+0.056
 working+0.055
 End+0.054
Neg logit contributions
 Pen-0.067
nes-0.062
den-0.059
igator-0.059
Pen-0.058
Token the
Token ID262
Feature activation+1.38e-02

Pos logit contributions
 accidents+0.179
ead+0.174
Time+0.174
aping+0.168
ucking+0.166
Neg logit contributions
 Pen-0.194
nes-0.180
igator-0.174
den-0.172
icity-0.167
Token truth
Token ID3872
Feature activation+1.65e-01

Pos logit contributions
 Pen+0.020
nes+0.019
den+0.018
igator+0.018
Pen+0.017
Neg logit contributions
 accidents-0.024
Time-0.023
 working-0.022
ead-0.022
 End-0.022
Token.
Token ID13
Feature activation-1.82e-02

Pos logit contributions
 Pen+0.345
nam+0.332
Pen+0.331
nes+0.324
icity+0.319
Neg logit contributions
 accidents-0.178
 working-0.164
Time-0.149
ores-0.144
rou-0.144
Token She
Token ID1375
Feature activation-3.23e-02

Pos logit contributions
 accidents+0.028
 working+0.026
Time+0.026
aping+0.026
ead+0.025
Neg logit contributions
 Pen-0.031
nes-0.027
Pen-0.026
igator-0.025
 Sunny-0.025
Token says
Token ID1139
Feature activation+5.76e-02

Pos logit contributions
 accidents+0.058
ead+0.056
Time+0.056
aping+0.054
ounds+0.054
Neg logit contributions
 Pen-0.043
igator-0.038
nes-0.038
den-0.036
icity-0.036
Token accidents
Token ID17390
Feature activation-3.68e-01

Pos logit contributions
 Pen+0.091
igator+0.080
nes+0.080
 Sunny+0.076
den+0.076
Neg logit contributions
ead-0.089
Time-0.088
aping-0.087
 accidents-0.086
ucking-0.086
Token happen
Token ID1645
Feature activation+6.11e-02

Pos logit contributions
 accidents+0.541
 working+0.474
Time+0.460
 pouring+0.416
ores+0.414
Neg logit contributions
 Pen-0.682
nes-0.648
nam-0.640
Pen-0.636
den-0.625
Token and
Token ID290
Feature activation+6.56e-03

Pos logit contributions
 Pen+0.098
nes+0.093
igator+0.088
den+0.088
icity+0.085
Neg logit contributions
 accidents-0.091
ead-0.090
Time-0.089
aping-0.084
ounds-0.084
Token they
Token ID484
Feature activation-1.01e-02

Pos logit contributions
 Pen+0.011
igator+0.010
nes+0.010
nam+0.010
den+0.010
Neg logit contributions
ead-0.009
Time-0.009
ucking-0.009
 accidents-0.009
ounds-0.009
Token can
Token ID460
Feature activation+3.88e-02

Pos logit contributions
 accidents+0.015
Time+0.014
ead+0.014
 working+0.014
 End+0.014
Neg logit contributions
 Pen-0.017
nes-0.016
igator-0.015
den-0.015
Pen-0.015
Token fix
Token ID4259
Feature activation-5.26e-02

Pos logit contributions
 Pen+0.069
nes+0.066
igator+0.063
den+0.062
Pen+0.061
Neg logit contributions
 accidents-0.054
Time-0.051
ead-0.050
 End-0.048
 working-0.048
Token said
Token ID531
Feature activation+9.37e-02

Pos logit contributions
 Pen+0.002
nes+0.002
igator+0.002
den+0.002
nam+0.002
Neg logit contributions
 accidents-0.003
Time-0.003
ead-0.003
 End-0.003
ucking-0.003
Token it
Token ID340
Feature activation-5.92e-02

Pos logit contributions
 Pen+0.169
nes+0.156
igator+0.151
den+0.148
Pen+0.147
Neg logit contributions
 accidents-0.126
Time-0.123
ead-0.122
aping-0.117
ucking-0.114
Token was
Token ID373
Feature activation-3.64e-02

Pos logit contributions
 accidents+0.071
Time+0.065
 working+0.062
ead+0.062
 End+0.059
Neg logit contributions
 Pen-0.117
nes-0.112
igator-0.109
den-0.107
nam-0.106
Token okay
Token ID8788
Feature activation-1.12e-01

Pos logit contributions
 accidents+0.038
ead+0.038
aping+0.037
Time+0.036
ucking+0.036
Neg logit contributions
 Pen-0.076
nes-0.071
igator-0.070
nam-0.068
Pen-0.068
Token,
Token ID11
Feature activation-7.28e-03

Pos logit contributions
ead+0.183
Time+0.177
aping+0.175
icious+0.173
ucking+0.172
Neg logit contributions
 Pen-0.170
nes-0.149
den-0.143
igator-0.140
Pen-0.139
Token accidents
Token ID17390
Feature activation-3.67e-01

Pos logit contributions
ead+0.014
 accidents+0.014
Time+0.014
aping+0.014
 End+0.014
Neg logit contributions
 Pen-0.008
nes-0.007
igator-0.007
Pen-0.006
den-0.006
Token happen
Token ID1645
Feature activation+6.31e-02

Pos logit contributions
 accidents+0.577
Time+0.516
 working+0.515
ead+0.490
 End+0.476
Neg logit contributions
 Pen-0.616
nes-0.580
den-0.562
Pen-0.553
nam-0.552
Token.
Token ID13
Feature activation-8.38e-03

Pos logit contributions
 Pen+0.096
nes+0.091
den+0.083
igator+0.082
icity+0.080
Neg logit contributions
ead-0.100
Time-0.098
 accidents-0.095
ounds-0.093
icious-0.092
Token They
Token ID1119
Feature activation-2.42e-02

Pos logit contributions
 accidents+0.011
Time+0.010
ead+0.010
 working+0.009
 End+0.009
Neg logit contributions
 Pen-0.016
nes-0.015
igator-0.015
den-0.014
Pen-0.014
Token cleaned
Token ID20750
Feature activation-5.34e-02

Pos logit contributions
 accidents+0.031
 working+0.028
Time+0.028
 End+0.028
rou+0.028
Neg logit contributions
 Pen-0.046
nes-0.043
den-0.041
Pen-0.041
igator-0.041
Token up
Token ID510
Feature activation-1.10e-02

Pos logit contributions
 accidents+0.070
ead+0.062
 working+0.060
Time+0.060
aping+0.059
Neg logit contributions
 Pen-0.102
nes-0.100
igator-0.099
den-0.095
Pen-0.093
Token this
Token ID428
Feature activation+3.57e-02

Pos logit contributions
 Pen+0.314
nam+0.284
nes+0.274
igator+0.262
 Sunshine+0.259
Neg logit contributions
ead-0.337
ucking-0.318
icious-0.316
ounds-0.315
acking-0.314
Token time
Token ID640
Feature activation+1.00e-01

Pos logit contributions
 Pen+0.050
nes+0.046
igator+0.045
den+0.043
icity+0.041
Neg logit contributions
 accidents-0.063
ead-0.061
aping-0.059
Time-0.059
ucking-0.058
Token she
Token ID673
Feature activation-2.78e-02

Pos logit contributions
 Pen+0.150
nam+0.137
nes+0.135
den+0.123
 Amelia+0.122
Neg logit contributions
ead-0.168
Time-0.161
icious-0.160
ucking-0.159
acking-0.156
Token understood
Token ID7247
Feature activation-7.60e-02

Pos logit contributions
 accidents+0.032
Time+0.030
 working+0.029
 End+0.029
ead+0.029
Neg logit contributions
 Pen-0.056
nes-0.053
igator-0.053
nam-0.051
den-0.051
Token that
Token ID326
Feature activation-1.76e-02

Pos logit contributions
 accidents+0.100
Time+0.089
 working+0.088
ead+0.085
 End+0.084
Neg logit contributions
 Pen-0.146
nes-0.142
igator-0.137
den-0.135
Pen-0.134
Token accidents
Token ID17390
Feature activation-3.67e-01

Pos logit contributions
ead+0.026
Time+0.025
ucking+0.025
 accidents+0.025
aping+0.024
Neg logit contributions
 Pen-0.029
nes-0.026
nam-0.026
igator-0.025
den-0.025
Token can
Token ID460
Feature activation+4.02e-02

Pos logit contributions
 accidents+0.566
 working+0.499
Time+0.497
ead+0.456
 pouring+0.452
Neg logit contributions
 Pen-0.642
nes-0.600
den-0.590
Pen-0.587
nam-0.575
Token happen
Token ID1645
Feature activation+6.08e-02

Pos logit contributions
 Pen+0.066
nes+0.065
igator+0.060
den+0.058
icity+0.057
Neg logit contributions
ead-0.057
 accidents-0.057
Time-0.056
joy-0.056
rou-0.054
Token and
Token ID290
Feature activation+8.90e-03

Pos logit contributions
 Pen+0.099
nes+0.094
den+0.088
igator+0.086
icity+0.086
Neg logit contributions
ead-0.088
Time-0.088
 accidents-0.087
 End-0.082
rou-0.082
Token sometimes
Token ID3360
Feature activation+9.32e-02

Pos logit contributions
 Pen+0.013
nam+0.012
nes+0.012
igator+0.012
 Sunny+0.011
Neg logit contributions
ead-0.015
ucking-0.015
icious-0.014
Time-0.014
acking-0.014
Token things
Token ID1243
Feature activation-6.38e-02

Pos logit contributions
 Pen+0.145
nam+0.134
nes+0.131
icity+0.121
 Sunny+0.120
Neg logit contributions
ead-0.151
ucking-0.146
Time-0.143
rou-0.142
icious-0.141
Token She
Token ID1375
Feature activation-3.11e-02

Pos logit contributions
 accidents+0.011
Time+0.010
ead+0.010
 working+0.010
aded+0.010
Neg logit contributions
 Pen-0.013
nes-0.012
Pen-0.011
nam-0.011
den-0.011
Token also
Token ID635
Feature activation+7.09e-02

Pos logit contributions
 accidents+0.042
Time+0.040
ead+0.039
 working+0.038
 End+0.037
Neg logit contributions
 Pen-0.056
nes-0.053
igator-0.051
den-0.051
Pen-0.050
Token learned
Token ID4499
Feature activation-5.76e-02

Pos logit contributions
 Pen+0.121
nes+0.116
igator+0.114
nam+0.111
den+0.110
Neg logit contributions
 accidents-0.098
Time-0.095
ead-0.093
ucking-0.089
ounds-0.087
Token that
Token ID326
Feature activation-1.66e-02

Pos logit contributions
 accidents+0.064
 working+0.051
Time+0.048
rou+0.048
ead+0.046
Neg logit contributions
 Pen-0.131
nes-0.126
igator-0.126
den-0.124
Pen-0.121
Token sometimes
Token ID3360
Feature activation+9.31e-02

Pos logit contributions
ead+0.024
icious+0.023
acking+0.023
Time+0.023
ucking+0.023
Neg logit contributions
 Pen-0.028
nam-0.025
nes-0.024
igator-0.024
 Sunny-0.023
Token accidents
Token ID17390
Feature activation-3.67e-01

Pos logit contributions
 Pen+0.146
nam+0.133
nes+0.124
 Sunny+0.122
 Sunshine+0.121
Neg logit contributions
ead-0.147
rou-0.144
ucking-0.142
acking-0.140
icious-0.140
Token happen
Token ID1645
Feature activation+6.03e-02

Pos logit contributions
 accidents+0.572
 working+0.505
Time+0.500
ead+0.475
aping+0.458
Neg logit contributions
 Pen-0.635
nes-0.599
den-0.583
Pen-0.575
igator-0.566
Token and
Token ID290
Feature activation+1.06e-02

Pos logit contributions
 Pen+0.088
nes+0.080
den+0.077
icity+0.074
igator+0.074
Neg logit contributions
ead-0.097
Time-0.096
 accidents-0.092
icious-0.091
 End-0.091
Token it
Token ID340
Feature activation-5.13e-02

Pos logit contributions
 Pen+0.016
nam+0.015
nes+0.014
igator+0.014
den+0.013
Neg logit contributions
ead-0.017
ucking-0.016
Time-0.016
icious-0.016
aming-0.016
Token's
Token ID338
Feature activation-7.70e-03

Pos logit contributions
 accidents+0.075
Time+0.073
ead+0.073
 End+0.069
ucking+0.068
Neg logit contributions
 Pen-0.085
nes-0.079
igator-0.077
den-0.075
Pen-0.074
Token okay
Token ID8788
Feature activation-1.09e-01

Pos logit contributions
ead+0.010
 accidents+0.010
ucking+0.010
ounds+0.010
Time+0.010
Neg logit contributions
 Pen-0.013
nes-0.013
nam-0.013
igator-0.012
icity-0.012
Token€
Token ID26391
Feature activation+2.17e-01

Pos logit contributions
 Pen+0.176
nes+0.168
igator+0.166
den+0.157
Pen+0.152
Neg logit contributions
 accidents-0.181
ead-0.166
rou-0.163
Time-0.162
 working-0.162
Tokenâ„¢
Token ID8151
Feature activation+4.80e-02

Pos logit contributions
 Pen+0.372
nes+0.347
den+0.318
Pen+0.314
 Robbie+0.311
Neg logit contributions
 accidents-0.328
Time-0.300
 End-0.298
ead-0.292
aping-0.291
Tokens
Token ID82
Feature activation+4.26e-02

Pos logit contributions
 Pen+0.088
nam+0.084
nes+0.083
icity+0.082
den+0.081
Neg logit contributions
 accidents-0.058
rou-0.057
uck-0.056
ead-0.055
ounds-0.055
Token ok
Token ID12876
Feature activation-8.20e-02

Pos logit contributions
 Pen+0.069
nes+0.064
igator+0.063
den+0.060
icity+0.059
Neg logit contributions
ead-0.064
 accidents-0.063
Time-0.062
ucking-0.061
aping-0.061
Token,
Token ID11
Feature activation-2.83e-03

Pos logit contributions
 accidents+0.112
Time+0.105
ead+0.103
 working+0.100
 End+0.099
Neg logit contributions
 Pen-0.148
nes-0.141
igator-0.136
den-0.134
Pen-0.131
Token accidents
Token ID17390
Feature activation-3.67e-01

Pos logit contributions
 accidents+0.004
ead+0.004
Time+0.004
aping+0.004
 working+0.004
Neg logit contributions
 Pen-0.005
nes-0.004
igator-0.004
den-0.004
Pen-0.004
Token happen
Token ID1645
Feature activation+6.31e-02

Pos logit contributions
 accidents+0.542
 working+0.485
Time+0.480
 Good+0.434
rou+0.433
Neg logit contributions
 Pen-0.642
nes-0.610
nam-0.610
Pen-0.590
den-0.589
Token.
Token ID13
Feature activation-9.49e-03

Pos logit contributions
 Pen+0.110
nes+0.103
igator+0.099
den+0.098
Pen+0.095
Neg logit contributions
 accidents-0.089
ead-0.085
Time-0.085
aping-0.080
 End-0.080
Token Let
Token ID3914
Feature activation-6.62e-02

Pos logit contributions
 accidents+0.012
Time+0.011
ead+0.011
 working+0.010
 End+0.010
Neg logit contributions
 Pen-0.018
nes-0.017
igator-0.017
den-0.017
Pen-0.016
Tokenâ
Token ID22940
Feature activation+1.12e-01

Pos logit contributions
 accidents+0.079
Time+0.075
ead+0.070
uck+0.068
 working+0.067
Neg logit contributions
 Pen-0.131
nes-0.125
nam-0.123
igator-0.122
den-0.121
Token€
Token ID26391
Feature activation+2.17e-01

Pos logit contributions
 Pen+0.161
nes+0.152
igator+0.147
den+0.142
Pen+0.137
Neg logit contributions
 accidents-0.194
Time-0.182
ead-0.181
 working-0.177
rou-0.175
Token her
Token ID607
Feature activation+6.61e-02

Pos logit contributions
 accidents+0.068
Time+0.064
uck+0.058
eared+0.057
 working+0.056
Neg logit contributions
 Pen-0.094
nes-0.091
icity-0.087
igator-0.087
nam-0.087
Token and
Token ID290
Feature activation+1.12e-02

Pos logit contributions
 Pen+0.128
nes+0.123
igator+0.118
Pen+0.117
den+0.116
Neg logit contributions
 accidents-0.084
 working-0.077
ead-0.075
 End-0.074
Time-0.073
Token told
Token ID1297
Feature activation+3.04e-02

Pos logit contributions
 Pen+0.015
nes+0.014
igator+0.014
nam+0.013
den+0.013
Neg logit contributions
ead-0.020
 accidents-0.019
ounds-0.019
Time-0.019
ucking-0.019
Token her
Token ID607
Feature activation+6.58e-02

Pos logit contributions
 Pen+0.046
nes+0.043
igator+0.041
den+0.040
Pen+0.039
Neg logit contributions
 accidents-0.050
ead-0.048
Time-0.048
aping-0.046
 working-0.046
Token that
Token ID326
Feature activation-1.68e-02

Pos logit contributions
 Pen+0.108
nes+0.102
igator+0.099
den+0.098
nam+0.094
Neg logit contributions
ead-0.097
Time-0.095
icious-0.092
 accidents-0.092
aping-0.090
Token accidents
Token ID17390
Feature activation-3.67e-01

Pos logit contributions
ead+0.025
Time+0.024
 accidents+0.024
icious+0.024
ounds+0.024
Neg logit contributions
 Pen-0.027
nes-0.025
nam-0.024
igator-0.024
den-0.024
Token happen
Token ID1645
Feature activation+6.14e-02

Pos logit contributions
 accidents+0.576
 working+0.511
Time+0.508
ead+0.475
rou+0.465
Neg logit contributions
 Pen-0.629
nes-0.589
den-0.571
Pen-0.569
nam-0.556
Token,
Token ID11
Feature activation-2.92e-03

Pos logit contributions
 Pen+0.086
nes+0.082
den+0.077
igator+0.073
icity+0.073
Neg logit contributions
ead-0.103
Time-0.099
icious-0.095
ucking-0.095
ounds-0.095
Token but
Token ID475
Feature activation+2.01e-01

Pos logit contributions
 accidents+0.005
ead+0.005
Time+0.005
 End+0.005
aping+0.005
Neg logit contributions
 Pen-0.004
nes-0.004
igator-0.004
den-0.003
nam-0.003
Token it
Token ID340
Feature activation-5.07e-02

Pos logit contributions
 Pen+0.350
nes+0.327
igator+0.318
nam+0.311
den+0.307
Neg logit contributions
ead-0.275
 accidents-0.272
Time-0.267
ucking-0.258
ounds-0.257
Token's
Token ID338
Feature activation-7.23e-03

Pos logit contributions
 accidents+0.071
Time+0.067
ead+0.067
 working+0.064
 End+0.063
Neg logit contributions
 Pen-0.089
nes-0.084
igator-0.081
den-0.080
Pen-0.078
Token "
Token ID366
Feature activation-1.05e-01

Pos logit contributions
 accidents+0.007
Time+0.006
ead+0.006
aping+0.006
rou+0.006
Neg logit contributions
 Pen-0.013
nes-0.012
igator-0.012
den-0.012
Pen-0.012
TokenIt
Token ID1026
Feature activation-1.94e-01

Pos logit contributions
 accidents+0.117
ead+0.107
 working+0.103
Time+0.103
 End+0.100
Neg logit contributions
 Pen-0.217
nes-0.205
igator-0.198
den-0.198
Pen-0.196
Token's
Token ID338
Feature activation-7.35e-03

Pos logit contributions
 accidents+0.285
ead+0.276
Time+0.275
 End+0.264
ucking+0.258
Neg logit contributions
 Pen-0.332
nes-0.305
igator-0.299
den-0.294
Pen-0.284
Token alright
Token ID23036
Feature activation-9.74e-02

Pos logit contributions
ead+0.009
ucking+0.009
aping+0.009
 accidents+0.009
ounds+0.008
Neg logit contributions
 Pen-0.014
nes-0.013
icity-0.013
igator-0.013
Pen-0.012
Token,
Token ID11
Feature activation-6.65e-03

Pos logit contributions
 accidents+0.136
Time+0.129
ead+0.129
aping+0.123
 working+0.122
Neg logit contributions
 Pen-0.173
nes-0.161
igator-0.155
den-0.154
Pen-0.151
Token accidents
Token ID17390
Feature activation-3.67e-01

Pos logit contributions
ead+0.009
 accidents+0.009
Time+0.009
aping+0.009
ucking+0.009
Neg logit contributions
 Pen-0.012
nes-0.010
igator-0.010
den-0.010
Pen-0.010
Token happen
Token ID1645
Feature activation+6.40e-02

Pos logit contributions
 accidents+0.551
 working+0.494
Time+0.490
 pouring+0.449
ores+0.449
Neg logit contributions
 Pen-0.627
nes-0.594
nam-0.587
den-0.581
Pen-0.571
Token.
Token ID13
Feature activation-1.09e-02

Pos logit contributions
 Pen+0.100
nes+0.093
den+0.087
igator+0.086
icity+0.084
Neg logit contributions
 accidents-0.102
ead-0.099
Time-0.099
aping-0.094
 End-0.094
Token Let
Token ID3914
Feature activation-6.61e-02

Pos logit contributions
 accidents+0.013
Time+0.012
ead+0.012
 working+0.012
 End+0.011
Neg logit contributions
 Pen-0.022
nes-0.020
igator-0.019
den-0.019
Pen-0.019
Token's
Token ID338
Feature activation-7.84e-03

Pos logit contributions
 accidents+0.084
Time+0.078
ead+0.074
 working+0.072
 End+0.071
Neg logit contributions
 Pen-0.126
nes-0.120
igator-0.118
den-0.117
nam-0.117
Token get
Token ID651
Feature activation-1.17e-01

Pos logit contributions
 accidents+0.010
Time+0.009
ead+0.009
aping+0.009
ucking+0.009
Neg logit contributions
 Pen-0.015
nes-0.014
igator-0.014
den-0.014
icity-0.013
Token it
Token ID340
Feature activation-5.54e-02

Pos logit contributions
 Pen+0.106
nes+0.100
igator+0.097
den+0.095
Pen+0.095
Neg logit contributions
 accidents-0.075
Time-0.069
ead-0.067
 working-0.067
 End-0.065
Token was
Token ID373
Feature activation-3.37e-02

Pos logit contributions
 accidents+0.070
Time+0.064
 working+0.062
ead+0.062
 End+0.059
Neg logit contributions
 Pen-0.105
nes-0.101
igator-0.098
den-0.096
Pen-0.096
Token okay
Token ID8788
Feature activation-1.10e-01

Pos logit contributions
 accidents+0.045
ead+0.044
aping+0.042
Time+0.042
ucking+0.042
Neg logit contributions
 Pen-0.061
nes-0.057
igator-0.056
den-0.054
Pen-0.054
Token and
Token ID290
Feature activation+6.60e-03

Pos logit contributions
 accidents+0.158
Time+0.149
ead+0.148
 working+0.141
 End+0.141
Neg logit contributions
 Pen-0.191
nes-0.180
igator-0.173
den-0.171
Pen-0.167
Token that
Token ID326
Feature activation-1.96e-02

Pos logit contributions
 Pen+0.011
nes+0.010
igator+0.010
den+0.010
nam+0.009
Neg logit contributions
ead-0.010
 accidents-0.010
Time-0.009
ounds-0.009
ucking-0.009
Token accidents
Token ID17390
Feature activation-3.66e-01

Pos logit contributions
 accidents+0.027
ead+0.025
Time+0.025
aping+0.024
 End+0.024
Neg logit contributions
 Pen-0.035
nes-0.033
igator-0.032
den-0.031
Pen-0.031
Token happen
Token ID1645
Feature activation+6.58e-02

Pos logit contributions
 accidents+0.551
 working+0.484
Time+0.466
 pouring+0.425
ores+0.423
Neg logit contributions
 Pen-0.657
nes-0.621
Pen-0.607
nam-0.601
den-0.601
Token.
Token ID13
Feature activation-1.25e-02

Pos logit contributions
 Pen+0.112
nes+0.106
den+0.100
igator+0.100
icity+0.096
Neg logit contributions
 accidents-0.092
ead-0.092
Time-0.091
aping-0.085
ounds-0.085
Token They
Token ID1119
Feature activation-2.39e-02

Pos logit contributions
 accidents+0.015
Time+0.014
ead+0.014
 Good+0.013
 End+0.013
Neg logit contributions
 Pen-0.024
nes-0.023
igator-0.023
den-0.023
icity-0.022
Token cleaned
Token ID20750
Feature activation-5.21e-02

Pos logit contributions
 accidents+0.030
 working+0.029
Time+0.028
 End+0.028
rou+0.027
Neg logit contributions
 Pen-0.045
nes-0.042
Pen-0.041
den-0.040
igator-0.039
Token up
Token ID510
Feature activation-1.06e-02

Pos logit contributions
 accidents+0.065
ead+0.055
 working+0.055
aping+0.053
Time+0.053
Neg logit contributions
nes-0.104
 Pen-0.102
igator-0.099
Pen-0.096
den-0.095
Token need
Token ID761
Feature activation-2.83e-02

Pos logit contributions
 Pen+0.015
nes+0.014
igator+0.014
den+0.013
Pen+0.013
Neg logit contributions
 accidents-0.012
Time-0.011
ead-0.011
 End-0.010
aping-0.010
Token it
Token ID340
Feature activation-5.02e-02

Pos logit contributions
ucking+0.045
rou+0.045
Time+0.045
icious+0.044
 End+0.043
Neg logit contributions
 Pen-0.042
nes-0.036
igator-0.036
nam-0.036
 Sunny-0.035
Token,
Token ID11
Feature activation-4.73e-03

Pos logit contributions
 accidents+0.069
Time+0.065
ead+0.064
 working+0.062
 End+0.061
Neg logit contributions
 Pen-0.090
nes-0.085
igator-0.082
den-0.080
Pen-0.079
Token and
Token ID290
Feature activation+9.35e-03

Pos logit contributions
 accidents+0.008
Time+0.008
ead+0.008
 End+0.008
aping+0.008
Neg logit contributions
 Pen-0.007
nes-0.006
igator-0.006
den-0.006
Pen-0.006
Token that
Token ID326
Feature activation-1.70e-02

Pos logit contributions
 Pen+0.015
nes+0.013
nam+0.013
igator+0.013
otte+0.013
Neg logit contributions
Time-0.014
ead-0.014
 accidents-0.014
ounds-0.013
icious-0.013
Token accidents
Token ID17390
Feature activation-3.66e-01

Pos logit contributions
ead+0.025
Time+0.025
eared+0.024
rou+0.024
acking+0.024
Neg logit contributions
 Pen-0.027
nam-0.025
igator-0.024
 Sunny-0.024
nes-0.023
Token happen
Token ID1645
Feature activation+6.25e-02

Pos logit contributions
 accidents+0.547
 working+0.482
Time+0.474
ead+0.438
 pouring+0.433
Neg logit contributions
 Pen-0.655
nes-0.609
den-0.607
Pen-0.598
nam-0.593
Token.
Token ID13
Feature activation-1.15e-02

Pos logit contributions
 Pen+0.100
nes+0.095
igator+0.089
den+0.089
icity+0.085
Neg logit contributions
ead-0.093
 accidents-0.093
Time-0.092
ucking-0.086
 End-0.086
Token Ho
Token ID9544
Feature activation+1.59e-01

Pos logit contributions
 accidents+0.021
Time+0.020
ead+0.019
 working+0.019
 End+0.019
Neg logit contributions
 Pen-0.016
nes-0.015
igator-0.014
den-0.014
Pen-0.013
Tokenpper
Token ID2848
Feature activation+1.51e-01

Pos logit contributions
 Pen+0.204
nes+0.187
igator+0.179
den+0.175
Pen+0.169
Neg logit contributions
 accidents-0.303
Time-0.290
ead-0.288
 working-0.280
 End-0.278
Token learned
Token ID4499
Feature activation-5.85e-02

Pos logit contributions
 Pen+0.263
nes+0.244
igator+0.242
den+0.232
Pen+0.226
Neg logit contributions
 accidents-0.212
Time-0.206
ead-0.202
ucking-0.190
 working-0.188
Token with
Token ID351
Feature activation-2.11e-02

Pos logit contributions
 accidents+0.177
 working+0.155
Time+0.152
uck+0.148
aping+0.148
Neg logit contributions
 Pen-0.278
nes-0.266
igator-0.264
den-0.259
Pen-0.259
Token the
Token ID262
Feature activation+1.81e-02

Pos logit contributions
 accidents+0.029
Time+0.026
 working+0.026
ead+0.026
 End+0.025
Neg logit contributions
 Pen-0.039
nes-0.038
igator-0.036
den-0.036
Pen-0.035
Token chores
Token ID46173
Feature activation+1.27e-01

Pos logit contributions
 Pen+0.029
nes+0.028
igator+0.026
den+0.026
Pen+0.025
Neg logit contributions
 accidents-0.029
Time-0.027
ead-0.027
 working-0.026
 End-0.026
Token can
Token ID460
Feature activation+3.92e-02

Pos logit contributions
 Pen+0.292
Pen+0.291
Flash+0.277
den+0.274
icity+0.273
Neg logit contributions
 accidents-0.108
 working-0.106
 End-0.087
uck-0.086
less-0.086
Token prevent
Token ID2948
Feature activation-1.33e-01

Pos logit contributions
 Pen+0.075
nes+0.071
igator+0.069
den+0.068
Pen+0.067
Neg logit contributions
 accidents-0.049
Time-0.046
ead-0.045
 working-0.043
 End-0.043
Token accidents
Token ID17390
Feature activation-3.66e-01

Pos logit contributions
 accidents+0.185
ead+0.168
Time+0.168
 working+0.164
 End+0.158
Neg logit contributions
 Pen-0.242
nes-0.231
igator-0.225
den-0.221
Pen-0.216
Token and
Token ID290
Feature activation+9.30e-03

Pos logit contributions
 accidents+0.557
Time+0.525
ead+0.519
 working+0.503
 End+0.496
Neg logit contributions
 Pen-0.605
nes-0.568
igator-0.547
den-0.539
Pen-0.528
Token save
Token ID3613
Feature activation-8.29e-02

Pos logit contributions
nam+0.015
 Pen+0.015
nes+0.014
igator+0.014
 tant+0.013
Neg logit contributions
ead-0.013
ucking-0.013
joy-0.013
Time-0.013
anging-0.013
Token things
Token ID1243
Feature activation-6.13e-02

Pos logit contributions
 accidents+0.111
 working+0.098
ead+0.096
Time+0.096
aping+0.091
Neg logit contributions
 Pen-0.157
nes-0.149
igator-0.148
den-0.145
Pen-0.143
Token we
Token ID356
Feature activation-4.07e-02

Pos logit contributions
 accidents+0.084
 working+0.075
Time+0.074
ead+0.074
aping+0.070
Neg logit contributions
 Pen-0.115
nes-0.107
igator-0.105
den-0.105
Pen-0.104
Token love
Token ID1842
Feature activation-3.98e-02

Pos logit contributions
 accidents+0.052
ead+0.048
 working+0.048
Time+0.048
 End+0.046
Neg logit contributions
 Pen-0.078
nes-0.072
Pen-0.070
den-0.069
igator-0.069
Token house
Token ID2156
Feature activation-1.25e-01

Pos logit contributions
 Pen+0.039
nes+0.037
igator+0.035
nam+0.035
 tant+0.034
Neg logit contributions
Time-0.026
 accidents-0.026
ead-0.026
aping-0.025
icious-0.025
Token and
Token ID290
Feature activation+9.97e-03

Pos logit contributions
Time+0.195
 accidents+0.192
ead+0.187
 End+0.184
 Good+0.180
Neg logit contributions
 Pen-0.188
nes-0.179
igator-0.170
nam-0.164
den-0.163
Token told
Token ID1297
Feature activation+3.00e-02

Pos logit contributions
 Pen+0.014
nam+0.013
nes+0.013
igator+0.013
otte+0.012
Neg logit contributions
icious-0.016
ead-0.016
ounds-0.016
Time-0.016
 End-0.016
Token her
Token ID607
Feature activation+6.63e-02

Pos logit contributions
 Pen+0.045
nes+0.041
igator+0.040
den+0.039
nam+0.039
Neg logit contributions
 accidents-0.048
ead-0.048
Time-0.048
aping-0.046
rou-0.046
Token that
Token ID326
Feature activation-1.65e-02

Pos logit contributions
 Pen+0.101
nes+0.094
igator+0.089
den+0.088
nam+0.086
Neg logit contributions
Time-0.104
ead-0.104
icious-0.104
 End-0.099
phony-0.099
Token accidents
Token ID17390
Feature activation-3.66e-01

Pos logit contributions
ead+0.025
icious+0.024
Time+0.024
ucking+0.024
acking+0.023
Neg logit contributions
 Pen-0.026
nam-0.025
igator-0.023
nes-0.023
 Sunny-0.022
Token happen
Token ID1645
Feature activation+6.20e-02

Pos logit contributions
 accidents+0.586
Time+0.536
 working+0.526
ead+0.520
aping+0.501
Neg logit contributions
 Pen-0.599
nes-0.560
den-0.538
igator-0.532
Pen-0.531
Token.
Token ID13
Feature activation-1.00e-02

Pos logit contributions
 Pen+0.081
nes+0.077
den+0.071
icity+0.069
igator+0.068
Neg logit contributions
ead-0.106
Time-0.105
icious-0.099
phony-0.099
ucking-0.098
Token Lily
Token ID20037
Feature activation-2.95e-02

Pos logit contributions
Time+0.015
 accidents+0.015
 End+0.014
 working+0.014
ucking+0.014
Neg logit contributions
 Pen-0.017
nes-0.015
igator-0.014
nam-0.014
 Sunny-0.014
Token felt
Token ID2936
Feature activation-4.10e-02

Pos logit contributions
 accidents+0.043
Time+0.043
ead+0.041
ores+0.039
joy+0.039
Neg logit contributions
 Pen-0.049
nes-0.046
den-0.043
igator-0.043
icity-0.042
Token better
Token ID1365
Feature activation-1.18e-01

Pos logit contributions
ead+0.056
Time+0.054
phony+0.053
aping+0.053
ounds+0.053
Neg logit contributions
 Pen-0.066
igator-0.064
nam-0.064
nes-0.062
 tant-0.061
Token that
Token ID326
Feature activation-1.31e-02

Pos logit contributions
 Pen+0.120
nes+0.113
igator+0.109
den+0.108
Pen+0.105
Neg logit contributions
 accidents-0.095
Time-0.091
ead-0.091
aping-0.086
 End-0.085
Token it
Token ID340
Feature activation-4.62e-02

Pos logit contributions
 accidents+0.018
Time+0.017
ead+0.017
 working+0.016
 End+0.016
Neg logit contributions
 Pen-0.023
nes-0.022
igator-0.021
den-0.021
Pen-0.021
Token was
Token ID373
Feature activation-2.55e-02

Pos logit contributions
 accidents+0.057
Time+0.051
ead+0.050
 working+0.050
aping+0.048
Neg logit contributions
 Pen-0.091
nes-0.086
igator-0.083
den-0.083
Pen-0.082
Token okay
Token ID8788
Feature activation-1.08e-01

Pos logit contributions
ucking+0.037
ead+0.037
aping+0.037
 accidents+0.036
Time+0.036
Neg logit contributions
 Pen-0.041
nes-0.039
igator-0.039
nam-0.036
Pen-0.036
Token and
Token ID290
Feature activation+1.25e-02

Pos logit contributions
ead+0.171
Time+0.168
 accidents+0.165
icious+0.163
 End+0.162
Neg logit contributions
 Pen-0.168
nes-0.151
den-0.145
igator-0.145
Pen-0.138
Token accidents
Token ID17390
Feature activation-3.66e-01

Pos logit contributions
 Pen+0.019
igator+0.017
nes+0.017
nam+0.016
 Sunny+0.016
Neg logit contributions
ead-0.020
Time-0.020
ucking-0.020
icious-0.020
joy-0.020
Token happen
Token ID1645
Feature activation+6.27e-02

Pos logit contributions
 accidents+0.565
 working+0.501
Time+0.497
ead+0.466
 pouring+0.454
Neg logit contributions
 Pen-0.629
nes-0.588
den-0.579
Pen-0.570
nam-0.567
Token to
Token ID284
Feature activation+2.86e-02

Pos logit contributions
 Pen+0.099
nes+0.095
den+0.088
igator+0.086
icity+0.085
Neg logit contributions
ead-0.095
Time-0.094
 accidents-0.093
 End-0.088
ounds-0.088
Token everyone
Token ID2506
Feature activation-6.22e-03

Pos logit contributions
 Pen+0.049
nes+0.046
igator+0.045
den+0.044
Pen+0.043
Neg logit contributions
 accidents-0.042
Time-0.039
ead-0.038
 working-0.037
 End-0.037
Token.
Token ID13
Feature activation-8.56e-03

Pos logit contributions
 accidents+0.009
Time+0.009
ead+0.009
 End+0.008
aping+0.008
Neg logit contributions
 Pen-0.010
nes-0.010
igator-0.010
den-0.009
nam-0.009
Token
Token ID198
Feature activation+2.73e-02

Pos logit contributions
 accidents+0.010
ead+0.009
Time+0.009
 Good+0.008
 End+0.008
Neg logit contributions
igator-0.017
 Pen-0.017
den-0.017
nes-0.017
nam-0.016
Token mistakes
Token ID10135
Feature activation-2.45e-01

Pos logit contributions
Time+0.020
 End+0.020
ead+0.019
 accidents+0.019
aping+0.018
Neg logit contributions
 Pen-0.035
nes-0.033
icity-0.031
Pen-0.030
nam-0.030
Token.
Token ID13
Feature activation-7.40e-03

Pos logit contributions
 accidents+0.382
Time+0.363
ead+0.360
 working+0.346
 End+0.345
Neg logit contributions
 Pen-0.392
nes-0.368
igator-0.353
den-0.347
Pen-0.339
Token We
Token ID775
Feature activation-1.47e-01

Pos logit contributions
 accidents+0.010
Time+0.010
 working+0.010
joy+0.010
ipping+0.010
Neg logit contributions
 Pen-0.013
nes-0.012
Pen-0.011
 Sunny-0.011
igator-0.011
Token all
Token ID477
Feature activation+7.95e-02

Pos logit contributions
 accidents+0.223
Time+0.210
ead+0.209
 working+0.206
 End+0.201
Neg logit contributions
 Pen-0.245
nes-0.226
den-0.218
igator-0.217
Pen-0.215
Token have
Token ID423
Feature activation-1.05e-01

Pos logit contributions
igator+0.126
nes+0.126
 Pen+0.125
 contain+0.115
nam+0.115
Neg logit contributions
 accidents-0.118
Time-0.115
ead-0.114
joy-0.111
ounds-0.111
Token accidents
Token ID17390
Feature activation-3.66e-01

Pos logit contributions
 accidents+0.134
Time+0.129
ead+0.127
 End+0.122
aping+0.121
Neg logit contributions
 Pen-0.196
nes-0.186
igator-0.176
den-0.175
nam-0.174
Token sometimes
Token ID3360
Feature activation+9.45e-02

Pos logit contributions
 accidents+0.568
 working+0.512
Time+0.502
ead+0.488
rou+0.472
Neg logit contributions
 Pen-0.625
nes-0.575
den-0.571
Pen-0.563
igator-0.561
Token."
Token ID526
Feature activation+1.34e-01

Pos logit contributions
 Pen+0.130
nes+0.122
igator+0.113
den+0.110
nam+0.109
Neg logit contributions
 accidents-0.164
Time-0.161
ead-0.159
rou-0.155
aping-0.154
Token Lily
Token ID20037
Feature activation-2.86e-02

Pos logit contributions
 Pen+0.234
nes+0.220
igator+0.208
den+0.206
Pen+0.204
Neg logit contributions
 accidents-0.192
Time-0.182
ead-0.178
 working-0.174
 End-0.172
Token felt
Token ID2936
Feature activation-4.03e-02

Pos logit contributions
 accidents+0.039
Time+0.037
ead+0.036
 working+0.035
 End+0.034
Neg logit contributions
 Pen-0.051
nes-0.048
igator-0.046
den-0.046
Pen-0.045
Token better
Token ID1365
Feature activation-1.16e-01

Pos logit contributions
ead+0.048
 accidents+0.047
Time+0.046
aping+0.045
ounds+0.045
Neg logit contributions
 Pen-0.076
nes-0.072
igator-0.071
nam-0.069
Pen-0.067
Token sad
Token ID6507
Feature activation-4.16e-03

Pos logit contributions
ead+0.061
 accidents+0.060
aping+0.059
Time+0.059
ucking+0.057
Neg logit contributions
 Pen-0.068
igator-0.063
nes-0.062
nam-0.060
Pen-0.059
Token but
Token ID475
Feature activation+2.01e-01

Pos logit contributions
Time+0.007
ead+0.006
 accidents+0.006
aping+0.006
ounds+0.006
Neg logit contributions
 Pen-0.006
nes-0.006
den-0.005
igator-0.005
icity-0.005
Token she
Token ID673
Feature activation-2.74e-02

Pos logit contributions
 Pen+0.327
nam+0.296
 Sunny+0.274
otte+0.267
 Sunshine+0.267
Neg logit contributions
ead-0.319
acking-0.303
ounds-0.301
ipping-0.301
icious-0.300
Token knew
Token ID2993
Feature activation-2.80e-02

Pos logit contributions
 accidents+0.035
Time+0.033
ead+0.033
 working+0.031
aping+0.031
Neg logit contributions
 Pen-0.052
nes-0.049
igator-0.047
den-0.047
Pen-0.046
Token that
Token ID326
Feature activation-1.66e-02

Pos logit contributions
 accidents+0.040
ead+0.038
Time+0.038
aping+0.036
ucking+0.036
Neg logit contributions
 Pen-0.049
nes-0.045
igator-0.043
den-0.043
Pen-0.042
Token accidents
Token ID17390
Feature activation-3.66e-01

Pos logit contributions
ead+0.023
ucking+0.022
Time+0.022
aping+0.022
 accidents+0.022
Neg logit contributions
 Pen-0.029
nam-0.025
nes-0.025
igator-0.024
 Sunny-0.024
Token happen
Token ID1645
Feature activation+6.31e-02

Pos logit contributions
 accidents+0.554
 working+0.481
Time+0.476
 pouring+0.437
ores+0.427
Neg logit contributions
 Pen-0.654
nes-0.623
den-0.610
Pen-0.606
nam-0.599
Token sometimes
Token ID3360
Feature activation+9.30e-02

Pos logit contributions
 Pen+0.102
nes+0.094
den+0.089
igator+0.088
icity+0.087
Neg logit contributions
ead-0.094
 accidents-0.093
Time-0.092
ounds-0.088
aping-0.088
Token.
Token ID13
Feature activation-7.77e-03

Pos logit contributions
 Pen+0.151
nes+0.136
den+0.130
icity+0.130
igator+0.129
Neg logit contributions
ead-0.138
Time-0.136
 accidents-0.135
rou-0.133
aping-0.132
Token She
Token ID1375
Feature activation-3.08e-02

Pos logit contributions
 accidents+0.013
Time+0.012
 working+0.012
ead+0.012
 End+0.011
Neg logit contributions
 Pen-0.012
nes-0.011
igator-0.011
Pen-0.010
den-0.010
Token cleaned
Token ID20750
Feature activation-5.35e-02

Pos logit contributions
 accidents+0.041
Time+0.038
ead+0.038
 working+0.036
 End+0.036
Neg logit contributions
 Pen-0.057
nes-0.054
igator-0.052
den-0.051
Pen-0.050
Token
Token ID198
Feature activation+3.02e-02

Pos logit contributions
 Pen+0.160
nes+0.151
igator+0.145
den+0.143
Pen+0.140
Neg logit contributions
 accidents-0.129
Time-0.121
ead-0.120
 working-0.116
 End-0.114
Token
Token ID198
Feature activation+3.00e-02

Pos logit contributions
igator+0.060
 Pen+0.058
nes+0.058
nam+0.057
den+0.056
Neg logit contributions
Time-0.034
 End-0.032
 accidents-0.032
 working-0.030
 Good-0.030
TokenAfter
Token ID3260
Feature activation-1.61e-01

Pos logit contributions
 Pen+0.048
nes+0.045
igator+0.045
den+0.043
nam+0.043
Neg logit contributions
 accidents-0.046
Time-0.045
 End-0.043
ead-0.042
 working-0.042
Token meals
Token ID13840
Feature activation+8.55e-03

Pos logit contributions
 accidents+0.214
ead+0.207
Time+0.203
aping+0.198
ucking+0.195
Neg logit contributions
 Pen-0.298
nes-0.271
den-0.260
igator-0.260
Pen-0.258
Token,
Token ID11
Feature activation+7.98e-04

Pos logit contributions
 Pen+0.016
nes+0.015
igator+0.015
nam+0.015
Pen+0.015
Neg logit contributions
 accidents-0.011
 working-0.010
Time-0.010
 End-0.010
ead-0.009
Token Annie
Token ID25860
Feature activation+2.79e-01

Pos logit contributions
igator+0.001
nes+0.001
 Pen+0.001
nam+0.001
 tant+0.001
Neg logit contributions
 accidents-0.002
 working-0.001
Time-0.001
 End-0.001
 Good-0.001
Token would
Token ID561
Feature activation+1.72e-01

Pos logit contributions
 Pen+0.523
nes+0.494
igator+0.478
den+0.472
Pen+0.463
Neg logit contributions
 accidents-0.362
Time-0.339
ead-0.335
 working-0.321
 End-0.318
Token take
Token ID1011
Feature activation-5.28e-02

Pos logit contributions
 Pen+0.320
nes+0.300
igator+0.293
den+0.285
Pen+0.281
Neg logit contributions
 accidents-0.229
Time-0.211
ead-0.211
aping-0.202
ucking-0.198
Token the
Token ID262
Feature activation+2.49e-02

Pos logit contributions
 accidents+0.067
Time+0.063
ead+0.062
 working+0.060
 End+0.058
Neg logit contributions
 Pen-0.097
nes-0.096
igator-0.095
nam-0.091
den-0.091
Token car
Token ID1097
Feature activation+1.21e-02

Pos logit contributions
 Pen+0.047
nes+0.047
Pen+0.044
den+0.044
icity+0.044
Neg logit contributions
 accidents-0.034
 working-0.030
Time-0.030
 End-0.030
ead-0.029
Token outside
Token ID2354
Feature activation-1.56e-02

Pos logit contributions
 Pen+0.024
nes+0.022
igator+0.021
den+0.021
Pen+0.021
Neg logit contributions
 accidents-0.015
Time-0.014
ead-0.014
 working-0.013
aping-0.013
Token
Token ID198
Feature activation+3.03e-02

Pos logit contributions
igator+0.062
 Pen+0.061
nes+0.059
den+0.059
nam+0.059
Neg logit contributions
Time-0.032
 accidents-0.030
ead-0.029
aping-0.029
Nothing-0.028
TokenHer
Token ID9360
Feature activation+8.31e-02

Pos logit contributions
 Pen+0.062
nes+0.058
igator+0.058
den+0.057
icity+0.055
Neg logit contributions
 accidents-0.034
Time-0.033
ead-0.031
 End-0.030
 working-0.030
Token mom
Token ID1995
Feature activation+3.08e-02

Pos logit contributions
 Pen+0.154
nes+0.149
igator+0.145
den+0.142
Pen+0.139
Neg logit contributions
 accidents-0.111
ead-0.101
Time-0.100
 working-0.099
 End-0.099
Tokenmy
Token ID1820
Feature activation-1.27e-01

Pos logit contributions
 Pen+0.058
den+0.053
nes+0.052
igator+0.052
Pen+0.050
Neg logit contributions
 accidents-0.041
ead-0.038
Time-0.038
ounds-0.035
ores-0.035
Token said
Token ID531
Feature activation+1.07e-01

Pos logit contributions
 accidents+0.201
Time+0.191
ead+0.189
 working+0.180
 End+0.180
Neg logit contributions
 Pen-0.204
nes-0.188
igator-0.182
den-0.181
Pen-0.175
Token yes
Token ID3763
Feature activation+2.80e-01

Pos logit contributions
 Pen+0.196
nes+0.188
igator+0.182
den+0.179
Pen+0.176
Neg logit contributions
 accidents-0.142
Time-0.129
ead-0.128
 working-0.126
 End-0.123
Token,
Token ID11
Feature activation+9.39e-04

Pos logit contributions
 Pen+0.536
nes+0.503
igator+0.500
nam+0.487
Pen+0.484
Neg logit contributions
 accidents-0.362
ead-0.332
Time-0.329
 working-0.324
 End-0.311
Token and
Token ID290
Feature activation+1.55e-02

Pos logit contributions
 Pen+0.002
nes+0.001
igator+0.001
den+0.001
Pen+0.001
Neg logit contributions
 accidents-0.001
Time-0.001
ead-0.001
 working-0.001
 End-0.001
Token she
Token ID673
Feature activation-2.46e-02

Pos logit contributions
 Pen+0.028
nes+0.027
igator+0.026
den+0.025
Pen+0.025
Neg logit contributions
 accidents-0.021
Time-0.020
ead-0.019
 working-0.019
aping-0.018
Token went
Token ID1816
Feature activation-1.01e-01

Pos logit contributions
 accidents+0.033
Time+0.031
ead+0.030
 working+0.029
 End+0.029
Neg logit contributions
 Pen-0.045
nes-0.043
igator-0.041
den-0.041
Pen-0.040
Token up
Token ID510
Feature activation-9.90e-03

Pos logit contributions
 accidents+0.179
icious+0.158
Time+0.158
 End+0.158
aping+0.155
Neg logit contributions
 Pen-0.158
nes-0.147
den-0.137
igator-0.134
Pen-0.131
Token y
Token ID331
Feature activation+8.36e-02

Pos logit contributions
 accidents+0.011
ead+0.011
Time+0.011
aping+0.010
 working+0.010
Neg logit contributions
 Pen-0.016
nes-0.015
igator-0.015
den-0.014
Pen-0.014
Tokenummy
Token ID13513
Feature activation-1.73e-01

Pos logit contributions
 Pen+0.153
igator+0.147
icity+0.146
nes+0.145
sie+0.143
Neg logit contributions
Time-0.100
 accidents-0.099
Are-0.098
Nothing-0.097
 working-0.093
Token meal
Token ID9799
Feature activation-1.02e-02

Pos logit contributions
 accidents+0.242
Time+0.228
ead+0.225
 working+0.218
 End+0.216
Neg logit contributions
 Pen-0.304
nes-0.289
igator-0.276
den-0.274
Pen-0.269
Token.
Token ID13
Feature activation-8.24e-03

Pos logit contributions
 accidents+0.012
Time+0.011
 working+0.011
ead+0.011
 End+0.010
Neg logit contributions
 Pen-0.020
nes-0.019
nam-0.018
Pen-0.018
igator-0.018
Token Little
Token ID7703
Feature activation-3.24e-02

Pos logit contributions
Time+0.010
 accidents+0.010
 Good+0.009
ead+0.009
 working+0.009
Neg logit contributions
igator-0.016
nes-0.015
 Pen-0.015
den-0.015
nam-0.015
Token May
Token ID1737
Feature activation+3.49e-01

Pos logit contributions
 accidents+0.072
Time+0.067
joy+0.065
 End+0.065
 Good+0.064
Neg logit contributions
igator-0.035
nes-0.028
nam-0.028
 tant-0.027
 contain-0.027
Token smiled
Token ID13541
Feature activation+2.23e-02

Pos logit contributions
 Pen+0.633
nes+0.600
igator+0.585
den+0.572
Pen+0.564
Neg logit contributions
 accidents-0.462
Time-0.434
ead-0.431
 working-0.417
 End-0.411
Token and
Token ID290
Feature activation+1.28e-02

Pos logit contributions
 Pen+0.034
den+0.029
nes+0.029
 Sunshine+0.029
 Robbie+0.028
Neg logit contributions
Time-0.036
 accidents-0.036
ead-0.035
ounds-0.035
icious-0.034
Token thanked
Token ID26280
Feature activation+7.03e-02

Pos logit contributions
 Pen+0.021
nes+0.020
igator+0.019
den+0.019
Pen+0.018
Neg logit contributions
 accidents-0.020
Time-0.019
ead-0.018
 working-0.018
 End-0.018
Token them
Token ID606
Feature activation+1.47e-02

Pos logit contributions
igator+0.138
nes+0.134
 tant+0.126
 Pen+0.125
den+0.124
Neg logit contributions
 accidents-0.086
 working-0.079
Time-0.077
ead-0.074
 End-0.072
Token for
Token ID329
Feature activation-1.56e-01

Pos logit contributions
 Pen+0.033
nes+0.032
igator+0.031
den+0.031
Pen+0.030
Neg logit contributions
 accidents-0.013
Time-0.012
ead-0.012
 working-0.011
 End-0.011
Token girl
Token ID2576
Feature activation+1.65e-02

Pos logit contributions
 Pen+0.073
igator+0.067
nes+0.066
den+0.063
Pen+0.063
Neg logit contributions
 accidents-0.075
Time-0.072
ead-0.071
aping-0.069
 End-0.069
Token who
Token ID508
Feature activation+1.82e-01

Pos logit contributions
 Pen+0.025
nes+0.023
igator+0.022
den+0.022
Pen+0.021
Neg logit contributions
 accidents-0.028
Time-0.026
ead-0.026
 End-0.025
 working-0.025
Token loved
Token ID6151
Feature activation+4.76e-02

Pos logit contributions
 Pen+0.269
nes+0.241
igator+0.237
Pen+0.227
den+0.227
Neg logit contributions
 accidents-0.320
ead-0.304
aping-0.293
ucking-0.293
Time-0.292
Token pink
Token ID11398
Feature activation-2.06e-02

Pos logit contributions
 Pen+0.083
nes+0.079
igator+0.076
den+0.075
Pen+0.073
Neg logit contributions
 accidents-0.068
Time-0.064
ead-0.063
 working-0.061
 End-0.060
Token.
Token ID13
Feature activation-8.83e-03

Pos logit contributions
 accidents+0.028
ead+0.026
Time+0.025
 working+0.024
 End+0.024
Neg logit contributions
 Pen-0.038
nes-0.037
den-0.035
igator-0.035
icity-0.034
Token Everywhere
Token ID48201
Feature activation+2.89e-01

Pos logit contributions
 accidents+0.011
Time+0.010
ead+0.010
 End+0.009
 working+0.009
Neg logit contributions
 Pen-0.017
nes-0.016
igator-0.016
den-0.016
icity-0.015
Token she
Token ID673
Feature activation-2.69e-02

Pos logit contributions
nes+0.586
 Pen+0.581
den+0.562
igator+0.549
icity+0.540
Neg logit contributions
 accidents-0.329
Time-0.303
 End-0.288
 working-0.282
ead-0.270
Token went
Token ID1816
Feature activation-1.02e-01

Pos logit contributions
 accidents+0.026
Time+0.024
ead+0.023
 working+0.022
 End+0.022
Neg logit contributions
 Pen-0.059
nes-0.057
igator-0.055
den-0.054
Pen-0.054
Token she
Token ID673
Feature activation-2.70e-02

Pos logit contributions
 accidents+0.152
ead+0.146
Time+0.145
rou+0.142
aping+0.140
Neg logit contributions
 Pen-0.172
nes-0.158
igator-0.153
den-0.149
Pen-0.146
Token looked
Token ID3114
Feature activation+5.14e-02

Pos logit contributions
 accidents+0.029
 working+0.029
Time+0.029
ead+0.028
 End+0.027
Neg logit contributions
 Pen-0.052
nes-0.050
igator-0.050
den-0.049
icity-0.048
Token for
Token ID329
Feature activation-1.54e-01

Pos logit contributions
 Pen+0.098
nes+0.092
igator+0.090
den+0.088
nam+0.087
Neg logit contributions
 accidents-0.065
Time-0.062
ead-0.061
aping-0.058
 End-0.058
Token his
Token ID465
Feature activation+5.62e-02

Pos logit contributions
 accidents+0.155
Time+0.139
ead+0.136
 working+0.136
rou+0.131
Neg logit contributions
 Pen-0.226
nes-0.220
Pen-0.205
den-0.205
igator-0.204
Token mom
Token ID1995
Feature activation+2.23e-02

Pos logit contributions
 Pen+0.104
nes+0.099
igator+0.095
den+0.094
Pen+0.093
Neg logit contributions
 accidents-0.075
Time-0.069
ead-0.069
 working-0.067
 End-0.066
Token's
Token ID338
Feature activation-1.26e-02

Pos logit contributions
 Pen+0.038
den+0.034
igator+0.034
 Robbie+0.033
nes+0.033
Neg logit contributions
 accidents-0.030
Time-0.030
ead-0.029
 End-0.029
Nothing-0.028
Token phone
Token ID3072
Feature activation+1.79e-01

Pos logit contributions
 accidents+0.017
Time+0.017
ead+0.016
aping+0.016
ucking+0.015
Neg logit contributions
 Pen-0.022
igator-0.020
nes-0.020
nam-0.020
den-0.020
Token,
Token ID11
Feature activation-8.62e-03

Pos logit contributions
 Pen+0.310
nes+0.282
den+0.279
igator+0.277
icity+0.270
Neg logit contributions
 accidents-0.246
Time-0.244
ead-0.237
 End-0.233
aping-0.227
Token keys
Token ID8251
Feature activation+3.17e-01

Pos logit contributions
 accidents+0.012
Time+0.011
ead+0.011
 working+0.011
 End+0.011
Neg logit contributions
 Pen-0.015
nes-0.014
igator-0.014
den-0.014
Pen-0.013
Token,
Token ID11
Feature activation-6.79e-03

Pos logit contributions
 Pen+0.551
nes+0.518
igator+0.503
den+0.495
Pen+0.479
Neg logit contributions
 accidents-0.447
Time-0.426
ead-0.420
 End-0.401
aping-0.397
Token compact
Token ID16001
Feature activation-3.13e-02

Pos logit contributions
 accidents+0.010
Time+0.009
ead+0.009
 working+0.009
 End+0.009
Neg logit contributions
 Pen-0.012
nes-0.011
igator-0.011
den-0.011
Pen-0.010
Token and
Token ID290
Feature activation+9.11e-03

Pos logit contributions
 accidents+0.044
Time+0.040
ead+0.040
 working+0.039
aping+0.038
Neg logit contributions
 Pen-0.056
nes-0.054
igator-0.051
den-0.050
Pen-0.050
Token lipstick
Token ID41429
Feature activation+8.55e-02

Pos logit contributions
 Pen+0.016
nes+0.015
igator+0.014
nam+0.014
den+0.014
Neg logit contributions
 accidents-0.013
Time-0.012
ead-0.012
ucking-0.012
 End-0.012
Token all
Token ID477
Feature activation+7.82e-02

Pos logit contributions
 Pen+0.148
nes+0.140
den+0.133
igator+0.131
icity+0.130
Neg logit contributions
 accidents-0.118
Time-0.118
 End-0.112
ead-0.110
aping-0.107
Token her
Token ID607
Feature activation+6.47e-02

Pos logit contributions
 accidents+0.134
Time+0.123
 working+0.121
 End+0.121
ead+0.119
Neg logit contributions
nes-0.204
 Pen-0.201
igator-0.187
den-0.187
Pen-0.183
Token gear
Token ID7733
Feature activation+1.09e-01

Pos logit contributions
 Pen+0.125
nes+0.120
den+0.115
igator+0.115
Pen+0.113
Neg logit contributions
 accidents-0.085
 working-0.077
 End-0.075
ead-0.074
Time-0.073
Token in
Token ID287
Feature activation+1.38e-01

Pos logit contributions
 Pen+0.190
nes+0.179
igator+0.173
den+0.170
Pen+0.168
Neg logit contributions
 accidents-0.154
Time-0.144
ead-0.143
 working-0.139
 End-0.136
Token hand
Token ID1021
Feature activation+4.02e-02

Pos logit contributions
nes+0.261
 Pen+0.253
igator+0.244
den+0.242
icity+0.240
Neg logit contributions
 accidents-0.177
Time-0.170
 End-0.161
joy-0.160
 working-0.158
Token,
Token ID11
Feature activation-3.30e-03

Pos logit contributions
 Pen+0.071
nes+0.067
igator+0.065
den+0.064
Pen+0.063
Neg logit contributions
 accidents-0.056
Time-0.053
ead-0.052
 working-0.050
 End-0.049
Token Jessie
Token ID43425
Feature activation+2.04e-01

Pos logit contributions
 accidents+0.004
Time+0.004
 working+0.004
 End+0.004
ead+0.004
Neg logit contributions
nes-0.006
 Pen-0.006
igator-0.006
den-0.006
Pen-0.005
Token walked
Token ID6807
Feature activation-5.84e-02

Pos logit contributions
 Pen+0.377
nes+0.354
den+0.342
igator+0.342
Pen+0.330
Neg logit contributions
 accidents-0.275
Time-0.257
ead-0.253
 End-0.239
 working-0.238
Token towards
Token ID3371
Feature activation+7.14e-02

Pos logit contributions
 accidents+0.100
Time+0.091
icious+0.091
ead+0.090
ounds+0.090
Neg logit contributions
 Pen-0.089
nes-0.081
igator-0.081
den-0.080
 Sunshine-0.075
Token it
Token ID340
Feature activation-4.67e-02

Pos logit contributions
 Pen+0.131
nes+0.126
igator+0.121
den+0.119
Pen+0.117
Neg logit contributions
 accidents-0.095
Time-0.089
ead-0.088
 working-0.085
 End-0.084
Token until
Token ID1566
Feature activation-4.69e-02

Pos logit contributions
 accidents+0.074
Time+0.073
ead+0.070
 End+0.069
icious+0.067
Neg logit contributions
 Pen-0.074
nes-0.066
igator-0.065
den-0.064
Pen-0.061
Token she
Token ID673
Feature activation-2.53e-02

Pos logit contributions
ead+0.076
icious+0.075
 accidents+0.075
rou+0.075
aping+0.074
Neg logit contributions
 Pen-0.075
nes-0.066
 Sunshine-0.063
igator-0.062
nam-0.062
Token lesson
Token ID11483
Feature activation+9.26e-02

Pos logit contributions
 Pen+0.040
nes+0.038
Pen+0.036
nam+0.036
den+0.035
Neg logit contributions
 accidents-0.033
Time-0.031
 working-0.030
ead-0.030
 End-0.029
Token.
Token ID13
Feature activation-9.73e-03

Pos logit contributions
 Pen+0.189
nes+0.180
igator+0.176
Pen+0.175
den+0.170
Neg logit contributions
 accidents-0.113
Time-0.099
 working-0.099
 End-0.096
ead-0.093
Token She
Token ID1375
Feature activation-2.99e-02

Pos logit contributions
 accidents+0.015
Time+0.014
 working+0.014
aping+0.014
aded+0.014
Neg logit contributions
 Pen-0.015
nes-0.013
nam-0.013
 Sunny-0.013
 Robbie-0.013
Token said
Token ID531
Feature activation+1.00e-01

Pos logit contributions
 accidents+0.046
Time+0.043
 working+0.042
ead+0.042
rou+0.042
Neg logit contributions
 Pen-0.049
nes-0.046
igator-0.044
den-0.044
Pen-0.044
Token they
Token ID484
Feature activation-9.42e-03

Pos logit contributions
 Pen+0.176
nes+0.163
igator+0.158
den+0.155
nam+0.153
Neg logit contributions
 accidents-0.139
Time-0.136
ead-0.134
aping-0.129
 End-0.127
Token should
Token ID815
Feature activation+1.96e-01

Pos logit contributions
 accidents+0.016
Time+0.016
ead+0.015
 working+0.015
 End+0.015
Neg logit contributions
 Pen-0.014
nes-0.012
igator-0.012
den-0.012
Pen-0.012
Token always
Token ID1464
Feature activation+8.15e-02

Pos logit contributions
 Pen+0.327
nes+0.314
igator+0.301
den+0.290
icity+0.288
Neg logit contributions
 accidents-0.289
ead-0.273
Time-0.271
aping-0.261
ucking-0.260
Token respect
Token ID2461
Feature activation-2.68e-02

Pos logit contributions
 Pen+0.149
nes+0.143
igator+0.135
nam+0.134
den+0.134
Neg logit contributions
 accidents-0.106
Time-0.098
ead-0.097
ucking-0.097
ounds-0.095
Token and
Token ID290
Feature activation+9.98e-03

Pos logit contributions
 accidents+0.032
 working+0.027
Time+0.026
aping+0.024
ead+0.024
Neg logit contributions
nes-0.059
 Pen-0.055
den-0.053
Pen-0.053
igator-0.052
Token share
Token ID2648
Feature activation-4.04e-02

Pos logit contributions
 Pen+0.017
nam+0.016
nes+0.016
igator+0.016
den+0.015
Neg logit contributions
Time-0.013
ead-0.013
ucking-0.013
 accidents-0.013
ounds-0.013
Token their
Token ID511
Feature activation+3.67e-02

Pos logit contributions
 accidents+0.052
 working+0.043
ead+0.041
Time+0.041
aping+0.039
Neg logit contributions
 Pen-0.082
nes-0.081
igator-0.077
den-0.077
Pen-0.076
Token Dad
Token ID17415
Feature activation-2.37e-02

Pos logit contributions
 accidents+0.002
Time+0.002
 working+0.002
ead+0.002
 End+0.002
Neg logit contributions
 Pen-0.003
nes-0.003
Pen-0.003
den-0.003
igator-0.003
Token."
Token ID526
Feature activation+1.34e-01

Pos logit contributions
 accidents+0.035
ead+0.033
Time+0.033
 working+0.033
aping+0.032
Neg logit contributions
 Pen-0.039
nes-0.037
igator-0.035
Pen-0.035
den-0.034
Token
Token ID198
Feature activation+2.68e-02

Pos logit contributions
 Pen+0.260
nes+0.256
igator+0.249
Pen+0.242
den+0.237
Neg logit contributions
 accidents-0.160
ead-0.151
Time-0.148
 working-0.143
ounds-0.139
Token
Token ID198
Feature activation+2.68e-02

Pos logit contributions
 Pen+0.054
igator+0.053
nam+0.051
nes+0.051
sie+0.050
Neg logit contributions
Time-0.030
 accidents-0.028
ead-0.027
aping-0.027
Nothing-0.026
Token"
Token ID1
Feature activation-1.16e-01

Pos logit contributions
 Pen+0.044
nes+0.042
den+0.040
igator+0.039
Pen+0.039
Neg logit contributions
 accidents-0.041
ead-0.038
Time-0.037
 working-0.037
rou-0.037
TokenIf
Token ID1532
Feature activation+1.51e-01

Pos logit contributions
 accidents+0.141
ead+0.125
 working+0.122
aping+0.120
Time+0.120
Neg logit contributions
 Pen-0.233
nes-0.220
den-0.214
igator-0.212
Pen-0.211
Token we
Token ID356
Feature activation-3.57e-02

Pos logit contributions
 Pen+0.271
nes+0.256
igator+0.248
den+0.244
Pen+0.240
Neg logit contributions
 accidents-0.206
Time-0.193
ead-0.190
 working-0.184
 End-0.182
Token all
Token ID477
Feature activation+7.63e-02

Pos logit contributions
 accidents+0.042
ead+0.040
 working+0.039
Time+0.039
 End+0.037
Neg logit contributions
 Pen-0.069
nes-0.065
den-0.063
igator-0.062
Pen-0.062
Token come
Token ID1282
Feature activation-1.62e-01

Pos logit contributions
 Pen+0.142
nes+0.134
igator+0.130
den+0.128
Pen+0.126
Neg logit contributions
 accidents-0.100
Time-0.093
ead-0.092
 working-0.088
 End-0.088
Token together
Token ID1978
Feature activation-8.05e-02

Pos logit contributions
 accidents+0.275
Time+0.264
icious+0.251
ead+0.249
 End+0.249
Neg logit contributions
 Pen-0.245
nes-0.223
 Sunshine-0.214
den-0.210
Pen-0.204
Token,"
Token ID553
Feature activation+2.60e-01

Pos logit contributions
 accidents+0.096
 working+0.096
ead+0.091
Time+0.089
 End+0.085
Neg logit contributions
 Pen-0.149
igator-0.144
nes-0.144
nam-0.138
den-0.137
Tokenuffy
Token ID15352
Feature activation+1.48e-01

Pos logit contributions
 Pen+0.333
nes+0.299
igator+0.278
Pen+0.276
den+0.270
Neg logit contributions
 accidents-0.559
Time-0.542
ead-0.527
 working-0.522
 End-0.517
Token was
Token ID373
Feature activation-2.85e-02

Pos logit contributions
 Pen+0.260
nes+0.255
igator+0.242
den+0.238
nam+0.238
Neg logit contributions
 accidents-0.199
ead-0.187
Time-0.185
 working-0.183
 End-0.178
Token not
Token ID407
Feature activation+1.57e-02

Pos logit contributions
 accidents+0.037
Time+0.035
ead+0.034
 working+0.033
 End+0.033
Neg logit contributions
 Pen-0.053
nes-0.051
igator-0.049
den-0.049
Pen-0.047
Token sure
Token ID1654
Feature activation+8.18e-03

Pos logit contributions
 Pen+0.035
nes+0.033
den+0.033
Pen+0.032
icity+0.032
Neg logit contributions
 working-0.015
 accidents-0.015
Time-0.013
ead-0.013
 End-0.012
Token at
Token ID379
Feature activation-6.43e-02

Pos logit contributions
nes+0.018
 Pen+0.017
den+0.017
igator+0.016
Pen+0.016
Neg logit contributions
 accidents-0.010
 working-0.008
rou-0.007
Time-0.007
ounds-0.007
Token first
Token ID717
Feature activation+1.68e-01

Pos logit contributions
 accidents+0.093
 working+0.087
 pouring+0.082
 End+0.077
 getting+0.076
Neg logit contributions
nes-0.120
den-0.116
 Pen-0.108
igator-0.108
Pen-0.104
Token,
Token ID11
Feature activation+6.12e-04

Pos logit contributions
nes+0.357
 Pen+0.354
den+0.346
Pen+0.343
igator+0.340
Neg logit contributions
 accidents-0.185
 working-0.154
ead-0.149
Time-0.148
joy-0.139
Token but
Token ID475
Feature activation+2.06e-01

Pos logit contributions
nes+0.001
igator+0.001
den+0.001
 tant+0.001
sie+0.001
Neg logit contributions
 accidents-0.001
 working-0.001
Time-0.001
ead-0.001
 louder-0.001
Token she
Token ID673
Feature activation-2.65e-02

Pos logit contributions
nes+0.388
den+0.366
 tant+0.361
icity+0.347
 Pen+0.344
Neg logit contributions
 accidents-0.286
 End-0.263
Time-0.254
 Good-0.232
 working-0.230
Token decided
Token ID3066
Feature activation-2.99e-02

Pos logit contributions
 accidents+0.034
Time+0.032
ead+0.032
 working+0.031
 End+0.031
Neg logit contributions
 Pen-0.049
nes-0.047
igator-0.045
den-0.045
nam-0.044
Token to
Token ID284
Feature activation+2.67e-02

Pos logit contributions
 accidents+0.044
Time+0.042
ead+0.041
 working+0.040
 End+0.040
Neg logit contributions
 Pen-0.051
nes-0.048
igator-0.046
den-0.045
Pen-0.044
Token not
Token ID407
Feature activation+1.37e-02

Pos logit contributions
 accidents+0.012
Time+0.011
ead+0.011
aping+0.011
 End+0.010
Neg logit contributions
 Pen-0.019
nes-0.018
igator-0.017
den-0.017
Pen-0.017
Token good
Token ID922
Feature activation-4.99e-04

Pos logit contributions
 Pen+0.026
nes+0.025
igator+0.024
den+0.024
Pen+0.023
Neg logit contributions
 accidents-0.018
Time-0.016
ead-0.016
 working-0.016
 End-0.015
Token for
Token ID329
Feature activation-1.56e-01

Pos logit contributions
 accidents+0.001
Time+0.001
ead+0.001
 working+0.001
 End+0.001
Neg logit contributions
 Pen-0.001
nes-0.001
igator-0.001
den-0.001
Pen-0.001
Token your
Token ID534
Feature activation+5.25e-02

Pos logit contributions
 accidents+0.210
Time+0.203
ead+0.199
aping+0.190
ucking+0.190
Neg logit contributions
 Pen-0.282
nes-0.264
igator-0.253
nam-0.249
den-0.249
Token hair
Token ID4190
Feature activation+5.68e-02

Pos logit contributions
 Pen+0.092
igator+0.089
nes+0.088
den+0.087
Pen+0.083
Neg logit contributions
 accidents-0.076
ead-0.071
 working-0.068
 End-0.066
Time-0.065
Token."
Token ID526
Feature activation+1.33e-01

Pos logit contributions
 Pen+0.112
den+0.104
Pen+0.103
igator+0.102
nes+0.101
Neg logit contributions
 accidents-0.073
ead-0.065
 working-0.065
rou-0.062
uck-0.060
Token
Token ID198
Feature activation+2.37e-02

Pos logit contributions
igator+0.281
nes+0.277
 Pen+0.269
den+0.269
icity+0.263
Neg logit contributions
 accidents-0.141
Time-0.133
ead-0.127
 End-0.121
 Good-0.120
Token
Token ID198
Feature activation+2.40e-02

Pos logit contributions
 Pen+0.046
nes+0.046
igator+0.045
den+0.044
nam+0.043
Neg logit contributions
 accidents-0.028
Time-0.027
 End-0.025
ead-0.025
 working-0.024
TokenAnna
Token ID31160
Feature activation+1.48e-01

Pos logit contributions
 Pen+0.040
nes+0.037
igator+0.037
den+0.036
nam+0.035
Neg logit contributions
 accidents-0.036
Time-0.035
 End-0.033
ead-0.033
 working-0.033
Token nodded
Token ID14464
Feature activation+5.21e-02

Pos logit contributions
 Pen+0.265
nes+0.252
igator+0.250
nam+0.241
den+0.240
Neg logit contributions
 accidents-0.201
ead-0.189
Time-0.189
 working-0.182
aping-0.180
Token and
Token ID290
Feature activation+1.02e-02

Pos logit contributions
 Pen+0.079
nes+0.070
den+0.068
igator+0.067
Pen+0.066
Neg logit contributions
 accidents-0.084
Time-0.083
ead-0.082
ounds-0.080
aping-0.080
Token Everyone
Token ID11075
Feature activation-6.89e-02

Pos logit contributions
Time+0.017
 accidents+0.016
ead+0.016
 Good+0.016
 End+0.015
Neg logit contributions
igator-0.029
nes-0.028
 Pen-0.028
nam-0.026
den-0.026
Token was
Token ID373
Feature activation-2.96e-02

Pos logit contributions
 accidents+0.081
Time+0.079
 working+0.077
aping+0.074
 End+0.072
Neg logit contributions
 Pen-0.130
nam-0.124
nes-0.124
Pen-0.122
icity-0.121
Token very
Token ID845
Feature activation+1.11e-01

Pos logit contributions
 accidents+0.042
ead+0.039
Time+0.039
 End+0.037
aping+0.037
Neg logit contributions
 Pen-0.052
nes-0.049
igator-0.047
den-0.046
Pen-0.045
Token surprised
Token ID6655
Feature activation-1.46e-01

Pos logit contributions
 Pen+0.208
nes+0.200
igator+0.191
den+0.186
nam+0.183
Neg logit contributions
 accidents-0.144
ead-0.130
Time-0.130
ounds-0.129
aping-0.127
Token!
Token ID0
Feature activation-1.62e-01

Pos logit contributions
 accidents+0.195
Time+0.182
ead+0.180
 working+0.173
 End+0.171
Neg logit contributions
 Pen-0.269
nes-0.255
igator-0.246
den-0.243
Pen-0.239
Token<|endoftext|>
Token ID50256
Feature activation-2.19e-02

Pos logit contributions
Time+0.174
 Good+0.163
 accidents+0.158
 End+0.154
joy+0.154
Neg logit contributions
igator-0.348
nes-0.326
 Pen-0.316
nam-0.314
sie-0.306
TokenThe
Token ID464
Feature activation+3.89e-03

Pos logit contributions
Time+0.022
 accidents+0.021
 End+0.019
ead+0.019
 working+0.019
Neg logit contributions
 Pen-0.045
nes-0.045
nam-0.044
igator-0.044
icity-0.043
Token sun
Token ID4252
Feature activation-2.33e-01

Pos logit contributions
 Pen+0.007
igator+0.007
nes+0.007
den+0.006
Pen+0.006
Neg logit contributions
 accidents-0.005
Time-0.005
ead-0.005
aping-0.005
ucking-0.005
Token was
Token ID373
Feature activation-2.78e-02

Pos logit contributions
 accidents+0.349
ead+0.332
Time+0.327
icious+0.317
ounds+0.314
Neg logit contributions
 Pen-0.398
igator-0.361
nes-0.353
den-0.346
Pen-0.334
Token high
Token ID1029
Feature activation+1.21e-01

Pos logit contributions
 accidents+0.035
Time+0.031
ead+0.031
aping+0.031
ounds+0.030
Neg logit contributions
 Pen-0.053
igator-0.049
nes-0.048
den-0.047
nam-0.047
Token in
Token ID287
Feature activation+1.37e-01

Pos logit contributions
nes+0.240
 Pen+0.237
nam+0.222
igator+0.221
Pen+0.219
Neg logit contributions
 accidents-0.145
 working-0.133
ead-0.130
uck-0.123
Time-0.123
Token With
Token ID2080
Feature activation-1.09e-01

Pos logit contributions
 accidents+0.009
ead+0.009
Time+0.009
 working+0.008
aping+0.008
Neg logit contributions
 Pen-0.014
nes-0.014
igator-0.013
den-0.013
icity-0.013
Token the
Token ID262
Feature activation+2.26e-02

Pos logit contributions
 accidents+0.152
Time+0.143
ead+0.141
 working+0.137
 End+0.136
Neg logit contributions
 Pen-0.192
nes-0.185
igator-0.175
den-0.174
Pen-0.170
Token smooth
Token ID7209
Feature activation-2.17e-02

Pos logit contributions
 Pen+0.038
igator+0.034
nes+0.033
nam+0.033
 tant+0.033
Neg logit contributions
 accidents-0.032
Time-0.031
ead-0.031
aping-0.030
ucking-0.030
Token pieces
Token ID5207
Feature activation+5.74e-03

Pos logit contributions
Time+0.033
Nothing+0.031
rou+0.031
 accidents+0.031
ucking+0.030
Neg logit contributions
 Pen-0.033
igator-0.031
 tant-0.031
sie-0.029
mine-0.029
Token of
Token ID286
Feature activation-7.20e-02

Pos logit contributions
 Pen+0.010
igator+0.010
nes+0.009
den+0.009
 contain+0.009
Neg logit contributions
Time-0.008
 accidents-0.008
ead-0.008
icious-0.007
 End-0.007
Token cel
Token ID18725
Feature activation-1.37e-01

Pos logit contributions
 accidents+0.091
Time+0.087
ead+0.085
ucking+0.082
 End+0.081
Neg logit contributions
 Pen-0.136
nes-0.125
igator-0.124
den-0.120
nam-0.120
Tokenery
Token ID1924
Feature activation+1.06e-01

Pos logit contributions
 accidents+0.259
Time+0.249
ead+0.246
 End+0.239
 working+0.236
Neg logit contributions
 Pen-0.172
nes-0.162
igator-0.154
den-0.149
Pen-0.144
Token,
Token ID11
Feature activation-8.45e-04

Pos logit contributions
 Pen+0.178
nes+0.166
igator+0.162
den+0.158
nam+0.152
Neg logit contributions
 accidents-0.154
Time-0.151
ead-0.147
 End-0.142
rou-0.140
Token she
Token ID673
Feature activation-2.70e-02

Pos logit contributions
 accidents+0.001
Time+0.001
ead+0.001
 End+0.001
 working+0.001
Neg logit contributions
 Pen-0.001
nes-0.001
igator-0.001
den-0.001
Pen-0.001
Token printed
Token ID10398
Feature activation-1.57e-01

Pos logit contributions
 accidents+0.036
Time+0.035
ead+0.033
 End+0.032
 Good+0.031
Neg logit contributions
 Pen-0.050
nes-0.048
igator-0.046
den-0.045
nam-0.044
Token a
Token ID257
Feature activation-6.03e-03

Pos logit contributions
 accidents+0.219
Time+0.211
ead+0.207
 End+0.200
aping+0.199
Neg logit contributions
 Pen-0.274
nes-0.253
igator-0.247
den-0.245
Pen-0.237
Tokenily
Token ID813
Feature activation+7.10e-02

Pos logit contributions
uck+0.080
 accidents+0.080
 End+0.079
Time+0.079
 working+0.078
Neg logit contributions
 Pen-0.145
nam-0.144
igator-0.139
Pen-0.134
nes-0.131
Token and
Token ID290
Feature activation+1.61e-02

Pos logit contributions
 Pen+0.134
nes+0.129
nam+0.125
igator+0.124
Pen+0.123
Neg logit contributions
 accidents-0.087
Time-0.083
ead-0.082
 working-0.080
 End-0.078
Token Tom
Token ID4186
Feature activation+3.51e-03

Pos logit contributions
nes+0.035
den+0.034
 Pen+0.033
 tant+0.033
icity+0.032
Neg logit contributions
 accidents-0.015
Time-0.013
uck-0.013
 working-0.013
 End-0.013
Token were
Token ID547
Feature activation+1.39e-01

Pos logit contributions
 Pen+0.006
nes+0.006
igator+0.005
den+0.005
Pen+0.005
Neg logit contributions
 accidents-0.005
Time-0.005
ead-0.005
 working-0.005
 End-0.005
Token best
Token ID1266
Feature activation+6.12e-02

Pos logit contributions
 Pen+0.294
nes+0.278
igator+0.270
den+0.265
Pen+0.263
Neg logit contributions
 accidents-0.149
Time-0.137
ead-0.132
aping-0.126
 End-0.122
Token friends
Token ID2460
Feature activation-9.00e-02

Pos logit contributions
 Pen+0.153
nes+0.150
igator+0.148
den+0.147
icity+0.142
Neg logit contributions
 accidents-0.043
ead-0.041
 working-0.035
ounds-0.035
rou-0.033
Token.
Token ID13
Feature activation-7.61e-03

Pos logit contributions
 accidents+0.081
joy+0.074
 working+0.074
 End+0.071
ead+0.068
Neg logit contributions
 Pen-0.200
nes-0.197
den-0.192
icity-0.191
igator-0.190
Token They
Token ID1119
Feature activation-2.08e-02

Pos logit contributions
 accidents+0.010
Time+0.009
ead+0.009
 End+0.009
 working+0.009
Neg logit contributions
 Pen-0.014
nes-0.014
igator-0.013
den-0.013
Pen-0.013
Token liked
Token ID8288
Feature activation+1.38e-01

Pos logit contributions
 working+0.024
 End+0.023
ead+0.023
Time+0.023
rou+0.022
Neg logit contributions
 Pen-0.040
nes-0.037
Pen-0.036
den-0.036
 tant-0.035
Token to
Token ID284
Feature activation+2.99e-02

Pos logit contributions
 Pen+0.244
nes+0.233
igator+0.223
den+0.221
Pen+0.216
Neg logit contributions
 accidents-0.195
ead-0.181
Time-0.181
 working-0.177
aping-0.169
Token play
Token ID711
Feature activation-1.17e-01

Pos logit contributions
 Pen+0.071
nes+0.068
den+0.066
igator+0.065
Pen+0.065
Neg logit contributions
 accidents-0.022
ead-0.021
Time-0.020
 working-0.020
 End-0.018
Token".
Token ID1911
Feature activation+9.93e-02

Pos logit contributions
 Pen+0.153
nes+0.145
igator+0.138
den+0.138
Pen+0.136
Neg logit contributions
 accidents-0.127
ead-0.119
Time-0.118
 working-0.116
aping-0.113
Token Spot
Token ID15899
Feature activation+1.92e-01

Pos logit contributions
den+0.205
igator+0.203
nes+0.197
sie+0.188
 Pen+0.188
Neg logit contributions
ead-0.114
 accidents-0.109
Time-0.105
uck-0.103
 Good-0.099
Token w
Token ID266
Feature activation-4.16e-02

Pos logit contributions
 Pen+0.351
nes+0.335
igator+0.325
den+0.320
nam+0.316
Neg logit contributions
 accidents-0.251
ead-0.238
Time-0.236
 working-0.229
aping-0.225
Tokenagged
Token ID14655
Feature activation+2.86e-02

Pos logit contributions
 accidents+0.054
Time+0.051
ead+0.051
aping+0.048
 End+0.048
Neg logit contributions
 Pen-0.079
nes-0.073
igator-0.072
den-0.071
Pen-0.070
Token his
Token ID465
Feature activation+7.04e-02

Pos logit contributions
 Pen+0.049
nes+0.047
igator+0.044
den+0.044
Pen+0.043
Neg logit contributions
 accidents-0.042
Time-0.039
ead-0.039
 working-0.038
 End-0.037
Token tail
Token ID7894
Feature activation+3.32e-02

Pos logit contributions
 Pen+0.102
nes+0.089
igator+0.088
Pen+0.086
nam+0.085
Neg logit contributions
 accidents-0.125
Time-0.121
ead-0.114
rou-0.113
ucking-0.113
Token and
Token ID290
Feature activation+1.32e-02

Pos logit contributions
 Pen+0.041
 Sunny+0.034
igator+0.034
 Sunshine+0.033
nes+0.031
Neg logit contributions
 accidents-0.064
Time-0.064
 Good-0.060
Nothing-0.060
aping-0.060
Token bark
Token ID21405
Feature activation+8.25e-02

Pos logit contributions
 Pen+0.022
nes+0.021
igator+0.020
den+0.020
Pen+0.020
Neg logit contributions
 accidents-0.020
Time-0.019
ead-0.018
 working-0.018
 End-0.018
Tokened
Token ID276
Feature activation-6.37e-02

Pos logit contributions
 Pen+0.125
nes+0.114
den+0.108
igator+0.106
 tant+0.103
Neg logit contributions
 accidents-0.134
Time-0.131
 End-0.126
 working-0.122
aping-0.120
Token happily
Token ID18177
Feature activation+3.20e-02

Pos logit contributions
Time+0.100
 accidents+0.099
aping+0.094
 End+0.093
ounds+0.093
Neg logit contributions
 Pen-0.103
nes-0.090
igator-0.090
den-0.086
 tant-0.086
Token when
Token ID618
Feature activation-5.06e-02

Pos logit contributions
 Pen+0.056
nes+0.053
igator+0.051
den+0.050
Pen+0.049
Neg logit contributions
 accidents-0.046
Time-0.044
ead-0.042
aping-0.041
 End-0.041
Token for
Token ID329
Feature activation-1.56e-01

Pos logit contributions
 accidents+0.297
Time+0.275
 working+0.268
ead+0.261
 End+0.258
Neg logit contributions
 Pen-0.350
nes-0.340
den-0.333
igator-0.321
nam-0.316
Token a
Token ID257
Feature activation-8.59e-03

Pos logit contributions
 accidents+0.178
Time+0.168
 working+0.160
 End+0.156
ead+0.147
Neg logit contributions
 Pen-0.315
nes-0.309
igator-0.308
den-0.301
nam-0.287
Token long
Token ID890
Feature activation+3.98e-02

Pos logit contributions
 accidents+0.011
Time+0.011
 working+0.011
ead+0.010
 End+0.010
Neg logit contributions
 Pen-0.015
nes-0.014
igator-0.014
den-0.014
nam-0.014
Token time
Token ID640
Feature activation+1.00e-01

Pos logit contributions
nam+0.080
 Pen+0.079
nes+0.077
den+0.074
Pen+0.073
Neg logit contributions
Time-0.043
 End-0.041
 working-0.040
 accidents-0.038
 pouring-0.037
Token and
Token ID290
Feature activation+9.96e-03

Pos logit contributions
 Pen+0.162
nes+0.147
den+0.139
igator+0.137
icity+0.133
Neg logit contributions
 accidents-0.153
Time-0.150
ead-0.144
aping-0.142
 End-0.138
Token wanted
Token ID2227
Feature activation+2.34e-02

Pos logit contributions
 Pen+0.017
nes+0.015
nam+0.014
igator+0.014
icity+0.014
Neg logit contributions
ead-0.015
ucking-0.015
 accidents-0.014
Time-0.014
aping-0.014
Token to
Token ID284
Feature activation+2.42e-02

Pos logit contributions
 Pen+0.039
nes+0.036
igator+0.035
den+0.034
Pen+0.034
Neg logit contributions
 accidents-0.035
Time-0.034
ead-0.034
 End-0.033
aping-0.032
Token rest
Token ID1334
Feature activation-3.37e-02

Pos logit contributions
 Pen+0.049
nes+0.046
den+0.045
igator+0.045
Pen+0.044
Neg logit contributions
 accidents-0.027
Time-0.025
ead-0.025
 working-0.024
 End-0.024
Token for
Token ID329
Feature activation-1.57e-01

Pos logit contributions
 accidents+0.041
 working+0.036
Time+0.035
 End+0.034
 pouring+0.033
Neg logit contributions
 Pen-0.067
nes-0.066
igator-0.065
den-0.064
Pen-0.062
Token a
Token ID257
Feature activation-8.71e-03

Pos logit contributions
 accidents+0.186
Time+0.172
 working+0.169
 End+0.160
ead+0.159
Neg logit contributions
 Pen-0.308
igator-0.308
nes-0.304
den-0.297
 tant-0.282
Token bit
Token ID1643
Feature activation+1.17e-01

Pos logit contributions
 accidents+0.013
Time+0.012
 working+0.012
ead+0.012
 End+0.012
Neg logit contributions
 Pen-0.014
nes-0.014
igator-0.013
den-0.013
icity-0.013
Token
Token ID198
Feature activation+2.81e-02

Pos logit contributions
 Pen+0.051
nes+0.048
igator+0.047
den+0.046
Pen+0.045
Neg logit contributions
 accidents-0.038
Time-0.036
ead-0.036
 working-0.034
aping-0.034
TokenAfter
Token ID3260
Feature activation-1.60e-01

Pos logit contributions
nes+0.044
 Pen+0.040
den+0.039
igator+0.038
Pen+0.037
Neg logit contributions
 accidents-0.045
joy-0.041
ead-0.041
arter-0.041
urg-0.039
Token they
Token ID484
Feature activation-1.37e-03

Pos logit contributions
ucking+0.251
rou+0.244
aping+0.243
ead+0.241
icious+0.238
Neg logit contributions
 Pen-0.243
 Robbie-0.217
nes-0.214
nam-0.213
 Rob-0.212
Token were
Token ID547
Feature activation+1.39e-01

Pos logit contributions
 accidents+0.001
Time+0.001
 End+0.001
ead+0.001
 working+0.001
Neg logit contributions
 Pen-0.003
nes-0.003
igator-0.003
den-0.003
Pen-0.003
Token finished
Token ID5201
Feature activation-2.15e-01

Pos logit contributions
 Pen+0.285
nes+0.274
igator+0.257
den+0.254
icity+0.253
Neg logit contributions
 accidents-0.161
aping-0.145
ead-0.142
ucking-0.142
Time-0.139
Token playing
Token ID2712
Feature activation-2.01e-01

Pos logit contributions
Time+0.314
 accidents+0.300
icious+0.298
ead+0.295
ounds+0.295
Neg logit contributions
 Pen-0.351
nes-0.317
 Robbie-0.316
nam-0.312
den-0.307
Token,
Token ID11
Feature activation+2.02e-04

Pos logit contributions
 accidents+0.267
Time+0.243
ead+0.240
 working+0.240
 End+0.230
Neg logit contributions
 Pen-0.378
nes-0.358
den-0.347
igator-0.345
Pen-0.342
Token Tim
Token ID5045
Feature activation-5.98e-02

Pos logit contributions
 Pen+0.000
nam+0.000
 Robbie+0.000
nes+0.000
 Rudolph+0.000
Neg logit contributions
ucking-0.000
rou-0.000
 End-0.000
ead-0.000
icious-0.000
Tokenmy
Token ID1820
Feature activation-1.30e-01

Pos logit contributions
 accidents+0.066
Time+0.061
ead+0.060
 End+0.056
ounds+0.056
Neg logit contributions
 Pen-0.121
nes-0.116
den-0.115
igator-0.112
icity-0.108
Token felt
Token ID2936
Feature activation-3.79e-02

Pos logit contributions
 accidents+0.204
Time+0.197
ead+0.188
 End+0.187
icious+0.185
Neg logit contributions
 Pen-0.207
nes-0.196
den-0.187
igator-0.177
icity-0.174
Token guilty
Token ID6717
Feature activation-3.38e-02

Pos logit contributions
aping+0.059
ead+0.058
ounds+0.057
ucking+0.057
urg+0.056
Neg logit contributions
 Pen-0.055
igator-0.054
nam-0.053
nes-0.052
 contain-0.051
Token that
Token ID326
Feature activation-2.97e-02

Pos logit contributions
 accidents+0.108
Time+0.103
ead+0.102
 working+0.097
aping+0.097
Neg logit contributions
 Pen-0.141
nes-0.132
igator-0.128
den-0.126
Pen-0.123
Token they
Token ID484
Feature activation-1.61e-02

Pos logit contributions
 accidents+0.041
Time+0.039
ead+0.038
 working+0.037
aping+0.037
Neg logit contributions
 Pen-0.053
nes-0.050
igator-0.048
den-0.048
Pen-0.047
Token had
Token ID550
Feature activation-3.51e-02

Pos logit contributions
 accidents+0.018
 working+0.017
Time+0.017
 End+0.016
rou+0.016
Neg logit contributions
 Pen-0.032
Pen-0.030
den-0.029
nes-0.029
icity-0.028
Token found
Token ID1043
Feature activation-1.25e-01

Pos logit contributions
 accidents+0.047
ucking+0.046
Time+0.046
ead+0.045
 End+0.044
Neg logit contributions
 Pen-0.060
nes-0.059
nam-0.055
igator-0.054
den-0.053
Token out
Token ID503
Feature activation-4.07e-02

Pos logit contributions
 accidents+0.157
Time+0.139
 working+0.138
ead+0.137
aping+0.131
Neg logit contributions
 Pen-0.245
nes-0.239
Pen-0.226
den-0.224
igator-0.224
Token more
Token ID517
Feature activation-2.15e-01

Pos logit contributions
 accidents+0.052
ead+0.051
Time+0.051
aping+0.047
 End+0.047
Neg logit contributions
 Pen-0.074
nes-0.070
igator-0.069
den-0.067
nam-0.065
Token about
Token ID546
Feature activation-1.15e-02

Pos logit contributions
 accidents+0.287
Time+0.261
ead+0.259
 working+0.256
 End+0.245
Neg logit contributions
 Pen-0.401
nes-0.381
den-0.362
igator-0.361
Pen-0.359
Token the
Token ID262
Feature activation+1.48e-02

Pos logit contributions
Time+0.016
 accidents+0.016
ead+0.016
ucking+0.015
 End+0.015
Neg logit contributions
 Pen-0.020
nam-0.018
igator-0.018
nes-0.018
den-0.017
Token world
Token ID995
Feature activation-9.74e-02

Pos logit contributions
 Pen+0.027
nes+0.026
igator+0.025
den+0.024
Pen+0.024
Neg logit contributions
 accidents-0.019
Time-0.018
ead-0.018
aping-0.017
 working-0.017
Token,
Token ID11
Feature activation-6.15e-03

Pos logit contributions
 accidents+0.131
Time+0.123
ead+0.121
 working+0.117
 End+0.115
Neg logit contributions
 Pen-0.177
nes-0.167
igator-0.162
den-0.160
Pen-0.157
Token thanks
Token ID5176
Feature activation-9.92e-02

Pos logit contributions
 accidents+0.009
Time+0.009
ead+0.009
 End+0.009
aping+0.009
Neg logit contributions
 Pen-0.010
nes-0.009
igator-0.009
nam-0.009
den-0.009
Token.
Token ID13
Feature activation-8.70e-03

Pos logit contributions
 working+0.068
 accidents+0.067
ead+0.062
aping+0.061
rou+0.058
Neg logit contributions
 Pen-0.133
igator-0.129
nes-0.129
Pen-0.125
icity-0.123
Token
Token ID198
Feature activation+2.44e-02

Pos logit contributions
 accidents+0.007
ead+0.007
Time+0.007
 working+0.007
 pouring+0.006
Neg logit contributions
nes-0.019
igator-0.019
 Pen-0.019
den-0.019
icity-0.018
Token
Token ID198
Feature activation+2.45e-02

Pos logit contributions
igator+0.049
 Pen+0.049
nes+0.048
nam+0.047
den+0.047
Neg logit contributions
Time-0.026
 accidents-0.025
ead-0.024
Nothing-0.023
aping-0.023
TokenShe
Token ID3347
Feature activation-6.68e-02

Pos logit contributions
 Pen+0.049
nes+0.047
Pen+0.044
den+0.044
igator+0.043
Neg logit contributions
 accidents-0.031
ead-0.028
joy-0.027
rou-0.027
Time-0.026
Token was
Token ID373
Feature activation-2.80e-02

Pos logit contributions
 accidents+0.106
Time+0.101
ead+0.101
ucking+0.096
icious+0.095
Neg logit contributions
 Pen-0.109
den-0.100
nes-0.099
igator-0.095
Pen-0.092
Token shrinking
Token ID27382
Feature activation-2.54e-01

Pos logit contributions
 accidents+0.044
Time+0.042
ead+0.041
 End+0.040
aping+0.040
Neg logit contributions
 Pen-0.045
nes-0.042
igator-0.040
den-0.040
Pen-0.039
Token very
Token ID845
Feature activation+1.13e-01

Pos logit contributions
 accidents+0.337
 working+0.290
rou+0.264
Time+0.259
ead+0.258
Neg logit contributions
nes-0.506
 Pen-0.489
igator-0.468
Pen-0.453
den-0.452
Token quickly
Token ID2952
Feature activation+1.74e-02

Pos logit contributions
 Pen+0.175
igator+0.158
nam+0.157
Pen+0.151
nes+0.150
Neg logit contributions
Time-0.183
 Good-0.170
 accidents-0.167
ead-0.167
icious-0.166
Token and
Token ID290
Feature activation+1.22e-02

Pos logit contributions
 Pen+0.027
nes+0.024
igator+0.024
den+0.024
icity+0.023
Neg logit contributions
Time-0.027
 accidents-0.026
 End-0.025
ead-0.025
aping-0.025
Token soon
Token ID2582
Feature activation-9.17e-02

Pos logit contributions
 Pen+0.020
nes+0.017
nam+0.017
igator+0.017
den+0.017
Neg logit contributions
ead-0.019
Time-0.019
icious-0.018
ucking-0.018
 accidents-0.018
Token she
Token ID673
Feature activation-2.63e-02

Pos logit contributions
icious+0.160
ead+0.154
Time+0.148
aping+0.146
 Good+0.146
Neg logit contributions
 Pen-0.139
nes-0.122
den-0.114
la-0.113
 Amelia-0.113
Token
Token ID198
Feature activation+2.41e-02

Pos logit contributions
 accidents+0.016
Time+0.015
ead+0.015
 working+0.014
 End+0.014
Neg logit contributions
 Pen-0.023
nes-0.021
igator-0.021
den-0.020
Pen-0.020
Token
Token ID198
Feature activation+2.42e-02

Pos logit contributions
 Pen+0.043
nes+0.040
igator+0.039
den+0.039
Pen+0.038
Neg logit contributions
 accidents-0.034
Time-0.032
ead-0.031
 working-0.030
 End-0.030
Token"
Token ID1
Feature activation-1.23e-01

Pos logit contributions
 Pen+0.041
nes+0.040
igator+0.038
den+0.037
Pen+0.037
Neg logit contributions
 accidents-0.039
 working-0.034
rou-0.032
urg-0.032
ead-0.032
TokenMe
Token ID5308
Feature activation+1.04e-01

Pos logit contributions
Time+0.122
 accidents+0.119
Nothing+0.116
ead+0.114
 End+0.104
Neg logit contributions
 Pen-0.267
nes-0.255
icity-0.247
den-0.244
igator-0.243
Token!"
Token ID2474
Feature activation+3.07e-02

Pos logit contributions
 Pen+0.200
nes+0.188
igator+0.183
den+0.179
Pen+0.177
Neg logit contributions
 accidents-0.132
Time-0.126
ead-0.120
 End-0.116
 working-0.116
Token Sam
Token ID3409
Feature activation-1.85e-01

Pos logit contributions
 Pen+0.071
nes+0.070
den+0.067
icity+0.067
Pen+0.067
Neg logit contributions
 accidents-0.026
Time-0.024
ead-0.024
 End-0.021
ounds-0.021
Token says
Token ID1139
Feature activation+5.76e-02

Pos logit contributions
ead+0.193
 accidents+0.186
 working+0.177
 wider+0.170
uck+0.168
Neg logit contributions
nes-0.372
 Pen-0.352
nam-0.350
otte-0.345
Pen-0.341
Token.
Token ID13
Feature activation-1.26e-02

Pos logit contributions
 Pen+0.093
nes+0.087
igator+0.082
den+0.082
nam+0.080
Neg logit contributions
 accidents-0.090
Time-0.089
ead-0.082
 End-0.081
aping-0.081
Token "
Token ID366
Feature activation-1.03e-01

Pos logit contributions
 accidents+0.014
ead+0.013
Time+0.013
 working+0.012
 End+0.012
Neg logit contributions
 Pen-0.026
nes-0.025
igator-0.024
den-0.024
icity-0.024
TokenL
Token ID43
Feature activation-7.94e-02

Pos logit contributions
 accidents+0.121
Time+0.108
ead+0.107
 working+0.103
rou+0.102
Neg logit contributions
 Pen-0.208
nes-0.198
igator-0.192
den-0.190
Pen-0.188
Tokenion
Token ID295
Feature activation+1.96e-01

Pos logit contributions
 accidents+0.157
Time+0.143
 working+0.143
ead+0.142
 End+0.141
Neg logit contributions
igator-0.095
 Pen-0.094
nes-0.094
den-0.081
icity-0.079
Token They
Token ID1119
Feature activation-2.24e-02

Pos logit contributions
 accidents+0.014
 working+0.013
aping+0.012
Time+0.012
rou+0.012
Neg logit contributions
 Pen-0.013
nes-0.011
 Sunny-0.011
Pen-0.011
 Sunshine-0.011
Token were
Token ID547
Feature activation+1.36e-01

Pos logit contributions
 End+0.019
 accidents+0.019
 working+0.018
Time+0.018
 continued+0.018
Neg logit contributions
 Pen-0.048
den-0.047
nes-0.045
Pen-0.045
igator-0.044
Token happy
Token ID3772
Feature activation-4.46e-02

Pos logit contributions
 Pen+0.241
nes+0.224
igator+0.217
Pen+0.210
nam+0.210
Neg logit contributions
 accidents-0.194
Time-0.184
ead-0.183
aping-0.175
ucking-0.173
Token.
Token ID13
Feature activation-8.60e-03

Pos logit contributions
Time+0.082
icious+0.082
aping+0.078
ead+0.077
ayed+0.077
Neg logit contributions
 Pen-0.058
 Sunny-0.049
nes-0.047
 Sunshine-0.043
 Robbie-0.043
Token The
Token ID383
Feature activation-2.58e-02

Pos logit contributions
 accidents+0.014
 working+0.013
ead+0.013
Time+0.013
aping+0.013
Neg logit contributions
 Pen-0.014
nes-0.012
Pen-0.012
 Sunny-0.011
nam-0.011
Token end
Token ID886
Feature activation-1.99e-01

Pos logit contributions
 accidents+0.026
ead+0.024
Time+0.024
aping+0.022
 working+0.022
Neg logit contributions
 Pen-0.056
nes-0.053
igator-0.052
den-0.051
Pen-0.050
Token.
Token ID13
Feature activation-9.46e-03

Pos logit contributions
 accidents+0.303
ead+0.289
Time+0.286
aping+0.278
 End+0.277
Neg logit contributions
 Pen-0.328
nes-0.303
igator-0.295
den-0.288
Pen-0.280
Token<|endoftext|>
Token ID50256
Feature activation-2.18e-02

Pos logit contributions
 accidents+0.016
aping+0.015
ead+0.015
ipping+0.015
ucking+0.015
Neg logit contributions
 Pen-0.013
nes-0.012
 Sunny-0.011
Pen-0.011
nam-0.011
TokenL
Token ID43
Feature activation-7.80e-02

Pos logit contributions
Time+0.022
 accidents+0.021
ead+0.020
 working+0.019
 End+0.019
Neg logit contributions
 Pen-0.046
nes-0.045
nam-0.044
igator-0.044
den-0.044
Tokenila
Token ID10102
Feature activation+6.04e-02

Pos logit contributions
 accidents+0.109
Time+0.104
ead+0.100
 End+0.099
 working+0.099
Neg logit contributions
 Pen-0.139
nes-0.130
igator-0.127
den-0.125
nam-0.125
Token was
Token ID373
Feature activation-2.91e-02

Pos logit contributions
 Pen+0.117
nes+0.113
nam+0.110
igator+0.109
den+0.109
Neg logit contributions
 accidents-0.070
Time-0.067
ead-0.066
 working-0.065
 End-0.063