TOP ACTIVATIONS
MAX = 12.059

stayed away from the all igator ," Mia said .
be careful . The all igator might bite us if we
fun , making the all igator and the bird fight .
and apples to the all igator , too . The all
" Look , an all igator !" Tim said . He
there was a wild all igator who lived in a big
not notice that the all igator toy was not a toy
, too . The all igator did not bite them .
his hand . The all igator opened its mouth and snapped
day , a wild all igator went to a big lake
was surprised that the all igator could talk . He said
can share with the all igator , too . Maybe it
Soon , the all igator 's family wrote back .
. It was an all igator ! " Look
and safely removed the all igator . Tim my and his
a big , green all igator ! The children were so
Hello all igator ! â .
swamp glow . The all igator and his friends were very
. The all igator replied
sweet treat . The all igator was so happy . He

MIN ACTIVATIONS
MIN = -12.456

into pieces and stopped z ooming . Sam cried and dropped
long , Billy was z ooming all over the place !
the air and make z ooming noises . Lily liked to
!" Ben said , z ooming his red boat past Anna
!" Ben says , z ooming his car around the sofa
saw a big plane z ooming by and wanted to try
had so much fun z ooming around the room with his
it every day , z ooming it around the room and
was the best at z ooming ! One day ,
, green car came z ooming into the park at top
The tank kept z ooming around in circles and made
soon the car was z ooming around the flowers and tables
it takes a little z ooming around to get there .
'd spent the day z ooming around the hill . He
knew it , he z ooming off to try all the
They make z ooming and who os hing noises
had a great time z ooming around and the tall tree
around the ocean , z ooming from one end to another
Ben . Ben stopped z ooming his car and looked at
forward and backward , z ooming all around the ranch .

INTERVAL 5.930 - 12.059
CONTAINS 0.332%

there was a little boy named Jason . Every day he
there was a little boy named Tim my . Tim my
, there was a girl named Lily . She was a
Sam gave a special fire man 's hat that he had
K aren was a 3 year old girl who was a

INTERVAL -0.199 - 5.930
CONTAINS 58.436%

and wanted to catch it , but she didn 't know
I 'm so proud of you for taking such good care
." After spending some time with his grandma ,
help others when they need it , even if it means
and that Tom was not ready for it .

INTERVAL -6.328 - -0.199
CONTAINS 40.901%

L ily and Max continued to be best friends and
was a new toy . She loved it so much that
around with excitement . M ia watched him
help , but no one heard him . Tim was stuck
on , Peter vowed to always listen to grown - ups

INTERVAL -12.456 - -6.328
CONTAINS 0.330%

! He tried again and again , but he just couldn
The stranger looked at the nap kin and said , "
finding each other . Z ara was very good at the
time , there was a fle a called Ho ppy .
. But sorry is not enough . You need to make
Token stayed
Token ID9658
Feature activation-3.54e-01

Pos logit contributions
igator+0.030
 Amen+0.025
boat+0.024
ull+0.023
 Mill+0.022
Neg logit contributions
 fault-0.036
 loses-0.034
joy-0.033
ooming-0.032
udd-0.032
Token away
Token ID1497
Feature activation+1.41e+00

Pos logit contributions
 fault+0.036
 loses+0.033
joy+0.032
udd+0.032
 blood+0.031
Neg logit contributions
igator-0.035
boat-0.028
 Amen-0.028
eway-0.027
igators-0.026
Token from
Token ID422
Feature activation+3.24e+00

Pos logit contributions
igator+0.122
 Amen+0.102
boat+0.101
eway+0.093
ull+0.089
Neg logit contributions
 fault-0.153
 loses-0.145
 blood-0.136
udd-0.135
joy-0.134
Token the
Token ID262
Feature activation+3.03e-01

Pos logit contributions
igator+0.260
 Amen+0.202
boat+0.189
igators+0.181
ull+0.178
Neg logit contributions
 fault-0.378
udd-0.353
 loses-0.352
joy-0.349
ooming-0.343
Token all
Token ID477
Feature activation-1.10e+00

Pos logit contributions
igator+0.031
 Amen+0.025
boat+0.025
igators+0.023
ull+0.023
Neg logit contributions
 fault-0.029
 loses-0.027
joy-0.026
udd-0.026
ooming-0.026
Tokenigator
Token ID23823
Feature activation+1.21e+01

Pos logit contributions
 loses+0.131
 fault+0.130
 again+0.126
 blood+0.126
 anymore+0.126
Neg logit contributions
 Amen-0.057
eway-0.047
 Mill-0.040
iona-0.039
boat-0.039
Token,"
Token ID553
Feature activation+2.28e+00

Pos logit contributions
igator+1.065
 Amen+0.861
boat+0.840
igators+0.762
ull+0.755
Neg logit contributions
 fault-1.297
 loses-1.208
joy-1.206
 blood-1.164
 underwear-1.161
Token Mia
Token ID32189
Feature activation+1.53e+00

Pos logit contributions
igator+0.233
boat+0.194
 Amen+0.194
eway+0.185
igators+0.177
Neg logit contributions
 fault-0.212
 loses-0.199
joy-0.195
 blood-0.193
 underwear-0.187
Token said
Token ID531
Feature activation+1.12e+00

Pos logit contributions
igator+0.131
 Amen+0.107
boat+0.101
ull+0.094
man+0.092
Neg logit contributions
 fault-0.172
joy-0.158
 loses-0.157
ooming-0.152
 underwear-0.149
Token.
Token ID13
Feature activation+2.02e-02

Pos logit contributions
igator+0.096
 Amen+0.083
boat+0.078
ull+0.073
 Mill+0.070
Neg logit contributions
 fault-0.120
 loses-0.113
joy-0.109
udd-0.107
 underwear-0.107
Token
Token ID198
Feature activation-1.23e+00

Pos logit contributions
igator+0.002
 Amen+0.002
boat+0.001
 Mill+0.001
ull+0.001
Neg logit contributions
 fault-0.002
 loses-0.002
udd-0.002
 underwear-0.002
ooming-0.002
Token be
Token ID307
Feature activation+1.92e+00

Pos logit contributions
igator+0.002
boat+0.002
eway+0.002
year+0.002
 Amen+0.002
Neg logit contributions
 fault-0.002
 injuries-0.002
 loses-0.002
 blood-0.002
 underwear-0.002
Token careful
Token ID8161
Feature activation-2.43e-01

Pos logit contributions
igator+0.215
 Amen+0.186
boat+0.185
eway+0.178
 Mill+0.171
Neg logit contributions
 fault-0.160
 loses-0.148
joy-0.146
 blood-0.141
udd-0.138
Token.
Token ID13
Feature activation-9.51e-02

Pos logit contributions
 fault+0.020
 loses+0.017
ooming+0.016
udd+0.016
 blood+0.016
Neg logit contributions
igator-0.028
boat-0.024
 Amen-0.024
 particular-0.023
 Mill-0.022
Token The
Token ID383
Feature activation-4.43e-01

Pos logit contributions
 fault+0.009
 loses+0.008
joy+0.008
 blood+0.008
udd+0.007
Neg logit contributions
igator-0.010
boat-0.008
eway-0.008
ull-0.008
igators-0.007
Token all
Token ID477
Feature activation-1.05e+00

Pos logit contributions
 fault+0.041
joy+0.038
 blood+0.037
 loses+0.037
 underwear+0.035
Neg logit contributions
igator-0.041
 Amen-0.038
boat-0.037
eway-0.035
ull-0.035
Tokenigator
Token ID23823
Feature activation+1.20e+01

Pos logit contributions
 loses+0.167
 fault+0.163
 blood+0.157
udd+0.153
 forg+0.153
Neg logit contributions
 Amen-0.023
eway-0.016
boat-0.008
ull-0.007
 Mill-0.007
Token might
Token ID1244
Feature activation-6.29e-01

Pos logit contributions
igator+1.215
 Amen+0.995
boat+0.982
igators+0.914
ull+0.902
Neg logit contributions
 fault-1.149
joy-1.071
 loses-1.043
 underwear-1.013
 blood-1.006
Token bite
Token ID13197
Feature activation-1.00e+00

Pos logit contributions
 fault+0.060
 loses+0.058
 blood+0.054
 injuries+0.051
 underwear+0.050
Neg logit contributions
igator-0.061
 Amen-0.055
boat-0.051
eway-0.050
year-0.049
Token us
Token ID514
Feature activation+3.31e+00

Pos logit contributions
 fault+0.102
 loses+0.096
joy+0.092
 blood+0.090
udd+0.090
Neg logit contributions
igator-0.094
 Amen-0.079
boat-0.076
eway-0.071
ull-0.070
Token if
Token ID611
Feature activation-6.85e-01

Pos logit contributions
igator+0.324
 Amen+0.278
boat+0.267
eway+0.250
ull+0.248
Neg logit contributions
 fault-0.322
 loses-0.301
joy-0.286
 blood-0.282
udd-0.282
Token we
Token ID356
Feature activation-2.75e-01

Pos logit contributions
 fault+0.068
 loses+0.064
joy+0.062
 blood+0.060
udd+0.060
Neg logit contributions
igator-0.065
 Amen-0.055
boat-0.053
eway-0.049
ull-0.049
Token fun
Token ID1257
Feature activation-2.56e+00

Pos logit contributions
igator+0.268
 Amen+0.231
boat+0.225
eway+0.212
ull+0.212
Neg logit contributions
 fault-0.196
 loses-0.181
joy-0.174
 blood-0.168
udd-0.168
Token,
Token ID11
Feature activation+4.78e-01

Pos logit contributions
 fault+0.243
 loses+0.227
joy+0.220
 blood+0.214
udd+0.212
Neg logit contributions
igator-0.259
 Amen-0.219
boat-0.213
eway-0.198
ull-0.196
Token making
Token ID1642
Feature activation-1.75e+00

Pos logit contributions
igator+0.045
boat+0.037
 Amen+0.036
 Mill+0.034
ull+0.034
Neg logit contributions
 fault-0.047
 loses-0.044
udd-0.043
ooming-0.042
joy-0.042
Token the
Token ID262
Feature activation+3.41e-01

Pos logit contributions
 fault+0.179
 loses+0.174
joy+0.173
ooming+0.171
 injuries+0.165
Neg logit contributions
igator-0.152
ull-0.118
 Amen-0.116
 Mill-0.115
eway-0.114
Token all
Token ID477
Feature activation-1.10e+00

Pos logit contributions
igator+0.031
 Amen+0.026
boat+0.025
eway+0.023
ull+0.023
Neg logit contributions
 fault-0.036
 loses-0.033
joy-0.033
 blood-0.032
udd-0.032
Tokenigator
Token ID23823
Feature activation+1.20e+01

Pos logit contributions
 fault+0.161
 blood+0.151
 loses+0.151
joy+0.147
 forg+0.145
Neg logit contributions
 Amen-0.040
igator-0.026
works-0.025
eway-0.024
boat-0.023
Token and
Token ID290
Feature activation-2.56e-01

Pos logit contributions
igator+1.054
 Amen+0.838
boat+0.834
ull+0.771
eway+0.758
Neg logit contributions
 fault-1.278
joy-1.200
 loses-1.179
udd-1.143
 blood-1.138
Token the
Token ID262
Feature activation+2.96e-01

Pos logit contributions
 fault+0.025
 loses+0.023
joy+0.023
 blood+0.022
udd+0.022
Neg logit contributions
igator-0.025
 Amen-0.021
boat-0.021
eway-0.019
ull-0.019
Token bird
Token ID6512
Feature activation-7.42e-01

Pos logit contributions
igator+0.030
 Amen+0.026
boat+0.025
eway+0.023
ull+0.023
Neg logit contributions
 fault-0.028
 loses-0.026
joy-0.025
 blood-0.025
udd-0.024
Token fight
Token ID1907
Feature activation-3.46e-01

Pos logit contributions
 fault+0.073
 loses+0.068
joy+0.067
 blood+0.064
udd+0.064
Neg logit contributions
igator-0.072
 Amen-0.060
boat-0.059
ull-0.055
eway-0.054
Token.
Token ID13
Feature activation+2.89e-03

Pos logit contributions
 fault+0.035
 loses+0.032
joy+0.032
udd+0.031
 underwear+0.031
Neg logit contributions
igator-0.033
 Amen-0.027
boat-0.027
eway-0.025
ull-0.025
Token and
Token ID290
Feature activation-3.75e-01

Pos logit contributions
 fault+0.041
 loses+0.038
joy+0.036
 blood+0.036
udd+0.035
Neg logit contributions
igator-0.046
 Amen-0.040
boat-0.038
eway-0.036
ull-0.035
Token apples
Token ID22514
Feature activation-1.57e+00

Pos logit contributions
 fault+0.032
 loses+0.030
 blood+0.028
joy+0.028
 underwear+0.028
Neg logit contributions
igator-0.041
 Amen-0.036
boat-0.035
eway-0.033
ull-0.032
Token to
Token ID284
Feature activation-3.16e-02

Pos logit contributions
 fault+0.150
 loses+0.140
joy+0.135
 blood+0.132
udd+0.131
Neg logit contributions
igator-0.156
 Amen-0.133
boat-0.128
eway-0.120
ull-0.119
Token the
Token ID262
Feature activation+2.78e-01

Pos logit contributions
 fault+0.003
 loses+0.003
 blood+0.003
joy+0.003
 underwear+0.003
Neg logit contributions
igator-0.003
 Amen-0.003
boat-0.002
eway-0.002
ull-0.002
Token all
Token ID477
Feature activation-1.14e+00

Pos logit contributions
igator+0.027
 Amen+0.024
boat+0.023
eway+0.022
ull+0.022
Neg logit contributions
 fault-0.026
 loses-0.024
joy-0.024
 blood-0.023
 underwear-0.023
Tokenigator
Token ID23823
Feature activation+1.20e+01

Pos logit contributions
 fault+0.110
 loses+0.104
 again+0.104
 anymore+0.103
udd+0.099
Neg logit contributions
 Amen-0.088
eway-0.075
works-0.067
 Mill-0.067
 Ally-0.066
Token,
Token ID11
Feature activation+3.80e-01

Pos logit contributions
igator+1.162
 Amen+0.971
boat+0.949
eway+0.878
ull+0.877
Neg logit contributions
 fault-1.176
 loses-1.096
joy-1.071
 blood-1.039
udd-1.034
Token too
Token ID1165
Feature activation-1.00e-01

Pos logit contributions
igator+0.039
 Amen+0.033
boat+0.032
eway+0.030
ull+0.029
Neg logit contributions
 fault-0.036
 loses-0.033
joy-0.032
udd-0.031
 blood-0.031
Token.
Token ID13
Feature activation-1.12e-01

Pos logit contributions
 fault+0.011
 loses+0.010
joy+0.010
 underwear+0.009
 blood+0.009
Neg logit contributions
igator-0.009
 Amen-0.007
boat-0.007
ull-0.007
eway-0.007
Token The
Token ID383
Feature activation-5.42e-01

Pos logit contributions
 fault+0.014
 loses+0.013
joy+0.013
 blood+0.013
ooming+0.013
Neg logit contributions
igator-0.008
 Amen-0.006
boat-0.006
 Mill-0.005
eway-0.005
Token all
Token ID477
Feature activation-1.16e+00

Pos logit contributions
 fault+0.050
joy+0.046
 loses+0.046
 blood+0.044
udd+0.043
Neg logit contributions
igator-0.053
 Amen-0.047
boat-0.046
eway-0.044
ull-0.043
Token"
Token ID1
Feature activation+4.82e+00

Pos logit contributions
 loses+0.104
udd+0.098
joy+0.097
ooming+0.096
 blood+0.095
Neg logit contributions
igator-0.106
 Amen-0.091
boat-0.084
 Mill-0.082
works-0.081
TokenLook
Token ID8567
Feature activation+4.17e-01

Pos logit contributions
igator+0.447
 Amen+0.373
boat+0.361
eway+0.342
 Mill+0.330
Neg logit contributions
 fault-0.467
 loses-0.457
 blood-0.450
joy-0.449
 underwear-0.434
Token,
Token ID11
Feature activation+5.76e-01

Pos logit contributions
igator+0.029
 Mill+0.021
 Amen+0.021
boat+0.020
 Joey+0.020
Neg logit contributions
 fault-0.052
joy-0.048
 loses-0.047
 blood-0.047
 injuries-0.046
Token an
Token ID281
Feature activation+8.90e-01

Pos logit contributions
igator+0.059
 Amen+0.051
boat+0.051
eway+0.048
ull+0.047
Neg logit contributions
 fault-0.052
 loses-0.049
 blood-0.046
joy-0.046
 underwear-0.045
Token all
Token ID477
Feature activation-1.01e+00

Pos logit contributions
 Amen+0.068
igator+0.068
boat+0.067
works+0.064
eway+0.063
Neg logit contributions
 fault-0.087
 loses-0.080
 blood-0.080
der-0.078
joy-0.075
Tokenigator
Token ID23823
Feature activation+1.20e+01

Pos logit contributions
 loses+0.142
 fault+0.138
 blood+0.134
 anymore+0.128
udd+0.126
Neg logit contributions
 Amen-0.038
eway-0.019
year-0.018
ull-0.016
man-0.016
Token!"
Token ID2474
Feature activation+1.17e+00

Pos logit contributions
igator+1.079
 Amen+0.948
boat+0.897
eway+0.850
ull+0.828
Neg logit contributions
 fault-1.196
 loses-1.182
 blood-1.087
joy-1.083
ooming-1.063
Token Tim
Token ID5045
Feature activation+2.90e-01

Pos logit contributions
igator+0.147
 Amen+0.130
boat+0.128
eway+0.121
ull+0.120
Neg logit contributions
 fault-0.078
 loses-0.075
 blood-0.070
joy-0.069
 underwear-0.067
Token said
Token ID531
Feature activation+1.17e+00

Pos logit contributions
igator+0.029
 Amen+0.024
boat+0.024
eway+0.022
ull+0.022
Neg logit contributions
 fault-0.028
 loses-0.026
joy-0.025
 blood-0.025
udd-0.025
Token.
Token ID13
Feature activation+1.02e-01

Pos logit contributions
igator+0.122
 Amen+0.106
boat+0.102
eway+0.095
igators+0.095
Neg logit contributions
 fault-0.106
 loses-0.100
joy-0.098
 blood-0.094
ooming-0.093
Token He
Token ID679
Feature activation+1.26e+00

Pos logit contributions
igator+0.011
 Amen+0.009
boat+0.009
igators+0.009
works+0.009
Neg logit contributions
 blood-0.008
 fault-0.008
joy-0.008
 loses-0.008
der-0.007
Token there
Token ID612
Feature activation+1.23e+00

Pos logit contributions
igator+0.047
 Amen+0.041
boat+0.039
eway+0.036
ull+0.036
Neg logit contributions
 fault-0.047
 loses-0.044
joy-0.042
 blood-0.042
ooming-0.041
Token was
Token ID373
Feature activation+7.20e-01

Pos logit contributions
igator+0.088
boat+0.068
 Amen+0.066
ull+0.064
 particular+0.062
Neg logit contributions
 fault-0.151
 loses-0.143
joy-0.140
 underwear-0.137
udd-0.136
Token a
Token ID257
Feature activation+4.61e-01

Pos logit contributions
igator+0.060
 Amen+0.049
boat+0.044
ull+0.044
 Mill+0.043
Neg logit contributions
 fault-0.081
 loses-0.079
joy-0.075
ooming-0.074
udd-0.074
Token wild
Token ID4295
Feature activation-6.28e-01

Pos logit contributions
igator+0.043
 Amen+0.036
boat+0.034
ull+0.032
 particular+0.031
Neg logit contributions
 fault-0.048
 loses-0.045
joy-0.043
 blood-0.042
 underwear-0.042
Token all
Token ID477
Feature activation-1.03e+00

Pos logit contributions
 fault+0.053
 loses+0.048
joy+0.048
 blood+0.046
udd+0.046
Neg logit contributions
igator-0.068
 Amen-0.060
boat-0.058
eway-0.056
igators-0.054
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 fault+0.127
 loses+0.123
 blood+0.123
udd+0.123
 forg+0.122
Neg logit contributions
 Amen-0.040
eway-0.029
works-0.027
wood-0.025
 Mill-0.022
Token who
Token ID508
Feature activation-1.52e+00

Pos logit contributions
igator+1.020
 Amen+0.884
eway+0.846
boat+0.836
works+0.807
Neg logit contributions
 loses-1.198
 fault-1.157
ooming-1.102
 blood-1.100
joy-1.093
Token lived
Token ID5615
Feature activation+3.85e+00

Pos logit contributions
 loses+0.141
 forg+0.140
udd+0.139
 blood+0.128
 fault+0.127
Neg logit contributions
igator-0.122
 Amen-0.115
eway-0.113
ole-0.104
works-0.103
Token in
Token ID287
Feature activation+1.35e+00

Pos logit contributions
igator+0.331
 Amen+0.277
boat+0.264
eway+0.244
 Mill+0.244
Neg logit contributions
 fault-0.410
 loses-0.388
joy-0.388
 blood-0.378
udd-0.372
Token a
Token ID257
Feature activation+4.07e-01

Pos logit contributions
igator+0.151
boat+0.135
 Amen+0.130
works+0.129
eway+0.124
Neg logit contributions
 blood-0.100
 fault-0.098
 loses-0.096
joy-0.090
 trouble-0.082
Token big
Token ID1263
Feature activation+3.06e-01

Pos logit contributions
igator+0.040
 Amen+0.034
boat+0.033
eway+0.032
ull+0.031
Neg logit contributions
 fault-0.038
 loses-0.036
joy-0.035
udd-0.035
 blood-0.034
Token not
Token ID407
Feature activation+1.74e+00

Pos logit contributions
 fault+0.097
joy+0.093
udd+0.091
ooming+0.090
 loses+0.090
Neg logit contributions
igator-0.066
 Amen-0.052
eway-0.050
boat-0.048
ull-0.047
Token notice
Token ID4003
Feature activation-4.76e+00

Pos logit contributions
igator+0.175
 Amen+0.152
boat+0.147
eway+0.140
ull+0.135
Neg logit contributions
 fault-0.162
 loses-0.155
 blood-0.145
joy-0.145
 underwear-0.144
Token that
Token ID326
Feature activation-1.74e+00

Pos logit contributions
 fault+0.507
 loses+0.488
joy+0.475
ooming+0.473
udd+0.464
Neg logit contributions
igator-0.412
boat-0.313
 Amen-0.301
ull-0.300
 Mill-0.299
Token the
Token ID262
Feature activation+2.72e-01

Pos logit contributions
 fault+0.192
 loses+0.181
udd+0.175
joy+0.175
ooming+0.173
Neg logit contributions
igator-0.150
 Amen-0.119
boat-0.118
ull-0.108
eway-0.107
Token all
Token ID477
Feature activation-1.15e+00

Pos logit contributions
igator+0.026
 Amen+0.022
boat+0.021
eway+0.020
ull+0.020
Neg logit contributions
 fault-0.027
 loses-0.025
joy-0.025
 blood-0.024
udd-0.024
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 loses+0.174
 blood+0.172
 fault+0.168
 forg+0.166
 anymore+0.165
Neg logit contributions
 Amen-0.029
eway-0.011
 Mill-0.008
wood-0.007
boat-0.006
Token toy
Token ID13373
Feature activation-1.60e+00

Pos logit contributions
igator+0.879
boat+0.659
ull+0.596
 Amen+0.584
man+0.578
Neg logit contributions
 fault-1.511
joy-1.392
udd-1.334
 underwear-1.313
 blood-1.282
Token was
Token ID373
Feature activation+5.67e-01

Pos logit contributions
 fault+0.166
 loses+0.154
joy+0.152
udd+0.147
 blood+0.145
Neg logit contributions
igator-0.148
boat-0.120
 Amen-0.119
ull-0.110
eway-0.109
Token not
Token ID407
Feature activation+1.70e+00

Pos logit contributions
igator+0.067
 Amen+0.058
boat+0.056
ull+0.053
eway+0.053
Neg logit contributions
 fault-0.044
 loses-0.041
joy-0.039
udd-0.038
 blood-0.038
Token a
Token ID257
Feature activation+3.03e-01

Pos logit contributions
igator+0.165
 Amen+0.138
boat+0.134
eway+0.125
ull+0.124
Neg logit contributions
 fault-0.168
 loses-0.158
joy-0.153
 blood-0.149
udd-0.148
Token toy
Token ID13373
Feature activation-1.60e+00

Pos logit contributions
igator+0.030
 Amen+0.025
boat+0.025
ull+0.023
eway+0.023
Neg logit contributions
 fault-0.029
 loses-0.027
joy-0.026
udd-0.026
ooming-0.025
Token,
Token ID11
Feature activation+3.80e-01

Pos logit contributions
igator+1.162
 Amen+0.971
boat+0.949
eway+0.878
ull+0.877
Neg logit contributions
 fault-1.176
 loses-1.096
joy-1.071
 blood-1.039
udd-1.034
Token too
Token ID1165
Feature activation-1.00e-01

Pos logit contributions
igator+0.039
 Amen+0.033
boat+0.032
eway+0.030
ull+0.029
Neg logit contributions
 fault-0.036
 loses-0.033
joy-0.032
udd-0.031
 blood-0.031
Token.
Token ID13
Feature activation-1.12e-01

Pos logit contributions
 fault+0.011
 loses+0.010
joy+0.010
 underwear+0.009
 blood+0.009
Neg logit contributions
igator-0.009
 Amen-0.007
boat-0.007
ull-0.007
eway-0.007
Token The
Token ID383
Feature activation-5.42e-01

Pos logit contributions
 fault+0.014
 loses+0.013
joy+0.013
 blood+0.013
ooming+0.013
Neg logit contributions
igator-0.008
 Amen-0.006
boat-0.006
 Mill-0.005
eway-0.005
Token all
Token ID477
Feature activation-1.16e+00

Pos logit contributions
 fault+0.050
joy+0.046
 loses+0.046
 blood+0.044
udd+0.043
Neg logit contributions
igator-0.053
 Amen-0.047
boat-0.046
eway-0.044
ull-0.043
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 fault+0.162
 forg+0.162
 loses+0.161
 blood+0.158
udd+0.153
Neg logit contributions
 Amen-0.035
eway-0.024
works-0.016
ull-0.010
fire-0.010
Token did
Token ID750
Feature activation-9.46e-01

Pos logit contributions
igator+1.049
boat+0.830
 Amen+0.825
ull+0.762
igators+0.745
Neg logit contributions
 fault-1.315
joy-1.203
 loses-1.187
 underwear-1.153
udd-1.153
Token not
Token ID407
Feature activation+1.64e+00

Pos logit contributions
 fault+0.097
 loses+0.090
joy+0.088
 blood+0.086
udd+0.085
Neg logit contributions
igator-0.089
 Amen-0.074
boat-0.072
eway-0.067
ull-0.067
Token bite
Token ID13197
Feature activation-1.10e+00

Pos logit contributions
igator+0.153
 Amen+0.140
boat+0.130
eway+0.129
ull+0.121
Neg logit contributions
 fault-0.158
 loses-0.154
 blood-0.144
 underwear-0.141
joy-0.138
Token them
Token ID606
Feature activation+1.69e+00

Pos logit contributions
 fault+0.114
joy+0.107
 loses+0.104
udd+0.102
ooming+0.102
Neg logit contributions
igator-0.100
boat-0.077
igators-0.076
ull-0.075
 Mill-0.071
Token.
Token ID13
Feature activation-1.37e-01

Pos logit contributions
igator+0.155
boat+0.122
 Amen+0.116
ull+0.112
igators+0.111
Neg logit contributions
 fault-0.174
joy-0.166
 loses-0.160
 underwear-0.156
udd-0.156
Token his
Token ID465
Feature activation+1.54e+00

Pos logit contributions
 fault+0.062
 blood+0.061
joy+0.060
 loses+0.059
 again+0.057
Neg logit contributions
igator-0.090
 Amen-0.081
boat-0.080
works-0.073
igators-0.072
Token hand
Token ID1021
Feature activation+2.25e+00

Pos logit contributions
igator+0.167
 Amen+0.144
boat+0.140
eway+0.132
ull+0.130
Neg logit contributions
 fault-0.138
 loses-0.127
joy-0.122
 blood-0.119
 underwear-0.118
Token.
Token ID13
Feature activation+3.38e-03

Pos logit contributions
igator+0.257
 Amen+0.227
boat+0.213
igators+0.207
eway+0.206
Neg logit contributions
 fault-0.184
 loses-0.170
 blood-0.164
 underwear-0.160
joy-0.160
Token The
Token ID383
Feature activation-4.49e-01

Pos logit contributions
igator+0.000
 Amen+0.000
boat+0.000
igators+0.000
ull+0.000
Neg logit contributions
 fault-0.000
 loses-0.000
 blood-0.000
joy-0.000
 underwear-0.000
Token all
Token ID477
Feature activation-1.13e+00

Pos logit contributions
 fault+0.038
 blood+0.036
 loses+0.036
joy+0.035
 underwear+0.033
Neg logit contributions
igator-0.043
 Amen-0.040
boat-0.038
eway-0.038
 Mill-0.037
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 blood+0.152
 loses+0.149
 fault+0.143
 forg+0.141
 spills+0.139
Neg logit contributions
 Amen-0.050
works-0.025
eway-0.024
 Mill-0.023
cle-0.021
Token opened
Token ID4721
Feature activation+1.92e+00

Pos logit contributions
igator+0.992
boat+0.775
 Amen+0.718
ull+0.713
man+0.680
Neg logit contributions
 fault-1.405
joy-1.276
udd-1.242
 loses-1.213
 underwear-1.213
Token its
Token ID663
Feature activation+2.98e+00

Pos logit contributions
igator+0.163
 Amen+0.137
boat+0.127
igators+0.118
works+0.117
Neg logit contributions
 fault-0.215
 blood-0.200
joy-0.200
 loses-0.199
 underwear-0.189
Token mouth
Token ID5422
Feature activation-9.71e-01

Pos logit contributions
igator+0.423
 Amen+0.385
boat+0.368
year+0.357
eway+0.349
Neg logit contributions
 fault-0.181
 loses-0.161
 blood-0.151
 underwear-0.135
joy-0.131
Token and
Token ID290
Feature activation-3.35e-01

Pos logit contributions
 fault+0.087
 loses+0.081
joy+0.077
 blood+0.076
udd+0.075
Neg logit contributions
igator-0.104
 Amen-0.090
boat-0.086
eway-0.081
igators-0.080
Token snapped
Token ID20821
Feature activation-8.60e-01

Pos logit contributions
 fault+0.031
 loses+0.030
 blood+0.028
joy+0.028
 underwear+0.028
Neg logit contributions
igator-0.034
 Amen-0.029
boat-0.028
eway-0.027
ull-0.026
Token day
Token ID1110
Feature activation+3.60e+00

Pos logit contributions
igator+0.059
 Amen+0.053
boat+0.047
eway+0.044
 Mill+0.042
Neg logit contributions
 fault-0.114
 loses-0.108
joy-0.105
 blood-0.104
udd-0.103
Token,
Token ID11
Feature activation+4.12e-01

Pos logit contributions
igator+0.336
 Amen+0.286
boat+0.274
eway+0.253
ull+0.250
Neg logit contributions
 fault-0.365
 loses-0.345
joy-0.335
 blood-0.326
ooming-0.325
Token a
Token ID257
Feature activation+3.49e-01

Pos logit contributions
igator+0.045
 Amen+0.042
boat+0.040
eway+0.037
igators+0.037
Neg logit contributions
 fault-0.031
 blood-0.029
 loses-0.029
joy-0.028
ooming-0.026
Token wild
Token ID4295
Feature activation-7.33e-01

Pos logit contributions
igator+0.033
 Amen+0.027
boat+0.027
ull+0.025
 particular+0.024
Neg logit contributions
 fault-0.036
 loses-0.033
joy-0.032
 underwear-0.031
udd-0.031
Token all
Token ID477
Feature activation-1.14e+00

Pos logit contributions
 fault+0.061
 loses+0.056
joy+0.055
 blood+0.054
udd+0.053
Neg logit contributions
igator-0.080
 Amen-0.071
boat-0.068
eway-0.065
igators-0.064
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 loses+0.125
 blood+0.124
 fault+0.122
 anymore+0.120
 forg+0.120
Neg logit contributions
 Amen-0.063
eway-0.046
works-0.044
 carriers-0.044
iona-0.042
Token went
Token ID1816
Feature activation+1.31e+00

Pos logit contributions
igator+0.944
 Amen+0.814
boat+0.744
eway+0.715
 Mill+0.687
Neg logit contributions
 loses-1.307
 fault-1.292
joy-1.223
 blood-1.222
ooming-1.216
Token to
Token ID284
Feature activation-5.67e-02

Pos logit contributions
igator+0.144
 Amen+0.135
boat+0.127
ull+0.123
eway+0.120
Neg logit contributions
 fault-0.097
 loses-0.094
 blood-0.089
udd-0.088
ooming-0.086
Token a
Token ID257
Feature activation+3.30e-01

Pos logit contributions
 fault+0.005
 loses+0.005
 blood+0.004
joy+0.004
 underwear+0.004
Neg logit contributions
igator-0.006
 Amen-0.005
boat-0.005
works-0.005
year-0.005
Token big
Token ID1263
Feature activation+2.05e-01

Pos logit contributions
igator+0.033
 Amen+0.028
boat+0.027
eway+0.026
ull+0.025
Neg logit contributions
 fault-0.031
 loses-0.029
joy-0.028
udd-0.028
 blood-0.028
Token lake
Token ID13546
Feature activation+1.49e+00

Pos logit contributions
igator+0.020
 Amen+0.018
eway+0.018
boat+0.017
year+0.017
Neg logit contributions
 fault-0.017
 loses-0.017
joy-0.017
 blood-0.016
udd-0.016
Token was
Token ID373
Feature activation+5.59e-01

Pos logit contributions
 fault+0.339
 loses+0.330
udd+0.315
joy+0.315
 underwear+0.309
Neg logit contributions
igator-0.394
 Amen-0.341
boat-0.325
eway-0.323
igators-0.304
Token surprised
Token ID6655
Feature activation-1.22e+00

Pos logit contributions
igator+0.053
 Amen+0.045
boat+0.044
eway+0.041
ull+0.040
Neg logit contributions
 fault-0.056
 loses-0.052
joy-0.051
 blood-0.050
 underwear-0.049
Token that
Token ID326
Feature activation-1.84e+00

Pos logit contributions
 fault+0.116
 loses+0.108
joy+0.105
 blood+0.102
udd+0.102
Neg logit contributions
igator-0.124
 Amen-0.106
boat-0.102
eway-0.095
ull-0.095
Token the
Token ID262
Feature activation+1.89e-01

Pos logit contributions
 fault+0.167
 loses+0.157
joy+0.154
 blood+0.146
 underwear+0.146
Neg logit contributions
igator-0.184
 Amen-0.162
boat-0.153
eway-0.151
ull-0.148
Token all
Token ID477
Feature activation-1.24e+00

Pos logit contributions
igator+0.019
 Amen+0.017
boat+0.016
ull+0.016
eway+0.016
Neg logit contributions
 fault-0.017
joy-0.015
 loses-0.015
 blood-0.015
 underwear-0.014
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 loses+0.187
 fault+0.182
 forg+0.178
udd+0.178
 blood+0.177
Neg logit contributions
 Amen-0.035
eway-0.019
ull-0.014
man-0.010
works-0.010
Token could
Token ID714
Feature activation+5.57e-01

Pos logit contributions
igator+1.046
 Amen+0.845
boat+0.829
ull+0.756
eway+0.754
Neg logit contributions
 fault-1.295
 loses-1.205
joy-1.188
 blood-1.151
udd-1.150
Token talk
Token ID1561
Feature activation+2.88e+00

Pos logit contributions
igator+0.052
 Amen+0.047
boat+0.045
eway+0.043
ull+0.043
Neg logit contributions
 fault-0.052
 loses-0.051
 blood-0.050
 underwear-0.047
 injuries-0.046
Token.
Token ID13
Feature activation-2.38e-01

Pos logit contributions
igator+0.295
 Amen+0.255
boat+0.245
eway+0.228
ull+0.228
Neg logit contributions
 fault-0.268
 loses-0.251
joy-0.240
udd-0.234
 blood-0.233
Token He
Token ID679
Feature activation+1.03e+00

Pos logit contributions
 fault+0.027
 loses+0.026
joy+0.025
udd+0.024
 blood+0.024
Neg logit contributions
igator-0.020
 Amen-0.016
boat-0.016
ull-0.014
eway-0.014
Token said
Token ID531
Feature activation+1.01e+00

Pos logit contributions
igator+0.097
 Amen+0.082
boat+0.079
eway+0.075
ull+0.073
Neg logit contributions
 fault-0.102
 loses-0.099
joy-0.094
 underwear-0.092
udd-0.092
Token can
Token ID460
Feature activation+1.40e-01

Pos logit contributions
 fault+0.027
 loses+0.025
 blood+0.023
udd+0.023
 underwear+0.022
Neg logit contributions
igator-0.034
boat-0.030
eway-0.030
 Amen-0.029
ull-0.028
Token share
Token ID2648
Feature activation+2.03e+00

Pos logit contributions
igator+0.013
boat+0.011
eway+0.010
 Amen+0.010
ull+0.010
Neg logit contributions
 fault-0.015
 loses-0.014
 blood-0.013
udd-0.013
 underwear-0.013
Token with
Token ID351
Feature activation+3.01e+00

Pos logit contributions
igator+0.189
 Amen+0.157
boat+0.152
eway+0.141
ull+0.141
Neg logit contributions
 fault-0.208
 loses-0.195
joy-0.190
 blood-0.184
udd-0.184
Token the
Token ID262
Feature activation+3.08e-01

Pos logit contributions
igator+0.284
 Amen+0.238
boat+0.232
eway+0.217
ull+0.212
Neg logit contributions
 fault-0.304
 loses-0.285
joy-0.276
 blood-0.271
udd-0.268
Token all
Token ID477
Feature activation-1.09e+00

Pos logit contributions
igator+0.033
 Amen+0.028
boat+0.027
eway+0.026
ull+0.026
Neg logit contributions
 fault-0.027
 loses-0.025
joy-0.025
 blood-0.024
udd-0.024
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 fault+0.074
 again+0.067
udd+0.065
 loses+0.061
 anymore+0.061
Neg logit contributions
 Amen-0.106
eway-0.101
boat-0.091
 Ally-0.089
 Mill-0.088
Token,
Token ID11
Feature activation+4.02e-01

Pos logit contributions
igator+1.145
 Amen+0.995
boat+0.960
eway+0.910
ull+0.895
Neg logit contributions
 fault-1.165
 loses-1.098
joy-1.037
udd-1.018
 blood-1.008
Token too
Token ID1165
Feature activation-1.32e-01

Pos logit contributions
igator+0.041
 Amen+0.036
boat+0.035
eway+0.034
ull+0.033
Neg logit contributions
 fault-0.037
 loses-0.034
joy-0.032
 blood-0.032
 underwear-0.032
Token.
Token ID13
Feature activation-1.83e-01

Pos logit contributions
 fault+0.014
 loses+0.013
joy+0.013
udd+0.012
 blood+0.012
Neg logit contributions
igator-0.012
 Amen-0.010
boat-0.010
eway-0.009
ull-0.009
Token Maybe
Token ID6674
Feature activation-9.35e-01

Pos logit contributions
 fault+0.015
 loses+0.014
joy+0.014
 blood+0.013
der+0.013
Neg logit contributions
igator-0.020
boat-0.017
eway-0.016
ull-0.016
igators-0.015
Token it
Token ID340
Feature activation+4.11e-01

Pos logit contributions
 fault+0.081
 loses+0.078
 blood+0.074
joy+0.073
 underwear+0.071
Neg logit contributions
igator-0.099
 Amen-0.084
boat-0.083
eway-0.079
ull-0.077
Token
Token ID198
Feature activation-1.26e+00

Pos logit contributions
 fault+0.088
 loses+0.083
joy+0.083
udd+0.080
 blood+0.079
Neg logit contributions
igator-0.147
 Amen-0.124
boat-0.122
igators-0.117
works-0.115
TokenSoon
Token ID28093
Feature activation-1.80e+00

Pos logit contributions
 loses+0.085
ooming+0.084
joy+0.084
udd+0.083
 blood+0.079
Neg logit contributions
igator-0.135
 Amen-0.116
 Mill-0.114
works-0.111
wood-0.106
Token,
Token ID11
Feature activation+4.39e-01

Pos logit contributions
 fault+0.169
 loses+0.158
joy+0.155
 blood+0.149
 underwear+0.147
Neg logit contributions
igator-0.184
 Amen-0.156
boat-0.151
eway-0.141
ull-0.140
Token the
Token ID262
Feature activation+3.03e-01

Pos logit contributions
igator+0.044
 Amen+0.039
boat+0.036
eway+0.035
ull+0.034
Neg logit contributions
 fault-0.038
joy-0.038
 loses-0.036
 blood-0.036
 injuries-0.033
Token all
Token ID477
Feature activation-1.08e+00

Pos logit contributions
igator+0.029
boat+0.026
 Amen+0.026
eway+0.026
ull+0.025
Neg logit contributions
 fault-0.026
joy-0.025
 blood-0.024
 loses-0.023
 underwear-0.023
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 forg+0.133
 blood+0.129
 fault+0.126
 loses+0.125
joy+0.123
Neg logit contributions
 Amen-0.045
eway-0.039
works-0.035
 type-0.029
fire-0.027
Token's
Token ID338
Feature activation-2.78e+00

Pos logit contributions
igator+1.053
boat+0.859
 Amen+0.844
ull+0.781
eway+0.766
Neg logit contributions
 fault-1.293
 loses-1.181
joy-1.164
 blood-1.137
udd-1.133
Token family
Token ID1641
Feature activation+1.18e+00

Pos logit contributions
 fault+0.251
 blood+0.218
joy+0.217
 loses+0.213
 underwear+0.210
Neg logit contributions
igator-0.305
boat-0.253
 Amen-0.251
eway-0.239
igators-0.235
Token wrote
Token ID2630
Feature activation+1.28e+00

Pos logit contributions
igator+0.108
 Amen+0.091
boat+0.086
eway+0.082
ull+0.079
Neg logit contributions
 fault-0.121
 loses-0.114
joy-0.111
 blood-0.108
udd-0.108
Token back
Token ID736
Feature activation-2.81e+00

Pos logit contributions
igator+0.130
 Amen+0.110
boat+0.105
igators+0.098
eway+0.098
Neg logit contributions
 fault-0.120
 loses-0.112
joy-0.110
 blood-0.106
udd-0.105
Token.
Token ID13
Feature activation-7.79e-02

Pos logit contributions
 fault+0.275
 loses+0.256
joy+0.252
 blood+0.241
udd+0.240
Neg logit contributions
igator-0.275
 Amen-0.237
boat-0.225
ull-0.210
eway-0.208
Token.
Token ID13
Feature activation+7.33e-02

Pos logit contributions
 fault+0.186
joy+0.174
 loses+0.173
ooming+0.165
udd+0.165
Neg logit contributions
igator-0.164
boat-0.131
 Amen-0.131
ull-0.124
eway-0.123
Token It
Token ID632
Feature activation+1.09e+00

Pos logit contributions
igator+0.007
boat+0.006
 Amen+0.006
eway+0.005
igators+0.005
Neg logit contributions
 fault-0.007
 loses-0.007
joy-0.007
 blood-0.006
 underwear-0.006
Token was
Token ID373
Feature activation+7.10e-01

Pos logit contributions
igator+0.110
 Amen+0.104
boat+0.098
eway+0.096
 Mill+0.091
Neg logit contributions
 loses-0.091
 blood-0.088
 underwear-0.082
 fault-0.082
 forg-0.080
Token an
Token ID281
Feature activation+8.96e-01

Pos logit contributions
igator+0.073
 Amen+0.066
boat+0.064
eway+0.058
ull+0.056
Neg logit contributions
 fault-0.066
 blood-0.062
 loses-0.060
joy-0.058
 underwear-0.057
Token all
Token ID477
Feature activation-9.71e-01

Pos logit contributions
 Amen+0.079
igator+0.076
boat+0.072
eway+0.070
works+0.067
Neg logit contributions
 fault-0.087
 loses-0.078
 blood-0.077
der-0.072
 underwear-0.072
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 fault+0.132
 loses+0.127
 blood+0.126
 anymore+0.114
 underwear+0.114
Neg logit contributions
 Amen-0.048
eway-0.026
boat-0.025
iona-0.024
 Ally-0.022
Token!
Token ID0
Feature activation-9.15e-01

Pos logit contributions
igator+1.207
 Amen+1.048
boat+1.008
eway+0.947
ull+0.937
Neg logit contributions
 fault-1.104
 loses-1.053
joy-0.991
 blood-0.974
 underwear-0.962
Token
Token ID198
Feature activation-1.12e+00

Pos logit contributions
 fault+0.083
 loses+0.079
joy+0.077
 blood+0.075
 underwear+0.072
Neg logit contributions
igator-0.095
 Amen-0.080
boat-0.079
eway-0.072
igators-0.072
Token
Token ID198
Feature activation-1.13e+00

Pos logit contributions
 fault+0.097
 loses+0.090
joy+0.087
 blood+0.085
udd+0.085
Neg logit contributions
igator-0.122
 Amen-0.104
boat-0.102
eway-0.094
igators-0.093
Token"
Token ID1
Feature activation+4.82e+00

Pos logit contributions
 loses+0.104
udd+0.098
joy+0.097
ooming+0.096
 blood+0.095
Neg logit contributions
igator-0.106
 Amen-0.091
boat-0.084
 Mill-0.082
works-0.081
TokenLook
Token ID8567
Feature activation+4.17e-01

Pos logit contributions
igator+0.447
 Amen+0.373
boat+0.361
eway+0.342
 Mill+0.330
Neg logit contributions
 fault-0.467
 loses-0.457
 blood-0.450
joy-0.449
 underwear-0.434
Token and
Token ID290
Feature activation-2.87e-01

Pos logit contributions
igator+0.044
 Amen+0.039
boat+0.036
eway+0.035
igators+0.034
Neg logit contributions
 fault-0.035
 loses-0.032
joy-0.032
udd-0.030
 blood-0.030
Token safely
Token ID11512
Feature activation-1.77e+00

Pos logit contributions
 fault+0.025
 loses+0.025
joy+0.024
 blood+0.024
 forg+0.023
Neg logit contributions
igator-0.028
 Amen-0.026
boat-0.024
eway-0.023
ull-0.023
Token removed
Token ID4615
Feature activation-1.14e+00

Pos logit contributions
 fault+0.171
 loses+0.160
joy+0.155
 blood+0.151
udd+0.150
Neg logit contributions
igator-0.175
 Amen-0.148
boat-0.143
eway-0.134
ull-0.133
Token the
Token ID262
Feature activation+3.59e-01

Pos logit contributions
 fault+0.117
 loses+0.109
joy+0.106
 blood+0.105
 underwear+0.102
Neg logit contributions
igator-0.104
 Amen-0.092
boat-0.087
eway-0.080
ull-0.079
Token all
Token ID477
Feature activation-1.12e+00

Pos logit contributions
igator+0.037
 Amen+0.030
boat+0.030
igators+0.028
eway+0.028
Neg logit contributions
 fault-0.034
 loses-0.032
joy-0.031
udd-0.030
ooming-0.030
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 fault+0.130
 blood+0.125
 loses+0.122
udd+0.121
 again+0.121
Neg logit contributions
 Amen-0.080
eway-0.050
works-0.049
igator-0.048
 type-0.047
Token.
Token ID13
Feature activation-1.00e-01

Pos logit contributions
igator+1.010
boat+0.789
 Amen+0.766
eway+0.721
igators+0.709
Neg logit contributions
 fault-1.326
 loses-1.238
joy-1.237
udd-1.199
 underwear-1.193
Token Tim
Token ID5045
Feature activation+1.85e-01

Pos logit contributions
 fault+0.009
joy+0.008
 loses+0.008
udd+0.008
 blood+0.008
Neg logit contributions
igator-0.010
boat-0.009
 Amen-0.009
ull-0.008
eway-0.008
Tokenmy
Token ID1820
Feature activation+6.17e-01

Pos logit contributions
igator+0.018
boat+0.014
 Amen+0.014
ull+0.013
man+0.013
Neg logit contributions
 fault-0.019
 loses-0.018
joy-0.017
 blood-0.017
 underwear-0.016
Token and
Token ID290
Feature activation-3.04e-01

Pos logit contributions
igator+0.055
 Amen+0.045
boat+0.045
ull+0.041
eway+0.040
Neg logit contributions
 fault-0.066
 loses-0.061
joy-0.060
 blood-0.058
 underwear-0.058
Token his
Token ID465
Feature activation+1.56e+00

Pos logit contributions
 fault+0.029
joy+0.027
 loses+0.027
 blood+0.026
 underwear+0.026
Neg logit contributions
igator-0.028
 Amen-0.026
boat-0.025
eway-0.024
works-0.023
Token a
Token ID257
Feature activation+3.76e-01

Pos logit contributions
igator+0.079
 Amen+0.076
boat+0.070
eway+0.063
works+0.063
Neg logit contributions
 fault-0.052
 blood-0.050
joy-0.045
 underwear-0.044
 loses-0.043
Token big
Token ID1263
Feature activation+3.03e-01

Pos logit contributions
igator+0.038
 Amen+0.034
eway+0.032
boat+0.032
igators+0.031
Neg logit contributions
 fault-0.033
joy-0.031
 loses-0.031
 blood-0.031
 underwear-0.030
Token,
Token ID11
Feature activation+4.59e-01

Pos logit contributions
igator+0.030
 Amen+0.027
eway+0.026
year+0.025
boat+0.025
Neg logit contributions
 fault-0.027
joy-0.026
 loses-0.025
 blood-0.025
 underwear-0.024
Token green
Token ID4077
Feature activation+1.16e+00

Pos logit contributions
igator+0.044
 Amen+0.044
eway+0.040
boat+0.040
man+0.037
Neg logit contributions
 loses-0.037
 blood-0.037
 fault-0.037
 underwear-0.037
joy-0.036
Token all
Token ID477
Feature activation-1.11e+00

Pos logit contributions
igator+0.118
 Amen+0.115
year+0.106
 Mill+0.101
eway+0.101
Neg logit contributions
 blood-0.089
 fault-0.087
joy-0.084
 loses-0.084
 underwear-0.083
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 fault+0.126
 blood+0.123
 loses+0.119
udd+0.118
 anymore+0.117
Neg logit contributions
 Amen-0.072
cle-0.047
person-0.046
iona-0.045
eway-0.044
Token!
Token ID0
Feature activation-9.91e-01

Pos logit contributions
igator+1.192
 Amen+1.018
boat+0.983
eway+0.919
ull+0.910
Neg logit contributions
 fault-1.129
 loses-1.067
joy-1.026
 blood-1.000
 underwear-0.990
Token The
Token ID383
Feature activation-4.20e-01

Pos logit contributions
 fault+0.100
 loses+0.094
joy+0.092
 blood+0.090
udd+0.089
Neg logit contributions
igator-0.094
 Amen-0.078
boat-0.077
eway-0.071
ull-0.070
Token children
Token ID1751
Feature activation-2.48e+00

Pos logit contributions
 fault+0.033
joy+0.032
 blood+0.031
 loses+0.030
 underwear+0.029
Neg logit contributions
igator-0.041
 Amen-0.038
boat-0.038
eway-0.038
ull-0.037
Token were
Token ID547
Feature activation-1.00e+00

Pos logit contributions
 loses+0.184
 fault+0.176
 blood+0.171
ooming+0.170
joy+0.170
Neg logit contributions
igator-0.270
 Amen-0.259
eway-0.230
boat-0.230
 particular-0.221
Token so
Token ID523
Feature activation+1.98e+00

Pos logit contributions
 fault+0.089
 loses+0.083
joy+0.080
 blood+0.079
 underwear+0.077
Neg logit contributions
igator-0.107
 Amen-0.092
boat-0.091
eway-0.085
 particular-0.082
Token
Token ID26391
Feature activation+1.28e+00

Pos logit contributions
 fault+0.118
 loses+0.117
udd+0.112
joy+0.110
ooming+0.105
Neg logit contributions
igator-0.119
 Amen-0.102
boat-0.097
ull-0.097
 Mill-0.094
Token
Token ID129
Feature activation-2.65e+00

Pos logit contributions
igator+0.113
 Amen+0.099
boat+0.096
ull+0.088
eway+0.088
Neg logit contributions
 fault-0.134
 blood-0.122
 loses-0.120
 underwear-0.117
joy-0.116
Token
Token ID241
Feature activation+7.23e-02

Pos logit contributions
 fault+0.253
 loses+0.242
udd+0.230
joy+0.222
 underwear+0.220
Neg logit contributions
igator-0.263
 Amen-0.225
boat-0.222
ull-0.207
 Mill-0.201
TokenHello
Token ID15496
Feature activation+3.07e+00

Pos logit contributions
igator+0.007
 Amen+0.006
boat+0.006
eway+0.005
igators+0.005
Neg logit contributions
 fault-0.007
 loses-0.007
joy-0.007
 blood-0.006
 underwear-0.006
Token all
Token ID477
Feature activation-1.17e+00

Pos logit contributions
igator+0.249
 Amen+0.202
boat+0.193
ull+0.176
 Mill+0.176
Neg logit contributions
 fault-0.354
 loses-0.327
joy-0.318
 blood-0.316
 underwear-0.312
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
udd+0.158
 loses+0.153
 fault+0.152
 forg+0.148
 anymore+0.147
Neg logit contributions
 Amen-0.038
fire-0.020
ull-0.018
works-0.016
eway-0.015
Token!
Token ID0
Feature activation-1.09e+00

Pos logit contributions
igator+1.258
 Amen+1.167
eway+1.125
boat+1.119
 particular+1.072
Neg logit contributions
 loses-0.935
 fault-0.905
joy-0.847
ooming-0.810
udd-0.804
Tokenâ
Token ID22940
Feature activation-1.32e-01

Pos logit contributions
 fault+0.107
joy+0.105
 loses+0.104
 blood+0.097
 underwear+0.096
Neg logit contributions
igator-0.099
boat-0.083
eway-0.077
 Amen-0.077
ull-0.077
Token
Token ID26391
Feature activation+1.31e+00

Pos logit contributions
udd+0.012
 fault+0.011
 loses+0.011
joy+0.011
ooming+0.010
Neg logit contributions
igator-0.012
 Amen-0.011
eway-0.010
ull-0.010
 Mill-0.010
Token.
Token ID13
Feature activation-2.58e-01

Pos logit contributions
igator+0.118
 Amen+0.101
boat+0.097
eway+0.090
ull+0.090
Neg logit contributions
 fault-0.136
 loses-0.124
 blood-0.123
joy-0.120
 underwear-0.119
Token
Token ID198
Feature activation-1.35e+00

Pos logit contributions
 fault+0.026
 loses+0.025
joy+0.025
 blood+0.024
 underwear+0.023
Neg logit contributions
igator-0.024
boat-0.019
 Amen-0.019
eway-0.018
ull-0.018
Token swamp
Token ID26837
Feature activation+3.69e+00

Pos logit contributions
igator+0.038
 Amen+0.034
boat+0.032
eway+0.031
ull+0.031
Neg logit contributions
 fault-0.039
 loses-0.036
 blood-0.036
joy-0.036
 underwear-0.034
Token glow
Token ID19634
Feature activation+2.03e+00

Pos logit contributions
igator+0.338
 Amen+0.299
boat+0.279
eway+0.253
ull+0.252
Neg logit contributions
 fault-0.378
 loses-0.363
udd-0.340
 underwear-0.337
joy-0.336
Token.
Token ID13
Feature activation+1.23e-02

Pos logit contributions
igator+0.213
 Amen+0.198
boat+0.178
 Mill+0.169
eway+0.168
Neg logit contributions
 fault-0.172
 loses-0.164
udd-0.152
 blood-0.151
joy-0.150
Token The
Token ID383
Feature activation-3.62e-01

Pos logit contributions
igator+0.001
 Amen+0.001
boat+0.001
eway+0.001
ull+0.001
Neg logit contributions
 fault-0.001
joy-0.001
 loses-0.001
 blood-0.001
udd-0.001
Token all
Token ID477
Feature activation-9.88e-01

Pos logit contributions
 blood+0.029
 fault+0.029
joy+0.028
 underwear+0.027
 forg+0.026
Neg logit contributions
igator-0.032
 Amen-0.031
boat-0.031
eway-0.029
ull-0.029
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 blood+0.120
 loses+0.119
 forg+0.118
 slid+0.113
 again+0.111
Neg logit contributions
 Amen-0.038
ole-0.029
works-0.027
cle-0.026
eway-0.024
Token and
Token ID290
Feature activation-2.32e-01

Pos logit contributions
igator+1.076
 Amen+0.893
boat+0.865
eway+0.799
ull+0.794
Neg logit contributions
 fault-1.251
 loses-1.177
joy-1.142
 blood-1.114
udd-1.110
Token his
Token ID465
Feature activation+1.65e+00

Pos logit contributions
 blood+0.017
joy+0.016
 fault+0.016
 elbow+0.015
 forg+0.015
Neg logit contributions
 Amen-0.022
igator-0.021
works-0.020
eway-0.020
year-0.019
Token friends
Token ID2460
Feature activation-1.90e+00

Pos logit contributions
igator+0.196
 Amen+0.170
boat+0.167
eway+0.158
ull+0.157
Neg logit contributions
 fault-0.127
 loses-0.117
joy-0.112
 blood-0.108
udd-0.108
Token were
Token ID547
Feature activation-9.18e-01

Pos logit contributions
 fault+0.173
 loses+0.167
joy+0.159
 underwear+0.157
udd+0.157
Neg logit contributions
igator-0.189
 Amen-0.165
boat-0.155
eway-0.151
 particular-0.144
Token very
Token ID845
Feature activation+2.99e+00

Pos logit contributions
 fault+0.088
 loses+0.081
joy+0.079
 blood+0.076
udd+0.076
Neg logit contributions
igator-0.093
 Amen-0.078
boat-0.077
eway-0.071
igators-0.069
Token.
Token ID13
Feature activation-2.58e-01

Pos logit contributions
igator+0.118
 Amen+0.101
boat+0.097
eway+0.090
ull+0.090
Neg logit contributions
 fault-0.136
 loses-0.124
 blood-0.123
joy-0.120
 underwear-0.119
Token
Token ID198
Feature activation-1.35e+00

Pos logit contributions
 fault+0.026
 loses+0.025
joy+0.025
 blood+0.024
 underwear+0.023
Neg logit contributions
igator-0.024
boat-0.019
 Amen-0.019
eway-0.018
ull-0.018
Token
Token ID198
Feature activation-1.35e+00

Pos logit contributions
 fault+0.131
 loses+0.121
joy+0.117
 underwear+0.114
 blood+0.114
Neg logit contributions
igator-0.134
 Amen-0.115
boat-0.111
eway-0.105
ull-0.104
TokenThe
Token ID464
Feature activation+2.35e-01

Pos logit contributions
 loses+0.108
joy+0.106
udd+0.105
 fault+0.104
ooming+0.100
Neg logit contributions
igator-0.146
 Amen-0.124
boat-0.122
ull-0.118
 Mill-0.115
Token all
Token ID477
Feature activation-1.21e+00

Pos logit contributions
igator+0.023
 Amen+0.022
boat+0.021
eway+0.020
ull+0.020
Neg logit contributions
 fault-0.019
joy-0.018
 loses-0.017
 blood-0.017
udd-0.016
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 loses+0.168
 forg+0.167
udd+0.167
 fault+0.163
 blood+0.160
Neg logit contributions
 Amen-0.036
eway-0.022
fire-0.020
works-0.017
ull-0.014
Token replied
Token ID8712
Feature activation+3.33e+00

Pos logit contributions
igator+1.046
boat+0.832
 Amen+0.831
ull+0.760
igators+0.748
Neg logit contributions
 fault-1.316
 loses-1.191
joy-1.189
 blood-1.151
udd-1.145
Token
Token ID6184
Feature activation-1.75e+00

Pos logit contributions
igator+0.308
 Amen+0.258
boat+0.250
eway+0.230
ull+0.227
Neg logit contributions
 fault-0.344
 loses-0.324
joy-0.318
 blood-0.307
udd-0.306
Token
Token ID95
Feature activation-1.24e+00

Pos logit contributions
 fault+0.157
 loses+0.156
joy+0.153
ooming+0.146
udd+0.144
Neg logit contributions
igator-0.171
 Amen-0.150
boat-0.144
ull-0.140
eway-0.138
Token
Token ID26391
Feature activation+1.34e+00

Pos logit contributions
 fault+0.119
 loses+0.115
joy+0.111
udd+0.108
ooming+0.103
Neg logit contributions
igator-0.113
 Amen-0.098
boat-0.093
ull-0.092
 Mill-0.089
Token
Token ID129
Feature activation-2.62e+00

Pos logit contributions
igator+0.129
 Amen+0.112
boat+0.109
eway+0.101
ull+0.101
Neg logit contributions
 fault-0.129
 blood-0.117
 loses-0.115
 underwear-0.112
joy-0.110
Token sweet
Token ID6029
Feature activation+4.61e-01

Pos logit contributions
igator+0.025
 Amen+0.020
boat+0.020
eway+0.020
igators+0.020
Neg logit contributions
 fault-0.023
joy-0.022
 blood-0.021
 loses-0.021
 underwear-0.021
Token treat
Token ID2190
Feature activation+9.47e-01

Pos logit contributions
igator+0.048
boat+0.041
 Amen+0.041
eway+0.041
igators+0.040
Neg logit contributions
 fault-0.039
joy-0.037
 blood-0.036
 underwear-0.034
 loses-0.033
Token.
Token ID13
Feature activation-7.01e-02

Pos logit contributions
igator+0.101
 Amen+0.094
eway+0.084
igators+0.083
boat+0.082
Neg logit contributions
 fault-0.077
 blood-0.067
 loses-0.067
joy-0.066
 underwear-0.066
Token The
Token ID383
Feature activation-4.85e-01

Pos logit contributions
 fault+0.006
joy+0.006
 loses+0.006
 blood+0.005
 underwear+0.005
Neg logit contributions
igator-0.007
boat-0.006
 Amen-0.006
ull-0.006
eway-0.006
Token all
Token ID477
Feature activation-1.06e+00

Pos logit contributions
 fault+0.039
joy+0.037
 blood+0.035
 underwear+0.034
 loses+0.033
Neg logit contributions
igator-0.049
 Amen-0.045
boat-0.044
eway-0.044
ull-0.043
Tokenigator
Token ID23823
Feature activation+1.19e+01

Pos logit contributions
 forg+0.136
 blood+0.133
 loses+0.125
 fault+0.125
 scrap+0.124
Neg logit contributions
 Amen-0.032
eway-0.032
works-0.030
fire-0.021
wood-0.021
Token was
Token ID373
Feature activation+6.05e-01

Pos logit contributions
igator+1.120
 Amen+0.960
boat+0.906
eway+0.866
ull+0.839
Neg logit contributions
 fault-1.174
 loses-1.133
joy-1.081
 blood-1.056
udd-1.053
Token so
Token ID523
Feature activation+2.02e+00

Pos logit contributions
igator+0.064
boat+0.054
 Amen+0.053
eway+0.053
works+0.053
Neg logit contributions
 fault-0.053
joy-0.048
 blood-0.048
 loses-0.046
 underwear-0.045
Token happy
Token ID3772
Feature activation-4.08e-01

Pos logit contributions
igator+0.230
boat+0.208
eway+0.206
 Amen+0.205
works+0.196
Neg logit contributions
 fault-0.141
 loses-0.137
udd-0.135
joy-0.129
 blood-0.129
Token.
Token ID13
Feature activation-1.91e-02

Pos logit contributions
 fault+0.040
 loses+0.038
joy+0.036
udd+0.035
 blood+0.035
Neg logit contributions
igator-0.039
 Amen-0.033
boat-0.032
eway-0.030
ull-0.030
Token He
Token ID679
Feature activation+1.12e+00

Pos logit contributions
 fault+0.002
joy+0.002
 loses+0.002
 blood+0.002
udd+0.002
Neg logit contributions
igator-0.002
 Amen-0.002
boat-0.002
ull-0.001
eway-0.001
Token into
Token ID656
Feature activation-1.69e+00

Pos logit contributions
 fault+0.348
joy+0.323
ooming+0.305
udd+0.302
 loses+0.299
Neg logit contributions
igator-0.263
boat-0.202
 Amen-0.195
man-0.186
igators-0.180
Token pieces
Token ID5207
Feature activation-3.22e+00

Pos logit contributions
 fault+0.168
 loses+0.159
joy+0.155
 blood+0.154
 underwear+0.148
Neg logit contributions
igator-0.159
 Amen-0.136
boat-0.133
ull-0.122
eway-0.119
Token and
Token ID290
Feature activation-8.03e-01

Pos logit contributions
 fault+0.319
 loses+0.297
 blood+0.282
joy+0.280
udd+0.278
Neg logit contributions
igator-0.305
 Amen-0.271
boat-0.249
eway-0.236
ull-0.233
Token stopped
Token ID5025
Feature activation-2.35e+00

Pos logit contributions
 fault+0.075
 loses+0.074
 blood+0.068
 underwear+0.068
 elbow+0.065
Neg logit contributions
igator-0.078
 Amen-0.071
boat-0.065
eway-0.062
ull-0.062
Token z
Token ID1976
Feature activation-3.60e+00

Pos logit contributions
 fault+0.227
 loses+0.215
udd+0.205
joy+0.201
 underwear+0.201
Neg logit contributions
igator-0.226
 Amen-0.190
boat-0.184
ull-0.177
 Mill-0.174
Tokenooming
Token ID30602
Feature activation-1.16e+01

Pos logit contributions
 fault+0.179
 blood+0.144
 loses+0.139
 underwear+0.126
joy+0.123
Neg logit contributions
igator-0.502
boat-0.459
ull-0.435
eway-0.435
ot-0.432
Token.
Token ID13
Feature activation-3.51e-01

Pos logit contributions
 fault+1.165
 loses+1.104
joy+1.063
 blood+1.032
udd+1.028
Neg logit contributions
igator-1.072
 Amen-0.956
boat-0.856
ull-0.810
eway-0.802
Token Sam
Token ID3409
Feature activation+4.98e-01

Pos logit contributions
 fault+0.034
joy+0.032
 loses+0.031
 underwear+0.030
 blood+0.030
Neg logit contributions
igator-0.034
 Amen-0.029
boat-0.028
ull-0.026
eway-0.026
Token cried
Token ID16896
Feature activation-2.09e+00

Pos logit contributions
igator+0.047
 Amen+0.040
boat+0.038
eway+0.036
ull+0.035
Neg logit contributions
 fault-0.050
 loses-0.047
joy-0.045
udd-0.044
 blood-0.044
Token and
Token ID290
Feature activation-5.43e-01

Pos logit contributions
 fault+0.216
 loses+0.204
joy+0.195
udd+0.190
 underwear+0.189
Neg logit contributions
igator-0.190
 Amen-0.159
boat-0.155
 Mill-0.144
ull-0.144
Token dropped
Token ID5710
Feature activation-4.66e+00

Pos logit contributions
 fault+0.047
 loses+0.045
joy+0.043
 blood+0.042
 underwear+0.042
Neg logit contributions
igator-0.058
 Amen-0.050
boat-0.049
eway-0.047
ull-0.046
Token long
Token ID890
Feature activation-7.07e-01

Pos logit contributions
igator+0.046
 Amen+0.039
boat+0.038
eway+0.036
ull+0.036
Neg logit contributions
 fault-0.040
 loses-0.037
joy-0.036
 blood-0.035
 underwear-0.035
Token,
Token ID11
Feature activation-2.10e-02

Pos logit contributions
 fault+0.082
 loses+0.077
udd+0.075
joy+0.075
ooming+0.073
Neg logit contributions
igator-0.055
boat-0.041
 Amen-0.041
 Mill-0.040
igators-0.039
Token Billy
Token ID15890
Feature activation+2.00e+00

Pos logit contributions
 fault+0.002
 loses+0.002
joy+0.002
 blood+0.002
 underwear+0.002
Neg logit contributions
igator-0.002
 Amen-0.002
boat-0.002
eway-0.002
ull-0.002
Token was
Token ID373
Feature activation+4.54e-01

Pos logit contributions
igator+0.173
boat+0.134
 Amen+0.127
man+0.121
igators+0.121
Neg logit contributions
 fault-0.223
joy-0.205
ooming-0.198
 loses-0.197
 blood-0.196
Token z
Token ID1976
Feature activation-3.36e+00

Pos logit contributions
igator+0.044
 Amen+0.036
boat+0.035
ull+0.033
eway+0.032
Neg logit contributions
 fault-0.045
 loses-0.042
joy-0.040
udd-0.040
ooming-0.039
Tokenooming
Token ID30602
Feature activation-1.14e+01

Pos logit contributions
 fault+0.195
 loses+0.164
 blood+0.155
 underwear+0.146
udd+0.138
Neg logit contributions
igator-0.457
boat-0.416
ull-0.384
 Amen-0.378
eway-0.377
Token all
Token ID477
Feature activation-1.43e+00

Pos logit contributions
 fault+1.203
 loses+1.154
joy+1.123
 blood+1.085
udd+1.085
Neg logit contributions
igator-0.977
 Amen-0.870
boat-0.768
ull-0.728
eway-0.713
Token over
Token ID625
Feature activation+3.31e+00

Pos logit contributions
 fault+0.135
 loses+0.126
joy+0.126
udd+0.123
 blood+0.122
Neg logit contributions
 Amen-0.121
igator-0.110
works-0.099
ull-0.099
eway-0.096
Token the
Token ID262
Feature activation+3.73e-02

Pos logit contributions
igator+0.265
boat+0.208
 Amen+0.204
eway+0.192
ull+0.191
Neg logit contributions
 fault-0.382
 loses-0.360
udd-0.347
 underwear-0.341
ooming-0.340
Token place
Token ID1295
Feature activation+2.41e+00

Pos logit contributions
igator+0.003
 Amen+0.003
boat+0.003
eway+0.003
ull+0.003
Neg logit contributions
 fault-0.004
 loses-0.004
joy-0.003
 blood-0.003
udd-0.003
Token!
Token ID0
Feature activation-1.14e+00

Pos logit contributions
igator+0.238
 Amen+0.209
boat+0.193
ull+0.181
eway+0.181
Neg logit contributions
 fault-0.234
 loses-0.216
joy-0.211
 blood-0.204
udd-0.203
Token the
Token ID262
Feature activation+4.21e-02

Pos logit contributions
igator+0.101
 Amen+0.087
boat+0.083
ull+0.077
works+0.077
Neg logit contributions
 fault-0.087
joy-0.079
 loses-0.078
 blood-0.077
 injuries-0.072
Token air
Token ID1633
Feature activation-1.21e+00

Pos logit contributions
igator+0.004
 Amen+0.004
boat+0.004
eway+0.004
ull+0.004
Neg logit contributions
 fault-0.004
 loses-0.003
joy-0.003
 blood-0.003
udd-0.003
Token and
Token ID290
Feature activation-4.89e-01

Pos logit contributions
 fault+0.108
 loses+0.098
udd+0.093
joy+0.093
 blood+0.091
Neg logit contributions
igator-0.128
 Amen-0.114
boat-0.105
eway-0.102
ull-0.101
Token make
Token ID787
Feature activation+1.05e+00

Pos logit contributions
 fault+0.051
 loses+0.049
 blood+0.046
 underwear+0.046
joy+0.045
Neg logit contributions
igator-0.045
 Amen-0.037
boat-0.036
eway-0.034
ull-0.034
Token z
Token ID1976
Feature activation-3.39e+00

Pos logit contributions
igator+0.085
 Amen+0.070
boat+0.068
ull+0.066
eway+0.065
Neg logit contributions
 fault-0.115
 loses-0.109
joy-0.109
ooming-0.105
udd-0.103
Tokenooming
Token ID30602
Feature activation-1.12e+01

Pos logit contributions
 fault+0.226
 loses+0.196
joy+0.194
 blood+0.186
 underwear+0.184
Neg logit contributions
igator-0.417
boat-0.383
ull-0.368
 Amen-0.363
eway-0.351
Token noises
Token ID26782
Feature activation-9.05e-01

Pos logit contributions
 fault+1.086
 loses+1.047
udd+0.971
joy+0.968
 blood+0.957
Neg logit contributions
igator-1.100
 Amen-0.971
boat-0.867
 particular-0.828
 Mill-0.827
Token.
Token ID13
Feature activation-2.23e-01

Pos logit contributions
 fault+0.089
 loses+0.083
joy+0.081
 blood+0.079
udd+0.078
Neg logit contributions
igator-0.088
 Amen-0.074
boat-0.072
eway-0.067
ull-0.067
Token Lily
Token ID20037
Feature activation-1.42e+00

Pos logit contributions
 fault+0.024
 loses+0.023
joy+0.022
 blood+0.022
udd+0.022
Neg logit contributions
igator-0.019
 Amen-0.015
boat-0.015
eway-0.014
ull-0.014
Token liked
Token ID8288
Feature activation+8.48e-01

Pos logit contributions
 fault+0.162
joy+0.150
 loses+0.150
 blood+0.146
ooming+0.143
Neg logit contributions
igator-0.117
 Amen-0.094
boat-0.093
ull-0.084
igators-0.082
Token to
Token ID284
Feature activation-3.14e-02

Pos logit contributions
igator+0.081
 Amen+0.067
boat+0.065
ull+0.061
eway+0.061
Neg logit contributions
 fault-0.085
 loses-0.080
joy-0.077
udd-0.076
ooming-0.075
Token!"
Token ID2474
Feature activation+7.85e-01

Pos logit contributions
igator+0.132
 Amen+0.106
boat+0.102
eway+0.093
ull+0.093
Neg logit contributions
 fault-0.196
 loses-0.185
joy-0.180
 blood-0.176
udd-0.176
Token Ben
Token ID3932
Feature activation-4.72e+00

Pos logit contributions
igator+0.087
 Amen+0.074
boat+0.072
eway+0.068
igators+0.068
Neg logit contributions
 fault-0.068
 loses-0.061
joy-0.060
udd-0.059
ooming-0.057
Token said
Token ID531
Feature activation+8.71e-01

Pos logit contributions
 fault+0.349
 loses+0.348
 underwear+0.328
joy+0.311
udd+0.308
Neg logit contributions
igator-0.543
 Amen-0.499
eway-0.459
boat-0.456
igators-0.439
Token,
Token ID11
Feature activation+1.55e-01

Pos logit contributions
igator+0.094
 Amen+0.081
boat+0.079
igators+0.076
eway+0.074
Neg logit contributions
 fault-0.075
joy-0.071
 loses-0.070
 underwear-0.066
ooming-0.066
Token z
Token ID1976
Feature activation-3.45e+00

Pos logit contributions
igator+0.017
 Amen+0.014
boat+0.014
igators+0.014
eway+0.014
Neg logit contributions
joy-0.012
 fault-0.012
 loses-0.012
 blood-0.012
ooming-0.011
Tokenooming
Token ID30602
Feature activation-1.12e+01

Pos logit contributions
 fault+0.174
 loses+0.148
 blood+0.133
joy+0.130
udd+0.128
Neg logit contributions
igator-0.502
boat-0.449
 Amen-0.449
ull-0.428
eway-0.423
Token his
Token ID465
Feature activation+1.33e+00

Pos logit contributions
 fault+1.083
joy+1.083
 loses+1.066
 blood+1.025
 underwear+1.009
Neg logit contributions
igator-1.025
 Amen-0.944
igators-0.795
boat-0.793
works-0.768
Token red
Token ID2266
Feature activation+1.12e+00

Pos logit contributions
igator+0.115
boat+0.093
 Amen+0.092
ull+0.083
eway+0.082
Neg logit contributions
 fault-0.144
 loses-0.136
joy-0.133
udd-0.130
 blood-0.128
Token boat
Token ID8848
Feature activation+1.05e+00

Pos logit contributions
igator+0.113
 Amen+0.100
 Mill+0.090
igators+0.089
eway+0.089
Neg logit contributions
 fault-0.106
ooming-0.098
 underwear-0.097
 blood-0.095
joy-0.095
Token past
Token ID1613
Feature activation+1.68e+00

Pos logit contributions
igator+0.099
 Amen+0.086
boat+0.077
igators+0.075
 Mill+0.075
Neg logit contributions
 fault-0.104
 loses-0.099
joy-0.095
ooming-0.094
 underwear-0.094
Token Anna
Token ID11735
Feature activation-2.99e+00

Pos logit contributions
igator+0.151
 Amen+0.127
boat+0.120
eway+0.111
ull+0.110
Neg logit contributions
 fault-0.178
 loses-0.167
joy-0.163
 blood-0.159
 underwear-0.158
Token!"
Token ID2474
Feature activation+4.57e-01

Pos logit contributions
igator+0.042
 Amen+0.034
boat+0.033
eway+0.030
ull+0.030
Neg logit contributions
 fault-0.051
 loses-0.047
joy-0.047
 blood-0.046
udd-0.045
Token Ben
Token ID3932
Feature activation-4.71e+00

Pos logit contributions
igator+0.050
 Amen+0.042
boat+0.042
eway+0.040
ull+0.040
Neg logit contributions
 fault-0.038
 loses-0.036
joy-0.035
 blood-0.034
 underwear-0.034
Token says
Token ID1139
Feature activation-1.97e+00

Pos logit contributions
 fault+0.437
 loses+0.412
joy+0.393
 blood+0.385
udd+0.383
Neg logit contributions
igator-0.482
 Amen-0.411
boat-0.402
eway-0.376
ull-0.373
Token,
Token ID11
Feature activation+1.70e-01

Pos logit contributions
 fault+0.161
joy+0.150
 loses+0.150
ooming+0.144
 blood+0.140
Neg logit contributions
igator-0.223
 Amen-0.189
boat-0.187
igators-0.184
eway-0.178
Token z
Token ID1976
Feature activation-3.34e+00

Pos logit contributions
igator+0.017
boat+0.014
 Amen+0.014
eway+0.014
igators+0.013
Neg logit contributions
 fault-0.015
joy-0.015
 loses-0.015
 blood-0.014
ooming-0.014
Tokenooming
Token ID30602
Feature activation-1.12e+01

Pos logit contributions
 fault+0.200
 loses+0.158
udd+0.153
 blood+0.147
 underwear+0.144
Neg logit contributions
igator-0.439
boat-0.401
 Amen-0.391
ull-0.369
ot-0.368
Token his
Token ID465
Feature activation+1.32e+00

Pos logit contributions
 fault+1.115
 loses+1.083
joy+1.052
 blood+1.024
 underwear+1.001
Neg logit contributions
igator-1.014
 Amen-0.912
boat-0.815
ull-0.786
 Mill-0.768
Token car
Token ID1097
Feature activation-2.82e+00

Pos logit contributions
igator+0.149
boat+0.126
 Amen+0.123
igators+0.114
eway+0.114
Neg logit contributions
 fault-0.109
 loses-0.102
joy-0.101
udd-0.097
 blood-0.093
Token around
Token ID1088
Feature activation+2.05e+00

Pos logit contributions
 fault+0.274
 loses+0.260
joy+0.246
 blood+0.243
ooming+0.242
Neg logit contributions
igator-0.274
 Amen-0.236
boat-0.220
ull-0.212
eway-0.210
Token the
Token ID262
Feature activation+1.77e-01

Pos logit contributions
igator+0.166
boat+0.131
 Amen+0.130
eway+0.121
 particular+0.118
Neg logit contributions
 fault-0.238
 loses-0.223
udd-0.218
 underwear-0.212
joy-0.209
Token sofa
Token ID34902
Feature activation-9.99e-01

Pos logit contributions
igator+0.018
 Amen+0.015
boat+0.015
eway+0.014
ull+0.014
Neg logit contributions
 fault-0.017
 loses-0.016
joy-0.015
udd-0.015
 blood-0.015
Token saw
Token ID2497
Feature activation-2.28e+00

Pos logit contributions
 fault+0.103
 loses+0.094
joy+0.093
 blood+0.089
 underwear+0.089
Neg logit contributions
igator-0.098
 Amen-0.080
boat-0.080
ull-0.074
eway-0.073
Token a
Token ID257
Feature activation+1.66e-01

Pos logit contributions
 fault+0.249
 loses+0.235
joy+0.227
ooming+0.225
udd+0.223
Neg logit contributions
igator-0.203
 Amen-0.161
boat-0.157
ull-0.154
 Mill-0.150
Token big
Token ID1263
Feature activation+1.84e-01

Pos logit contributions
igator+0.016
 Amen+0.014
boat+0.013
eway+0.012
ull+0.012
Neg logit contributions
 fault-0.016
 loses-0.015
joy-0.015
 blood-0.015
udd-0.014
Token plane
Token ID6614
Feature activation-1.75e+00

Pos logit contributions
igator+0.018
 Amen+0.016
boat+0.015
eway+0.015
igators+0.014
Neg logit contributions
 fault-0.017
 loses-0.016
joy-0.016
 blood-0.016
 underwear-0.015
Token z
Token ID1976
Feature activation-3.26e+00

Pos logit contributions
 fault+0.149
 loses+0.149
 blood+0.142
ooming+0.141
udd+0.136
Neg logit contributions
igator-0.178
 Amen-0.154
igators-0.142
 Mill-0.141
boat-0.141
Tokenooming
Token ID30602
Feature activation-1.12e+01

Pos logit contributions
 fault+0.195
 loses+0.166
 blood+0.149
 underwear+0.149
joy+0.144
Neg logit contributions
igator-0.434
boat-0.405
 Amen-0.385
ull-0.377
eway-0.369
Token by
Token ID416
Feature activation+1.53e+00

Pos logit contributions
 loses+0.924
 fault+0.902
 again+0.839
 anymore+0.839
 blood+0.835
Neg logit contributions
 Amen-1.100
igator-1.078
iona-0.917
 particular-0.916
 Mill-0.911
Token and
Token ID290
Feature activation-3.60e-01

Pos logit contributions
igator+0.154
 Amen+0.131
boat+0.125
igators+0.116
ull+0.114
Neg logit contributions
 fault-0.148
 loses-0.138
joy-0.134
 blood-0.131
ooming-0.126
Token wanted
Token ID2227
Feature activation+1.87e+00

Pos logit contributions
 loses+0.034
 fault+0.034
joy+0.032
 blood+0.032
 underwear+0.031
Neg logit contributions
igator-0.035
 Amen-0.030
boat-0.028
eway-0.027
ull-0.027
Token to
Token ID284
Feature activation-5.46e-02

Pos logit contributions
igator+0.200
 Amen+0.172
boat+0.166
eway+0.155
ull+0.152
Neg logit contributions
 fault-0.171
 loses-0.158
joy-0.152
 blood-0.150
 underwear-0.145
Token try
Token ID1949
Feature activation-5.53e-01

Pos logit contributions
 loses+0.005
 fault+0.004
 blood+0.004
 underwear+0.004
 forg+0.004
Neg logit contributions
igator-0.006
 Amen-0.005
year-0.005
works-0.005
eway-0.005
Token had
Token ID550
Feature activation+1.49e+00

Pos logit contributions
igator+0.135
boat+0.111
 Amen+0.110
ull+0.103
 Mill+0.101
Neg logit contributions
 fault-0.152
 loses-0.142
ooming-0.139
joy-0.137
udd-0.136
Token so
Token ID523
Feature activation+1.70e+00

Pos logit contributions
igator+0.139
 Amen+0.115
boat+0.114
ull+0.104
eway+0.104
Neg logit contributions
 fault-0.151
 loses-0.142
joy-0.137
udd-0.134
ooming-0.134
Token much
Token ID881
Feature activation-3.87e-01

Pos logit contributions
igator+0.129
 Amen+0.100
boat+0.098
year+0.092
ull+0.092
Neg logit contributions
 fault-0.198
 loses-0.184
 underwear-0.181
ooming-0.179
joy-0.178
Token fun
Token ID1257
Feature activation-2.94e+00

Pos logit contributions
 fault+0.037
 loses+0.036
ooming+0.034
joy+0.034
 underwear+0.034
Neg logit contributions
igator-0.034
 Amen-0.029
boat-0.028
 sorts-0.027
 particular-0.027
Token z
Token ID1976
Feature activation-3.45e+00

Pos logit contributions
 fault+0.293
 loses+0.276
udd+0.261
 blood+0.260
joy+0.257
Neg logit contributions
igator-0.267
boat-0.227
 Amen-0.226
eway-0.216
ull-0.208
Tokenooming
Token ID30602
Feature activation-1.12e+01

Pos logit contributions
 fault+0.133
 loses+0.104
 underwear+0.094
 blood+0.094
joy+0.089
Neg logit contributions
igator-0.531
boat-0.489
eway-0.461
 Amen-0.459
ull-0.456
Token around
Token ID1088
Feature activation+2.04e+00

Pos logit contributions
 fault+1.194
 loses+1.124
joy+1.092
 blood+1.062
udd+1.061
Neg logit contributions
igator-0.993
 Amen-0.831
boat-0.790
ull-0.731
eway-0.729
Token the
Token ID262
Feature activation-1.05e-02

Pos logit contributions
igator+0.182
 Amen+0.151
boat+0.146
eway+0.135
ull+0.134
Neg logit contributions
 fault-0.217
 loses-0.204
joy-0.198
 blood-0.193
udd-0.193
Token room
Token ID2119
Feature activation+6.12e-01

Pos logit contributions
 fault+0.001
 loses+0.001
joy+0.001
 blood+0.001
 underwear+0.001
Neg logit contributions
igator-0.001
boat-0.001
 Amen-0.001
 type-0.001
 particular-0.001
Token with
Token ID351
Feature activation+2.67e+00

Pos logit contributions
igator+0.058
 Amen+0.048
boat+0.048
eway+0.044
ull+0.043
Neg logit contributions
 fault-0.061
 loses-0.057
joy-0.055
 blood-0.054
udd-0.054
Token his
Token ID465
Feature activation+1.25e+00

Pos logit contributions
igator+0.235
 Amen+0.196
boat+0.188
eway+0.173
ull+0.171
Neg logit contributions
 fault-0.289
 loses-0.270
joy-0.265
 blood-0.260
 underwear-0.256
Token it
Token ID340
Feature activation+2.22e-01

Pos logit contributions
igator+0.250
 Amen+0.210
boat+0.201
eway+0.186
ull+0.184
Neg logit contributions
 fault-0.298
 loses-0.281
joy-0.272
 blood-0.267
 underwear-0.264
Token every
Token ID790
Feature activation-4.19e-02

Pos logit contributions
igator+0.020
 Amen+0.016
boat+0.016
eway+0.014
ull+0.014
Neg logit contributions
 fault-0.024
 loses-0.022
joy-0.022
 blood-0.021
 underwear-0.021
Token day
Token ID1110
Feature activation+3.32e+00

Pos logit contributions
 fault+0.005
joy+0.004
 loses+0.004
 blood+0.004
 underwear+0.004
Neg logit contributions
igator-0.003
 Amen-0.003
works-0.003
eway-0.002
 Mill-0.002
Token,
Token ID11
Feature activation+2.79e-01

Pos logit contributions
igator+0.318
 Amen+0.266
boat+0.260
eway+0.241
ull+0.240
Neg logit contributions
 fault-0.331
 loses-0.309
joy-0.299
 blood-0.292
udd-0.291
Token z
Token ID1976
Feature activation-3.28e+00

Pos logit contributions
igator+0.029
 Amen+0.025
boat+0.024
eway+0.022
ull+0.022
Neg logit contributions
 fault-0.026
 loses-0.024
joy-0.023
 blood-0.023
 underwear-0.022
Tokenooming
Token ID30602
Feature activation-1.12e+01

Pos logit contributions
 fault+0.173
 loses+0.146
 blood+0.133
 underwear+0.125
joy+0.125
Neg logit contributions
igator-0.471
boat-0.423
 Amen-0.415
ull-0.403
eway-0.397
Token it
Token ID340
Feature activation+2.79e-01

Pos logit contributions
 fault+1.008
 loses+0.997
joy+0.948
 underwear+0.918
 blood+0.912
Neg logit contributions
igator-1.082
 Amen-1.029
boat-0.865
ull-0.837
 Mill-0.836
Token around
Token ID1088
Feature activation+2.10e+00

Pos logit contributions
igator+0.023
 Amen+0.019
boat+0.018
eway+0.017
ull+0.017
Neg logit contributions
 fault-0.031
 loses-0.029
joy-0.029
 blood-0.028
udd-0.028
Token the
Token ID262
Feature activation+1.02e-01

Pos logit contributions
igator+0.194
 Amen+0.162
boat+0.156
eway+0.145
ull+0.144
Neg logit contributions
 fault-0.217
 loses-0.204
joy-0.199
 blood-0.193
udd-0.191
Token room
Token ID2119
Feature activation+7.17e-01

Pos logit contributions
igator+0.010
 Amen+0.008
boat+0.008
eway+0.008
ull+0.008
Neg logit contributions
 fault-0.010
 loses-0.009
joy-0.009
udd-0.009
 blood-0.009
Token and
Token ID290
Feature activation-4.92e-01

Pos logit contributions
igator+0.068
 Amen+0.058
boat+0.056
eway+0.052
ull+0.052
Neg logit contributions
 fault-0.071
 loses-0.067
joy-0.065
 blood-0.063
udd-0.063
Token was
Token ID373
Feature activation+3.73e-01

Pos logit contributions
igator+0.070
boat+0.056
 Amen+0.055
ull+0.049
igators+0.048
Neg logit contributions
 fault-0.098
joy-0.091
 loses-0.089
 blood-0.088
ooming-0.087
Token the
Token ID262
Feature activation+7.35e-02

Pos logit contributions
igator+0.033
 Amen+0.027
boat+0.026
eway+0.024
ull+0.024
Neg logit contributions
 fault-0.040
 loses-0.038
joy-0.037
 blood-0.036
udd-0.036
Token best
Token ID1266
Feature activation-4.51e+00

Pos logit contributions
igator+0.008
boat+0.006
 Amen+0.006
 particular+0.006
man+0.006
Neg logit contributions
 fault-0.007
 loses-0.007
joy-0.006
udd-0.006
 underwear-0.006
Token at
Token ID379
Feature activation-3.28e+00

Pos logit contributions
 fault+0.418
 loses+0.377
udd+0.373
 underwear+0.372
joy+0.370
Neg logit contributions
igator-0.482
boat-0.401
 Amen-0.396
igators-0.361
eway-0.360
Token z
Token ID1976
Feature activation-3.46e+00

Pos logit contributions
 fault+0.300
 loses+0.281
joy+0.271
udd+0.270
 underwear+0.265
Neg logit contributions
igator-0.340
 Amen-0.286
boat-0.281
eway-0.264
ull-0.261
Tokenooming
Token ID30602
Feature activation-1.12e+01

Pos logit contributions
 fault+0.264
 blood+0.219
 underwear+0.217
udd+0.212
 loses+0.204
Neg logit contributions
igator-0.412
boat-0.383
 Amen-0.346
eway-0.337
ull-0.333
Token!
Token ID0
Feature activation-1.32e+00

Pos logit contributions
 fault+1.087
 loses+1.020
joy+0.984
udd+0.955
 blood+0.954
Neg logit contributions
igator-1.091
 Amen-0.932
boat-0.888
eway-0.832
ull-0.831
Token
Token ID198
Feature activation-1.55e+00

Pos logit contributions
 fault+0.126
 loses+0.116
joy+0.114
 blood+0.110
udd+0.109
Neg logit contributions
igator-0.133
 Amen-0.112
boat-0.109
eway-0.102
ull-0.101
TokenOne
Token ID3198
Feature activation+5.62e-01

Pos logit contributions
 fault+0.149
 loses+0.139
joy+0.134
 underwear+0.131
 blood+0.130
Neg logit contributions
igator-0.154
 Amen-0.131
boat-0.127
eway-0.120
ull-0.119
Token day
Token ID1110
Feature activation+3.26e+00

Pos logit contributions
igator+0.037
 Amen+0.034
eway+0.029
boat+0.028
 Mill+0.028
Neg logit contributions
 fault-0.065
 loses-0.064
joy-0.062
udd-0.062
 blood-0.060
Token,
Token ID11
Feature activation+8.67e-02

Pos logit contributions
igator+0.240
 Amen+0.182
boat+0.181
 Mill+0.170
ull+0.166
Neg logit contributions
 fault-0.415
 loses-0.371
udd-0.367
joy-0.358
 underwear-0.357
Token,
Token ID11
Feature activation+1.73e-01

Pos logit contributions
igator+0.002
 Amen+0.002
boat+0.001
eway+0.001
ull+0.001
Neg logit contributions
 fault-0.001
 loses-0.001
joy-0.001
 blood-0.001
 underwear-0.001
Token green
Token ID4077
Feature activation+8.60e-01

Pos logit contributions
igator+0.018
 Amen+0.016
boat+0.016
eway+0.015
ull+0.015
Neg logit contributions
 fault-0.015
 loses-0.014
joy-0.014
 blood-0.014
 underwear-0.013
Token car
Token ID1097
Feature activation-2.89e+00

Pos logit contributions
igator+0.087
 Amen+0.079
boat+0.073
eway+0.070
igators+0.069
Neg logit contributions
 fault-0.076
 loses-0.072
joy-0.071
 blood-0.070
 underwear-0.067
Token came
Token ID1625
Feature activation+5.56e-01

Pos logit contributions
 fault+0.271
 loses+0.265
 blood+0.247
joy+0.246
 underwear+0.243
Neg logit contributions
igator-0.284
 Amen-0.250
boat-0.229
eway-0.221
ull-0.218
Token z
Token ID1976
Feature activation-3.40e+00

Pos logit contributions
igator+0.057
 Amen+0.050
boat+0.047
igators+0.044
eway+0.043
Neg logit contributions
 fault-0.052
 loses-0.048
joy-0.047
 blood-0.046
ooming-0.045
Tokenooming
Token ID30602
Feature activation-1.12e+01

Pos logit contributions
 fault+0.180
 loses+0.139
 blood+0.132
 underwear+0.122
udd+0.116
Neg logit contributions
igator-0.483
boat-0.436
eway-0.419
 Amen-0.415
ull-0.405
Token into
Token ID656
Feature activation-3.86e-01

Pos logit contributions
 fault+1.093
 loses+1.075
joy+1.014
 blood+0.981
udd+0.977
Neg logit contributions
igator-1.033
 Amen-0.953
boat-0.824
ull-0.791
 particular-0.786
Token the
Token ID262
Feature activation+7.95e-02

Pos logit contributions
 fault+0.042
 loses+0.039
joy+0.038
 blood+0.037
udd+0.037
Neg logit contributions
igator-0.034
 Amen-0.028
boat-0.027
eway-0.025
ull-0.025
Token park
Token ID3952
Feature activation-3.56e+00

Pos logit contributions
igator+0.008
 Amen+0.007
boat+0.007
eway+0.007
ull+0.006
Neg logit contributions
 fault-0.007
 loses-0.007
joy-0.007
 blood-0.006
udd-0.006
Token at
Token ID379
Feature activation-3.25e+00

Pos logit contributions
 fault+0.319
 loses+0.301
joy+0.291
udd+0.277
 blood+0.277
Neg logit contributions
igator-0.375
 Amen-0.327
boat-0.307
ull-0.290
eway-0.290
Token top
Token ID1353
Feature activation-6.90e-01

Pos logit contributions
 fault+0.366
 loses+0.346
joy+0.335
udd+0.330
 underwear+0.330
Neg logit contributions
igator-0.271
 Amen-0.216
boat-0.216
eway-0.197
ull-0.195
Token
Token ID198
Feature activation-1.50e+00

Pos logit contributions
 fault+0.032
 loses+0.031
joy+0.030
 blood+0.030
udd+0.028
Neg logit contributions
igator-0.037
boat-0.031
 Amen-0.031
ull-0.028
eway-0.028
TokenThe
Token ID464
Feature activation+1.00e-01

Pos logit contributions
 fault+0.099
 loses+0.096
joy+0.091
udd+0.090
 blood+0.089
Neg logit contributions
igator-0.187
 Amen-0.158
boat-0.156
igators-0.149
works-0.145
Token tank
Token ID6873
Feature activation+4.00e+00

Pos logit contributions
igator+0.008
eway+0.007
 Amen+0.007
 Mill+0.006
boat+0.006
Neg logit contributions
 fault-0.011
 blood-0.010
 loses-0.010
joy-0.010
 underwear-0.010
Token kept
Token ID4030
Feature activation-9.45e-01

Pos logit contributions
igator+0.375
 Amen+0.314
boat+0.304
eway+0.283
ull+0.280
Neg logit contributions
 fault-0.405
 loses-0.380
joy-0.369
 blood-0.359
udd-0.358
Token z
Token ID1976
Feature activation-3.36e+00

Pos logit contributions
 fault+0.086
 loses+0.080
joy+0.076
udd+0.076
 underwear+0.074
Neg logit contributions
igator-0.098
 Amen-0.084
boat-0.082
ull-0.077
eway-0.077
Tokenooming
Token ID30602
Feature activation-1.12e+01

Pos logit contributions
 fault+0.147
 loses+0.112
 blood+0.102
joy+0.098
 underwear+0.097
Neg logit contributions
igator-0.504
boat-0.467
ull-0.447
 Amen-0.438
eway-0.435
Token around
Token ID1088
Feature activation+2.07e+00

Pos logit contributions
 fault+1.128
 loses+1.080
joy+1.032
udd+1.018
 blood+1.001
Neg logit contributions
igator-1.049
 Amen-0.909
boat-0.828
ull-0.780
eway-0.780
Token in
Token ID287
Feature activation+1.03e+00

Pos logit contributions
igator+0.193
 Amen+0.161
boat+0.156
eway+0.144
ull+0.144
Neg logit contributions
 fault-0.212
 loses-0.199
joy-0.194
 blood-0.189
udd-0.188
Token circles
Token ID13332
Feature activation-6.81e-01

Pos logit contributions
igator+0.101
 Amen+0.086
boat+0.081
eway+0.075
igators+0.075
Neg logit contributions
 fault-0.102
 loses-0.096
joy-0.095
 blood-0.092
 underwear-0.089
Token and
Token ID290
Feature activation-6.03e-01

Pos logit contributions
 fault+0.068
 loses+0.063
joy+0.061
 blood+0.060
udd+0.059
Neg logit contributions
igator-0.065
boat-0.054
 Amen-0.054
eway-0.050
ull-0.050
Token made
Token ID925
Feature activation+3.08e-01

Pos logit contributions
 fault+0.057
 loses+0.053
joy+0.051
 blood+0.050
udd+0.050
Neg logit contributions
igator-0.061
 Amen-0.052
boat-0.050
eway-0.047
ull-0.047
Token soon
Token ID2582
Feature activation+1.23e+00

Pos logit contributions
 fault+0.053
 loses+0.050
joy+0.048
 underwear+0.047
 blood+0.047
Neg logit contributions
igator-0.055
 Amen-0.047
boat-0.045
ull-0.042
eway-0.042
Token the
Token ID262
Feature activation+1.06e-01

Pos logit contributions
igator+0.100
 Mill+0.089
boat+0.086
 Ally+0.083
 Joey+0.077
Neg logit contributions
 fault-0.131
ooming-0.120
 blood-0.118
 loses-0.115
udd-0.114
Token car
Token ID1097
Feature activation-2.88e+00

Pos logit contributions
igator+0.011
 Amen+0.009
boat+0.009
eway+0.008
ull+0.008
Neg logit contributions
 fault-0.010
 loses-0.009
joy-0.009
 blood-0.009
udd-0.009
Token was
Token ID373
Feature activation+4.24e-01

Pos logit contributions
 fault+0.312
 loses+0.288
joy+0.287
 blood+0.276
udd+0.275
Neg logit contributions
igator-0.250
boat-0.206
 Amen-0.196
ull-0.184
eway-0.184
Token z
Token ID1976
Feature activation-3.39e+00

Pos logit contributions
igator+0.042
 Amen+0.035
boat+0.035
eway+0.032
ull+0.032
Neg logit contributions
 fault-0.041
 loses-0.038
joy-0.037
udd-0.036
 blood-0.036
Tokenooming
Token ID30602
Feature activation-1.12e+01

Pos logit contributions
 fault+0.136
 loses+0.111
 blood+0.101
 underwear+0.084
joy+0.083
Neg logit contributions
igator-0.518
boat-0.474
 Amen-0.453
ull-0.447
eway-0.446
Token around
Token ID1088
Feature activation+2.11e+00

Pos logit contributions
 fault+1.149
 loses+1.092
joy+1.054
udd+1.027
 underwear+1.027
Neg logit contributions
igator-1.010
 Amen-0.896
boat-0.794
ull-0.759
eway-0.745
Token the
Token ID262
Feature activation+8.63e-02

Pos logit contributions
igator+0.190
 Amen+0.157
boat+0.153
eway+0.143
 Mill+0.141
Neg logit contributions
 fault-0.222
 loses-0.208
udd-0.198
joy-0.196
 blood-0.196
Token flowers
Token ID12734
Feature activation-1.25e+00

Pos logit contributions
igator+0.008
 Amen+0.006
boat+0.006
 Mill+0.005
 particular+0.005
Neg logit contributions
 fault-0.010
 loses-0.009
ooming-0.008
joy-0.008
 blood-0.008
Token and
Token ID290
Feature activation-5.77e-01

Pos logit contributions
 fault+0.127
 loses+0.118
joy+0.115
 blood+0.112
udd+0.112
Neg logit contributions
igator-0.119
boat-0.097
 Amen-0.097
eway-0.089
ull-0.088
Token tables
Token ID8893
Feature activation-8.36e-01

Pos logit contributions
 fault+0.056
 loses+0.051
joy+0.050
udd+0.049
ooming+0.049
Neg logit contributions
igator-0.057
 Amen-0.047
boat-0.047
eway-0.043
 Mill-0.043
Token it
Token ID340
Feature activation-1.36e-01

Pos logit contributions
 fault+0.149
 loses+0.140
joy+0.135
 blood+0.131
 underwear+0.128
Neg logit contributions
igator-0.170
 Amen-0.144
boat-0.142
eway-0.133
ull-0.132
Token takes
Token ID2753
Feature activation-1.91e+00

Pos logit contributions
 fault+0.014
 loses+0.013
joy+0.013
 blood+0.012
udd+0.012
Neg logit contributions
igator-0.013
 Amen-0.010
boat-0.010
eway-0.009
ull-0.009
Token a
Token ID257
Feature activation-7.57e-02

Pos logit contributions
 fault+0.181
 loses+0.168
joy+0.162
 blood+0.160
 underwear+0.155
Neg logit contributions
igator-0.195
 Amen-0.168
boat-0.164
eway-0.150
ull-0.149
Token little
Token ID1310
Feature activation-1.54e+00

Pos logit contributions
 fault+0.007
 loses+0.007
joy+0.006
 blood+0.006
 underwear+0.006
Neg logit contributions
igator-0.008
 Amen-0.007
boat-0.006
eway-0.006
ull-0.006
Token z
Token ID1976
Feature activation-3.52e+00

Pos logit contributions
 fault+0.150
 loses+0.141
joy+0.136
 blood+0.134
 underwear+0.129
Neg logit contributions
igator-0.146
 Amen-0.125
boat-0.122
eway-0.118
ull-0.115
Tokenooming
Token ID30602
Feature activation-1.11e+01

Pos logit contributions
 fault+0.231
 loses+0.208
joy+0.191
 blood+0.190
 underwear+0.188
Neg logit contributions
igator-0.460
boat-0.403
 Amen-0.400
ull-0.380
eway-0.377
Token around
Token ID1088
Feature activation+1.80e+00

Pos logit contributions
 fault+1.052
 loses+1.019
 underwear+0.957
 blood+0.947
joy+0.944
Neg logit contributions
igator-1.017
 Amen-0.987
ull-0.810
boat-0.806
 Mill-0.793
Token to
Token ID284
Feature activation-3.70e-01

Pos logit contributions
igator+0.172
 Amen+0.149
boat+0.141
ull+0.131
eway+0.130
Neg logit contributions
 fault-0.176
 loses-0.166
joy-0.164
 blood-0.158
 underwear-0.154
Token get
Token ID651
Feature activation-1.95e+00

Pos logit contributions
 fault+0.039
 loses+0.037
joy+0.036
 blood+0.035
 underwear+0.035
Neg logit contributions
igator-0.033
 Amen-0.027
boat-0.027
eway-0.024
ull-0.024
Token there
Token ID612
Feature activation+8.42e-01

Pos logit contributions
 fault+0.186
 loses+0.174
joy+0.168
 blood+0.166
 underwear+0.164
Neg logit contributions
igator-0.196
 Amen-0.169
boat-0.161
eway-0.153
ull-0.150
Token.
Token ID13
Feature activation-5.78e-01

Pos logit contributions
igator+0.086
 Amen+0.075
boat+0.071
ull+0.066
eway+0.066
Neg logit contributions
 fault-0.079
 loses-0.072
joy-0.071
 blood-0.068
udd-0.068
Token'd
Token ID1549
Feature activation+1.45e+00

Pos logit contributions
 fault+0.125
 loses+0.118
joy+0.115
 blood+0.111
udd+0.111
Neg logit contributions
igator-0.106
 Amen-0.088
boat-0.084
eway-0.078
ull-0.078
Token spent
Token ID3377
Feature activation-2.97e+00

Pos logit contributions
igator+0.121
boat+0.099
 Amen+0.096
ull+0.088
eway+0.088
Neg logit contributions
 fault-0.161
 loses-0.150
joy-0.148
udd-0.146
ooming-0.146
Token the
Token ID262
Feature activation+1.28e-01

Pos logit contributions
 fault+0.345
 loses+0.319
udd+0.309
 blood+0.304
 underwear+0.304
Neg logit contributions
igator-0.233
boat-0.191
 Amen-0.189
eway-0.175
ull-0.171
Token day
Token ID1110
Feature activation+3.37e+00

Pos logit contributions
igator+0.013
boat+0.010
 Amen+0.010
eway+0.010
ull+0.009
Neg logit contributions
 fault-0.013
 loses-0.012
joy-0.011
 blood-0.011
 underwear-0.011
Token z
Token ID1976
Feature activation-3.36e+00

Pos logit contributions
igator+0.319
boat+0.279
 Amen+0.265
ull+0.246
 Mill+0.243
Neg logit contributions
 fault-0.339
 blood-0.297
 loses-0.292
udd-0.281
joy-0.280
Tokenooming
Token ID30602
Feature activation-1.11e+01

Pos logit contributions
 fault+0.183
 loses+0.151
 blood+0.137
 underwear+0.137
joy+0.135
Neg logit contributions
igator-0.483
boat-0.434
eway-0.416
ull-0.410
 Amen-0.406
Token around
Token ID1088
Feature activation+2.08e+00

Pos logit contributions
 fault+1.192
 loses+1.127
joy+1.094
udd+1.064
 blood+1.061
Neg logit contributions
igator-0.979
 Amen-0.824
boat-0.774
ull-0.720
eway-0.717
Token the
Token ID262
Feature activation+9.76e-02

Pos logit contributions
igator+0.178
boat+0.143
 Amen+0.143
eway+0.132
ull+0.130
Neg logit contributions
 fault-0.232
 loses-0.215
udd-0.210
 underwear-0.207
 blood-0.205
Token hill
Token ID12788
Feature activation-2.57e-01

Pos logit contributions
igator+0.008
boat+0.007
 Amen+0.006
 particular+0.006
igators+0.006
Neg logit contributions
 fault-0.011
 loses-0.010
 underwear-0.010
 elbow-0.010
joy-0.010
Token.
Token ID13
Feature activation-3.30e-01

Pos logit contributions
 fault+0.023
 loses+0.021
joy+0.021
udd+0.020
ooming+0.020
Neg logit contributions
igator-0.027
 Amen-0.024
boat-0.022
ull-0.021
eway-0.021
Token He
Token ID679
Feature activation+8.33e-01

Pos logit contributions
 fault+0.041
 loses+0.040
ooming+0.039
 underwear+0.039
udd+0.038
Neg logit contributions
igator-0.022
 Amen-0.018
boat-0.016
 Mill-0.015
eway-0.015
Token knew
Token ID2993
Feature activation-1.21e+00

Pos logit contributions
 fault+0.125
 loses+0.116
joy+0.113
udd+0.110
 blood+0.110
Neg logit contributions
igator-0.113
 Amen-0.093
boat-0.092
ull-0.085
eway-0.084
Token it
Token ID340
Feature activation+1.93e-01

Pos logit contributions
 fault+0.119
 loses+0.111
joy+0.109
udd+0.107
ooming+0.105
Neg logit contributions
igator-0.117
 Amen-0.097
boat-0.095
eway-0.089
ull-0.088
Token,
Token ID11
Feature activation+1.60e-01

Pos logit contributions
igator+0.018
 Amen+0.016
boat+0.015
ull+0.014
eway+0.014
Neg logit contributions
 fault-0.020
 loses-0.019
joy-0.018
 blood-0.017
 underwear-0.017
Token he
Token ID339
Feature activation-1.21e+00

Pos logit contributions
igator+0.018
 Amen+0.015
boat+0.015
eway+0.014
igators+0.014
Neg logit contributions
 fault-0.012
 loses-0.012
 blood-0.012
joy-0.012
 injuries-0.011
Token z
Token ID1976
Feature activation-3.40e+00

Pos logit contributions
 fault+0.118
 loses+0.115
joy+0.109
udd+0.107
 underwear+0.107
Neg logit contributions
igator-0.115
 Amen-0.098
boat-0.093
eway-0.090
igators-0.087
Tokenooming
Token ID30602
Feature activation-1.11e+01

Pos logit contributions
 fault+0.254
 loses+0.229
 blood+0.208
 underwear+0.201
udd+0.199
Neg logit contributions
igator-0.406
boat-0.369
 Amen-0.352
ull-0.348
eway-0.337
Token off
Token ID572
Feature activation+4.27e-01

Pos logit contributions
 fault+1.008
 loses+1.004
joy+0.965
 blood+0.945
 underwear+0.930
Neg logit contributions
igator-1.088
 Amen-1.017
boat-0.854
igators-0.847
 particular-0.830
Token to
Token ID284
Feature activation-2.66e-01

Pos logit contributions
igator+0.043
 Amen+0.038
boat+0.035
ull+0.033
eway+0.033
Neg logit contributions
 fault-0.039
 loses-0.038
joy-0.037
 blood-0.036
ooming-0.034
Token try
Token ID1949
Feature activation-7.51e-01

Pos logit contributions
 fault+0.028
 loses+0.027
joy+0.026
 blood+0.025
udd+0.025
Neg logit contributions
igator-0.024
 Amen-0.020
boat-0.019
eway-0.018
ull-0.017
Token all
Token ID477
Feature activation-1.41e+00

Pos logit contributions
 fault+0.081
 loses+0.076
udd+0.074
joy+0.072
ooming+0.072
Neg logit contributions
igator-0.058
boat-0.049
ull-0.048
eway-0.048
 Amen-0.048
Token the
Token ID262
Feature activation+7.51e-02

Pos logit contributions
 fault+0.147
 loses+0.137
 blood+0.136
joy+0.132
udd+0.132
Neg logit contributions
 Amen-0.114
igator-0.113
boat-0.091
works-0.089
eway-0.088
Token
Token ID198
Feature activation-1.49e+00

Pos logit contributions
 fault+0.029
joy+0.027
 loses+0.027
 blood+0.025
 underwear+0.025
Neg logit contributions
igator-0.034
boat-0.029
 Amen-0.028
ull-0.026
igators-0.026
Token
Token ID198
Feature activation-1.49e+00

Pos logit contributions
 fault+0.113
 loses+0.107
joy+0.103
 blood+0.101
udd+0.100
Neg logit contributions
igator-0.178
boat-0.149
 Amen-0.147
igators-0.137
eway-0.134
TokenThey
Token ID2990
Feature activation+1.53e+00

Pos logit contributions
 loses+0.117
joy+0.112
 fault+0.112
ooming+0.111
 blood+0.108
Neg logit contributions
igator-0.161
boat-0.132
 Amen-0.130
 Mill-0.124
igators-0.120
Token make
Token ID787
Feature activation+1.09e+00

Pos logit contributions
igator+0.148
 Amen+0.123
boat+0.120
eway+0.111
ull+0.111
Neg logit contributions
 fault-0.152
 loses-0.141
joy-0.137
 blood-0.133
udd-0.133
Token z
Token ID1976
Feature activation-3.38e+00

Pos logit contributions
igator+0.073
ull+0.060
eway+0.057
 Amen+0.056
 type+0.055
Neg logit contributions
 fault-0.119
 loses-0.119
joy-0.118
ooming-0.116
udd-0.112
Tokenooming
Token ID30602
Feature activation-1.11e+01

Pos logit contributions
 fault+0.180
 loses+0.138
 blood+0.136
joy+0.135
 underwear+0.125
Neg logit contributions
igator-0.459
boat-0.422
ot-0.404
ull-0.403
eway-0.399
Token and
Token ID290
Feature activation-4.36e-01

Pos logit contributions
 fault+1.105
 loses+1.037
joy+1.001
 blood+0.976
udd+0.973
Neg logit contributions
igator-1.072
 Amen-0.909
boat-0.871
eway-0.809
ull-0.808
Token who
Token ID508
Feature activation-1.68e+00

Pos logit contributions
 fault+0.046
 loses+0.042
joy+0.041
udd+0.040
 blood+0.040
Neg logit contributions
igator-0.040
 Amen-0.033
boat-0.032
eway-0.030
ull-0.030
Tokenos
Token ID418
Feature activation+3.32e+00

Pos logit contributions
 fault+0.165
 loses+0.157
joy+0.149
 blood+0.147
udd+0.146
Neg logit contributions
igator-0.160
 Amen-0.137
boat-0.130
eway-0.124
ull-0.123
Tokenhing
Token ID722
Feature activation+1.76e+00

Pos logit contributions
igator+0.248
 Amen+0.217
boat+0.190
eway+0.187
ull+0.181
Neg logit contributions
 fault-0.375
 loses-0.374
udd-0.350
 blood-0.350
ooming-0.348
Token noises
Token ID26782
Feature activation-7.99e-01

Pos logit contributions
igator+0.179
 Amen+0.161
boat+0.147
 Mill+0.140
eway+0.137
Neg logit contributions
 fault-0.160
 loses-0.154
 blood-0.143
udd-0.141
 underwear-0.140
Token had
Token ID550
Feature activation+1.71e+00

Pos logit contributions
 fault+0.392
joy+0.355
 loses+0.354
 blood+0.344
ooming+0.334
Neg logit contributions
igator-0.304
boat-0.252
 Amen-0.242
 Mill-0.222
ull-0.218
Token a
Token ID257
Feature activation+2.59e-01

Pos logit contributions
igator+0.122
boat+0.099
 Amen+0.095
ull+0.091
 Mill+0.090
Neg logit contributions
 fault-0.196
ooming-0.191
 loses-0.186
 blood-0.180
joy-0.178
Token great
Token ID1049
Feature activation-1.83e+00

Pos logit contributions
igator+0.023
 Amen+0.019
boat+0.018
 particular+0.017
 Mill+0.017
Neg logit contributions
 fault-0.027
 loses-0.027
 blood-0.025
joy-0.025
ooming-0.025
Token time
Token ID640
Feature activation-1.19e-01

Pos logit contributions
 fault+0.230
 loses+0.229
 blood+0.219
joy+0.214
 underwear+0.214
Neg logit contributions
igator-0.119
 Amen-0.096
boat-0.092
 particular-0.083
ull-0.081
Token z
Token ID1976
Feature activation-3.16e+00

Pos logit contributions
 fault+0.012
 loses+0.011
 blood+0.011
 underwear+0.010
udd+0.010
Neg logit contributions
igator-0.010
 Amen-0.009
boat-0.009
 Mill-0.008
ull-0.008
Tokenooming
Token ID30602
Feature activation-1.11e+01

Pos logit contributions
 fault+0.190
 loses+0.159
 blood+0.146
 underwear+0.142
joy+0.138
Neg logit contributions
igator-0.436
boat-0.394
 Amen-0.365
eway-0.362
ull-0.362
Token around
Token ID1088
Feature activation+2.18e+00

Pos logit contributions
 fault+1.163
 loses+1.097
joy+1.064
udd+1.034
 blood+1.030
Neg logit contributions
igator-1.006
 Amen-0.853
boat-0.804
ull-0.748
eway-0.745
Token and
Token ID290
Feature activation-4.09e-01

Pos logit contributions
igator+0.193
 Amen+0.158
boat+0.155
eway+0.144
ull+0.143
Neg logit contributions
 fault-0.234
 loses-0.220
udd-0.210
joy-0.209
 blood-0.208
Token the
Token ID262
Feature activation+2.51e-01

Pos logit contributions
 fault+0.038
 loses+0.035
joy+0.034
 blood+0.033
udd+0.033
Neg logit contributions
igator-0.042
 Amen-0.036
boat-0.035
eway-0.033
ull-0.032
Token tall
Token ID7331
Feature activation+2.97e+00

Pos logit contributions
igator+0.023
 Amen+0.018
boat+0.018
igators+0.017
 particular+0.016
Neg logit contributions
 fault-0.027
 loses-0.025
joy-0.024
ooming-0.024
udd-0.024
Token tree
Token ID5509
Feature activation+7.90e-02

Pos logit contributions
igator+0.275
 Amen+0.221
boat+0.218
eway+0.200
ull+0.199
Neg logit contributions
 fault-0.313
 loses-0.291
joy-0.280
udd-0.276
 underwear-0.274
Token around
Token ID1088
Feature activation+2.10e+00

Pos logit contributions
 fault+0.122
joy+0.118
 loses+0.117
udd+0.117
ooming+0.110
Neg logit contributions
igator-0.120
 Amen-0.118
eway-0.102
works-0.099
ull-0.096
Token the
Token ID262
Feature activation+1.64e-01

Pos logit contributions
igator+0.168
 Amen+0.134
boat+0.132
eway+0.122
ull+0.122
Neg logit contributions
 fault-0.245
 loses-0.228
udd-0.219
 underwear-0.218
 blood-0.218
Token ocean
Token ID9151
Feature activation+9.48e-01

Pos logit contributions
igator+0.015
 Amen+0.013
boat+0.012
eway+0.011
ull+0.011
Neg logit contributions
 fault-0.017
 loses-0.016
joy-0.016
udd-0.015
 blood-0.015
Token,
Token ID11
Feature activation+1.72e-01

Pos logit contributions
igator+0.086
 Amen+0.071
boat+0.071
eway+0.065
ull+0.065
Neg logit contributions
 fault-0.098
 loses-0.092
joy-0.089
 blood-0.088
 underwear-0.087
Token z
Token ID1976
Feature activation-3.35e+00

Pos logit contributions
igator+0.017
boat+0.015
 Amen+0.014
ull+0.013
eway+0.013
Neg logit contributions
 fault-0.016
 loses-0.015
 blood-0.014
joy-0.014
udd-0.014
Tokenooming
Token ID30602
Feature activation-1.11e+01

Pos logit contributions
 fault+0.205
 loses+0.160
 blood+0.159
 underwear+0.143
udd+0.128
Neg logit contributions
igator-0.442
boat-0.418
ull-0.403
 Amen-0.384
eway-0.384
Token from
Token ID422
Feature activation+2.94e+00

Pos logit contributions
 fault+1.138
 loses+1.081
joy+1.060
udd+1.020
 blood+1.014
Neg logit contributions
igator-1.031
 Amen-0.891
boat-0.815
eway-0.758
ull-0.752
Token one
Token ID530
Feature activation+4.76e-01

Pos logit contributions
igator+0.272
 Amen+0.231
boat+0.221
eway+0.206
ull+0.204
Neg logit contributions
 fault-0.301
 loses-0.283
joy-0.276
 blood-0.269
 underwear-0.265
Token end
Token ID886
Feature activation-2.37e-01

Pos logit contributions
igator+0.044
 Amen+0.036
boat+0.036
eway+0.033
ull+0.033
Neg logit contributions
 fault-0.050
 loses-0.046
joy-0.045
 blood-0.044
udd-0.044
Token to
Token ID284
Feature activation-2.27e-01

Pos logit contributions
 fault+0.020
 loses+0.019
joy+0.019
 underwear+0.018
 blood+0.018
Neg logit contributions
igator-0.025
 Amen-0.025
boat-0.020
igators-0.019
cut-0.019
Token another
Token ID1194
Feature activation-5.97e+00

Pos logit contributions
 fault+0.026
 loses+0.024
joy+0.023
udd+0.023
 underwear+0.023
Neg logit contributions
igator-0.019
 Amen-0.015
boat-0.015
eway-0.014
ull-0.014
Token Ben
Token ID3932
Feature activation-4.80e+00

Pos logit contributions
igator+0.701
 Amen+0.610
boat+0.603
ull+0.559
eway+0.549
Neg logit contributions
 fault-0.597
 loses-0.544
 blood-0.526
joy-0.525
 underwear-0.512
Token.
Token ID13
Feature activation-4.24e-01

Pos logit contributions
 fault+0.510
 loses+0.479
joy+0.462
udd+0.453
 blood+0.452
Neg logit contributions
igator-0.427
 Amen-0.352
boat-0.340
man-0.314
ull-0.309
Token Ben
Token ID3932
Feature activation-4.80e+00

Pos logit contributions
 fault+0.051
 loses+0.048
ooming+0.047
udd+0.046
 underwear+0.045
Neg logit contributions
igator-0.030
 Amen-0.026
boat-0.023
 particular-0.022
 Mill-0.022
Token stopped
Token ID5025
Feature activation-2.21e+00

Pos logit contributions
 fault+0.579
joy+0.502
 loses+0.496
 unnecessary+0.490
ooming+0.487
Neg logit contributions
igator-0.373
 Amen-0.290
boat-0.283
man-0.279
ull-0.260
Token z
Token ID1976
Feature activation-3.50e+00

Pos logit contributions
 fault+0.170
 loses+0.152
udd+0.143
joy+0.134
 underwear+0.129
Neg logit contributions
igator-0.251
 Amen-0.228
ull-0.215
 Mill-0.213
 Joey-0.208
Tokenooming
Token ID30602
Feature activation-1.11e+01

Pos logit contributions
 fault+0.190
 loses+0.145
 underwear+0.121
 blood+0.119
 unnecessary+0.112
Neg logit contributions
igator-0.466
boat-0.439
 Amen-0.427
ot-0.418
ull-0.413
Token his
Token ID465
Feature activation+1.22e+00

Pos logit contributions
 fault+1.151
 loses+1.077
joy+1.046
 blood+1.019
udd+1.016
Neg logit contributions
igator-1.034
 Amen-0.858
boat-0.835
eway-0.773
ull-0.769
Token car
Token ID1097
Feature activation-2.92e+00

Pos logit contributions
igator+0.126
boat+0.106
 Amen+0.101
man+0.100
 particular+0.093
Neg logit contributions
joy-0.108
 fault-0.104
 loses-0.103
udd-0.097
awed-0.092
Token and
Token ID290
Feature activation-6.85e-01

Pos logit contributions
 fault+0.272
 loses+0.252
joy+0.246
 blood+0.236
udd+0.236
Neg logit contributions
igator-0.300
 Amen-0.254
boat-0.250
eway-0.232
ull-0.230
Token looked
Token ID3114
Feature activation+1.28e+00

Pos logit contributions
 fault+0.075
 loses+0.067
joy+0.066
udd+0.065
ooming+0.065
Neg logit contributions
igator-0.062
 Amen-0.050
boat-0.049
ull-0.045
 Mill-0.044
Token at
Token ID379
Feature activation-3.28e+00

Pos logit contributions
igator+0.125
 Amen+0.100
boat+0.093
 Mill+0.089
igators+0.087
Neg logit contributions
 fault-0.129
 loses-0.115
 injuries-0.113
ooming-0.110
 blood-0.108
Token forward
Token ID2651
Feature activation+1.39e+00

Pos logit contributions
 fault+0.264
 loses+0.251
udd+0.234
ooming+0.234
joy+0.231
Neg logit contributions
igator-0.281
 Amen-0.249
boat-0.226
ull-0.222
eway-0.218
Token and
Token ID290
Feature activation-5.08e-01

Pos logit contributions
igator+0.145
 Amen+0.124
boat+0.120
eway+0.112
ull+0.112
Neg logit contributions
 fault-0.127
 loses-0.118
joy-0.115
 blood-0.111
udd-0.111
Token backward
Token ID19528
Feature activation+1.83e+00

Pos logit contributions
 fault+0.053
 loses+0.048
joy+0.048
udd+0.046
 blood+0.046
Neg logit contributions
igator-0.047
 Amen-0.039
boat-0.039
eway-0.035
ull-0.035
Token,
Token ID11
Feature activation+2.02e-01

Pos logit contributions
igator+0.160
boat+0.133
 Amen+0.130
eway+0.121
ull+0.120
Neg logit contributions
 fault-0.193
 loses-0.177
joy-0.175
 blood-0.172
udd-0.171
Token z
Token ID1976
Feature activation-3.37e+00

Pos logit contributions
igator+0.020
 Amen+0.017
boat+0.017
eway+0.016
ull+0.015
Neg logit contributions
 fault-0.019
 loses-0.018
joy-0.017
udd-0.017
 blood-0.017
Tokenooming
Token ID30602
Feature activation-1.11e+01

Pos logit contributions
 fault+0.204
 loses+0.167
 blood+0.161
 underwear+0.149
udd+0.145
Neg logit contributions
igator-0.435
boat-0.403
 Amen-0.386
ull-0.377
eway-0.377
Token all
Token ID477
Feature activation-1.35e+00

Pos logit contributions
 fault+1.116
 loses+1.081
joy+1.037
 blood+1.004
udd+1.000
Neg logit contributions
igator-1.032
 Amen-0.904
boat-0.819
ull-0.771
igators-0.765
Token around
Token ID1088
Feature activation+2.10e+00

Pos logit contributions
 fault+0.130
 loses+0.121
joy+0.121
udd+0.119
 blood+0.116
Neg logit contributions
igator-0.116
 Amen-0.114
eway-0.097
ull-0.093
 Mill-0.093
Token the
Token ID262
Feature activation+7.21e-02

Pos logit contributions
igator+0.161
boat+0.126
 Amen+0.120
eway+0.118
ull+0.117
Neg logit contributions
 fault-0.250
 loses-0.234
udd-0.228
 underwear-0.226
 blood-0.221
Token ranch
Token ID28752
Feature activation+2.07e+00

Pos logit contributions
igator+0.006
boat+0.005
 Amen+0.004
 type+0.004
man+0.004
Neg logit contributions
 fault-0.008
 loses-0.008
joy-0.007
 blood-0.007
 underwear-0.007
Token.
Token ID13
Feature activation-3.74e-01

Pos logit contributions
igator+0.195
 Amen+0.161
boat+0.160
eway+0.147
ull+0.146
Neg logit contributions
 fault-0.209
 loses-0.194
joy-0.189
 blood-0.186
 underwear-0.184
Token there
Token ID612
Feature activation+1.13e+00

Pos logit contributions
igator+0.039
 Amen+0.035
boat+0.034
eway+0.031
ull+0.031
Neg logit contributions
 fault-0.030
 loses-0.028
joy-0.027
 blood-0.027
ooming-0.026
Token was
Token ID373
Feature activation+6.08e-01

Pos logit contributions
igator+0.100
 Amen+0.083
boat+0.080
eway+0.073
ull+0.073
Neg logit contributions
 fault-0.121
 loses-0.114
joy-0.111
 blood-0.108
udd-0.108
Token a
Token ID257
Feature activation+3.34e-01

Pos logit contributions
igator+0.054
 Amen+0.044
boat+0.042
ull+0.040
 Mill+0.039
Neg logit contributions
 fault-0.066
 loses-0.063
joy-0.060
udd-0.059
ooming-0.059
Token little
Token ID1310
Feature activation-1.16e+00

Pos logit contributions
igator+0.033
 Amen+0.028
boat+0.027
eway+0.026
ull+0.025
Neg logit contributions
 fault-0.032
 loses-0.030
joy-0.029
 blood-0.028
udd-0.028
Token boy
Token ID2933
Feature activation-1.72e+00

Pos logit contributions
 fault+0.094
joy+0.090
 loses+0.088
 blood+0.087
udd+0.086
Neg logit contributions
igator-0.122
 Amen-0.109
eway-0.108
boat-0.105
ull-0.099
Token named
Token ID3706
Feature activation+6.72e+00

Pos logit contributions
 blood+0.163
 loses+0.162
ooming+0.161
 forg+0.159
udd+0.158
Neg logit contributions
igator-0.146
eway-0.128
works-0.124
boat-0.122
 Amen-0.116
Token Jason
Token ID8982
Feature activation-6.51e-01

Pos logit contributions
igator+0.598
 Amen+0.496
boat+0.482
eway+0.443
ull+0.439
Neg logit contributions
 fault-0.728
 loses-0.684
joy-0.665
 blood-0.650
udd-0.647
Token.
Token ID13
Feature activation-1.87e-01

Pos logit contributions
 fault+0.045
joy+0.040
 blood+0.040
 loses+0.038
udd+0.038
Neg logit contributions
igator-0.080
eway-0.069
boat-0.068
igators-0.067
 Amen-0.067
Token Every
Token ID3887
Feature activation+1.72e+00

Pos logit contributions
 fault+0.020
 loses+0.019
 blood+0.018
ooming+0.018
udd+0.018
Neg logit contributions
igator-0.015
 Amen-0.014
boat-0.013
 particular-0.012
ull-0.012
Token day
Token ID1110
Feature activation+3.47e+00

Pos logit contributions
igator+0.113
 Amen+0.085
boat+0.080
eway+0.073
igators+0.073
Neg logit contributions
 fault-0.224
 loses-0.208
joy-0.206
 blood-0.203
udd-0.202
Token he
Token ID339
Feature activation-1.01e+00

Pos logit contributions
igator+0.297
 Amen+0.246
boat+0.238
ull+0.217
eway+0.215
Neg logit contributions
 fault-0.384
 loses-0.358
joy-0.348
 blood-0.341
udd-0.340
Token there
Token ID612
Feature activation+1.09e+00

Pos logit contributions
igator+0.031
 Amen+0.026
boat+0.025
eway+0.024
ull+0.023
Neg logit contributions
 fault-0.032
 loses-0.030
joy-0.029
 blood-0.028
ooming-0.028
Token was
Token ID373
Feature activation+5.84e-01

Pos logit contributions
igator+0.085
boat+0.066
 Amen+0.066
ull+0.061
eway+0.060
Neg logit contributions
 fault-0.128
 loses-0.121
joy-0.118
 underwear-0.115
udd-0.115
Token a
Token ID257
Feature activation+3.42e-01

Pos logit contributions
igator+0.051
 Amen+0.042
boat+0.039
ull+0.038
 Mill+0.037
Neg logit contributions
 fault-0.064
 loses-0.062
joy-0.059
ooming-0.058
udd-0.058
Token little
Token ID1310
Feature activation-1.16e+00

Pos logit contributions
igator+0.034
 Amen+0.028
boat+0.027
eway+0.026
ull+0.025
Neg logit contributions
 fault-0.033
 loses-0.031
joy-0.030
 blood-0.029
udd-0.029
Token boy
Token ID2933
Feature activation-1.86e+00

Pos logit contributions
 fault+0.093
joy+0.088
 loses+0.088
 blood+0.086
udd+0.086
Neg logit contributions
igator-0.121
 Amen-0.109
eway-0.109
boat-0.105
ull-0.099
Token named
Token ID3706
Feature activation+6.70e+00

Pos logit contributions
 loses+0.179
 blood+0.177
ooming+0.175
udd+0.174
 fault+0.173
Neg logit contributions
igator-0.157
eway-0.141
works-0.132
boat-0.131
 Amen-0.124
Token Tim
Token ID5045
Feature activation+2.45e-01

Pos logit contributions
igator+0.579
 Amen+0.471
boat+0.454
eway+0.418
ull+0.416
Neg logit contributions
 fault-0.747
 loses-0.704
joy-0.686
 blood-0.669
udd-0.666
Tokenmy
Token ID1820
Feature activation+4.16e-01

Pos logit contributions
igator+0.024
 Amen+0.020
boat+0.020
ull+0.019
eway+0.018
Neg logit contributions
 fault-0.024
 loses-0.022
joy-0.022
 underwear-0.021
 blood-0.021
Token.
Token ID13
Feature activation-9.75e-02

Pos logit contributions
igator+0.042
 Amen+0.035
boat+0.034
eway+0.032
ull+0.032
Neg logit contributions
 fault-0.040
 loses-0.037
joy-0.036
 blood-0.035
udd-0.035
Token Tim
Token ID5045
Feature activation+2.57e-01

Pos logit contributions
 fault+0.009
joy+0.008
udd+0.008
 loses+0.008
 blood+0.008
Neg logit contributions
igator-0.010
boat-0.009
 Amen-0.009
eway-0.008
ull-0.008
Tokenmy
Token ID1820
Feature activation+4.39e-01

Pos logit contributions
igator+0.026
 Amen+0.022
boat+0.021
ull+0.020
eway+0.020
Neg logit contributions
 fault-0.024
 loses-0.023
joy-0.022
 blood-0.021
 underwear-0.021
Token,
Token ID11
Feature activation+1.35e-01

Pos logit contributions
 fault+0.035
 loses+0.033
joy+0.032
 blood+0.031
udd+0.031
Neg logit contributions
igator-0.030
 Amen-0.025
boat-0.024
eway-0.022
ull-0.022
Token there
Token ID612
Feature activation+8.64e-01

Pos logit contributions
igator+0.014
 Amen+0.013
boat+0.013
eway+0.012
ull+0.011
Neg logit contributions
 fault-0.011
 loses-0.010
joy-0.010
 blood-0.010
ooming-0.010
Token was
Token ID373
Feature activation+3.65e-01

Pos logit contributions
igator+0.073
 Amen+0.059
boat+0.058
eway+0.053
ull+0.053
Neg logit contributions
 fault-0.096
 loses-0.090
joy-0.088
 blood-0.086
udd-0.086
Token a
Token ID257
Feature activation+8.46e-02

Pos logit contributions
igator+0.034
 Amen+0.028
boat+0.027
ull+0.025
eway+0.025
Neg logit contributions
 fault-0.038
 loses-0.036
joy-0.034
udd-0.034
ooming-0.033
Token girl
Token ID2576
Feature activation-9.26e-01

Pos logit contributions
igator+0.008
 Amen+0.007
boat+0.007
eway+0.007
ull+0.006
Neg logit contributions
 fault-0.008
 loses-0.007
joy-0.007
 blood-0.007
udd-0.007
Token named
Token ID3706
Feature activation+6.55e+00

Pos logit contributions
udd+0.086
 blood+0.085
joy+0.084
 forg+0.084
 loses+0.083
Neg logit contributions
igator-0.081
eway-0.072
boat-0.070
works-0.067
igators-0.065
Token Lily
Token ID20037
Feature activation-1.51e+00

Pos logit contributions
igator+0.726
 Amen+0.630
boat+0.625
eway+0.577
ull+0.577
Neg logit contributions
 fault-0.557
 loses-0.515
joy-0.498
 blood-0.482
udd-0.482
Token.
Token ID13
Feature activation-4.30e-01

Pos logit contributions
 fault+0.119
 loses+0.108
 blood+0.107
joy+0.107
udd+0.106
Neg logit contributions
igator-0.172
 Amen-0.145
boat-0.144
eway-0.141
igators-0.138
Token She
Token ID1375
Feature activation-5.99e-01

Pos logit contributions
 fault+0.042
 loses+0.039
joy+0.038
 blood+0.037
udd+0.037
Neg logit contributions
igator-0.042
 Amen-0.036
boat-0.035
eway-0.032
ull-0.032
Token was
Token ID373
Feature activation+3.54e-01

Pos logit contributions
 fault+0.057
 loses+0.057
udd+0.054
 blood+0.054
 underwear+0.054
Neg logit contributions
igator-0.056
boat-0.047
 Amen-0.046
eway-0.045
igators-0.043
Token a
Token ID257
Feature activation+8.37e-02

Pos logit contributions
igator+0.035
boat+0.031
 Amen+0.029
eway+0.029
ull+0.027
Neg logit contributions
 fault-0.034
joy-0.031
 loses-0.031
 blood-0.031
 underwear-0.030
Token Sam
Token ID3409
Feature activation+5.93e-01

Pos logit contributions
 fault+0.027
joy+0.026
 loses+0.026
udd+0.024
 underwear+0.024
Neg logit contributions
igator-0.025
 Amen-0.021
boat-0.020
ull-0.018
igators-0.018
Token gave
Token ID2921
Feature activation+1.95e+00

Pos logit contributions
igator+0.056
 Amen+0.047
boat+0.045
eway+0.042
ull+0.042
Neg logit contributions
 fault-0.060
 loses-0.056
joy-0.054
 blood-0.053
udd-0.053
Token a
Token ID257
Feature activation+1.90e-01

Pos logit contributions
igator+0.191
 Amen+0.160
boat+0.156
eway+0.145
ull+0.145
Neg logit contributions
 fault-0.192
 loses-0.179
joy-0.173
 blood-0.169
udd-0.169
Token special
Token ID2041
Feature activation+2.31e+00

Pos logit contributions
igator+0.018
 Amen+0.016
boat+0.015
eway+0.014
ull+0.014
Neg logit contributions
 fault-0.018
 loses-0.017
joy-0.017
 blood-0.016
 underwear-0.016
Token fire
Token ID2046
Feature activation+1.28e+00

Pos logit contributions
igator+0.209
igators+0.170
boat+0.169
 Amen+0.168
eway+0.163
Neg logit contributions
 fault-0.240
joy-0.221
 blood-0.219
 underwear-0.206
 loses-0.204
Tokenman
Token ID805
Feature activation+7.96e+00

Pos logit contributions
igator+0.108
 Amen+0.092
eway+0.084
boat+0.083
igators+0.081
Neg logit contributions
 fault-0.142
joy-0.125
 blood-0.123
 loses-0.123
 underwear-0.121
Token's
Token ID338
Feature activation-2.89e+00

Pos logit contributions
igator+0.837
 Amen+0.746
boat+0.693
eway+0.689
igators+0.670
Neg logit contributions
 fault-0.690
joy-0.643
 loses-0.629
 underwear-0.605
 blood-0.593
Token hat
Token ID6877
Feature activation+6.80e-01

Pos logit contributions
 fault+0.293
 blood+0.255
joy+0.255
 loses+0.251
 underwear+0.246
Neg logit contributions
igator-0.285
boat-0.235
 Amen-0.229
eway-0.222
igators-0.218
Token that
Token ID326
Feature activation-1.95e+00

Pos logit contributions
igator+0.072
 Amen+0.064
boat+0.059
eway+0.058
igators+0.057
Neg logit contributions
 fault-0.061
 loses-0.055
joy-0.053
 underwear-0.053
 blood-0.052
Token he
Token ID339
Feature activation-1.19e+00

Pos logit contributions
 fault+0.167
 loses+0.159
 blood+0.153
 underwear+0.147
joy+0.144
Neg logit contributions
igator-0.195
 Amen-0.184
eway-0.162
boat-0.161
iona-0.151
Token had
Token ID550
Feature activation+1.56e+00

Pos logit contributions
 fault+0.117
 loses+0.115
udd+0.107
 underwear+0.106
joy+0.106
Neg logit contributions
igator-0.110
 Amen-0.095
boat-0.090
eway-0.089
ull-0.082
TokenK
Token ID42
Feature activation+3.32e-02

Pos logit contributions
igator+0.111
 Amen+0.094
boat+0.091
ull+0.088
eway+0.086
Neg logit contributions
 fault-0.143
 loses-0.133
 underwear-0.129
udd-0.126
ooming-0.125
Tokenaren
Token ID5757
Feature activation+1.34e-01

Pos logit contributions
igator+0.003
boat+0.003
 Amen+0.003
ull+0.002
eway+0.002
Neg logit contributions
 fault-0.003
 loses-0.003
joy-0.003
 blood-0.003
 underwear-0.003
Token was
Token ID373
Feature activation+4.83e-01

Pos logit contributions
igator+0.014
 Amen+0.012
boat+0.012
eway+0.011
ull+0.011
Neg logit contributions
 fault-0.012
 loses-0.011
joy-0.011
udd-0.011
 blood-0.010
Token a
Token ID257
Feature activation+2.08e-01

Pos logit contributions
igator+0.047
 Amen+0.039
boat+0.038
eway+0.036
ull+0.035
Neg logit contributions
 fault-0.048
 loses-0.045
joy-0.043
 blood-0.042
udd-0.042
Token 3
Token ID513
Feature activation+1.09e+00

Pos logit contributions
igator+0.021
 Amen+0.017
boat+0.017
eway+0.017
ull+0.016
Neg logit contributions
 fault-0.019
joy-0.018
 loses-0.018
udd-0.017
 blood-0.017
Token year
Token ID614
Feature activation+6.53e+00

Pos logit contributions
igator+0.073
boat+0.063
 Amen+0.060
eway+0.058
works+0.058
Neg logit contributions
joy-0.121
udd-0.117
 loses-0.115
ooming-0.115
 forg-0.114
Token old
Token ID1468
Feature activation+1.90e+00

Pos logit contributions
igator+0.649
 Amen+0.621
boat+0.606
eway+0.579
ull+0.568
Neg logit contributions
udd-0.542
 fault-0.531
joy-0.524
 loses-0.518
ooming-0.467
Token girl
Token ID2576
Feature activation-8.44e-01

Pos logit contributions
igator+0.192
 Amen+0.162
boat+0.159
eway+0.151
ull+0.148
Neg logit contributions
 fault-0.178
 loses-0.166
joy-0.163
 blood-0.157
udd-0.156
Token who
Token ID508
Feature activation-1.74e+00

Pos logit contributions
 fault+0.082
 loses+0.078
joy+0.078
udd+0.074
ooming+0.074
Neg logit contributions
igator-0.081
boat-0.066
 Amen-0.065
eway-0.064
ull-0.061
Token was
Token ID373
Feature activation+4.65e-01

Pos logit contributions
 fault+0.186
 loses+0.179
udd+0.172
joy+0.170
 underwear+0.167
Neg logit contributions
igator-0.150
 Amen-0.125
boat-0.121
eway-0.117
ull-0.114
Token a
Token ID257
Feature activation+1.89e-01

Pos logit contributions
igator+0.045
boat+0.038
 Amen+0.037
eway+0.036
ull+0.035
Neg logit contributions
 fault-0.046
 loses-0.042
joy-0.042
 blood-0.040
udd-0.039
Token and
Token ID290
Feature activation-6.45e-01

Pos logit contributions
 fault+0.093
 loses+0.088
joy+0.084
 blood+0.083
udd+0.082
Neg logit contributions
igator-0.105
 Amen-0.089
boat-0.087
eway-0.082
ull-0.081
Token wanted
Token ID2227
Feature activation+1.67e+00

Pos logit contributions
 fault+0.070
 loses+0.068
joy+0.065
 blood+0.064
 underwear+0.064
Neg logit contributions
igator-0.055
 Amen-0.045
boat-0.044
eway-0.040
ull-0.040
Token to
Token ID284
Feature activation-3.15e-01

Pos logit contributions
igator+0.151
 Amen+0.123
boat+0.119
ull+0.114
 Mill+0.112
Neg logit contributions
 fault-0.176
 loses-0.163
udd-0.159
joy-0.159
ooming-0.159
Token catch
Token ID4929
Feature activation-9.63e-01

Pos logit contributions
 loses+0.026
 fault+0.024
 blood+0.024
 underwear+0.022
 forg+0.021
Neg logit contributions
igator-0.033
 Amen-0.031
boat-0.030
works-0.029
eway-0.028
Token it
Token ID340
Feature activation+1.46e-01

Pos logit contributions
 fault+0.113
 loses+0.103
joy+0.102
udd+0.101
ooming+0.100
Neg logit contributions
igator-0.077
 Amen-0.062
boat-0.059
ull-0.056
eway-0.054
Token,
Token ID11
Feature activation+9.82e-02

Pos logit contributions
igator+0.015
 Amen+0.014
boat+0.013
ull+0.012
eway+0.012
Neg logit contributions
 fault-0.013
 loses-0.012
joy-0.012
 blood-0.011
 underwear-0.011
Token but
Token ID475
Feature activation-1.10e+00

Pos logit contributions
igator+0.011
 Amen+0.009
boat+0.009
eway+0.008
ull+0.008
Neg logit contributions
 fault-0.009
 loses-0.008
joy-0.008
 blood-0.008
 underwear-0.007
Token she
Token ID673
Feature activation-1.93e+00

Pos logit contributions
 fault+0.117
 loses+0.109
joy+0.107
udd+0.104
 blood+0.103
Neg logit contributions
igator-0.100
 Amen-0.082
boat-0.081
eway-0.074
ull-0.073
Token didn
Token ID1422
Feature activation+1.81e+00

Pos logit contributions
 fault+0.235
joy+0.217
 loses+0.205
ooming+0.201
udd+0.200
Neg logit contributions
igator-0.151
boat-0.118
 Amen-0.113
ull-0.112
man-0.105
Token't
Token ID470
Feature activation-3.65e-01

Pos logit contributions
igator+0.164
 Amen+0.136
boat+0.132
eway+0.122
ull+0.121
Neg logit contributions
 fault-0.189
 loses-0.178
joy-0.173
 blood-0.168
udd-0.168
Token know
Token ID760
Feature activation+7.96e-01

Pos logit contributions
 fault+0.039
 loses+0.038
joy+0.036
 blood+0.036
 underwear+0.035
Neg logit contributions
igator-0.031
 Amen-0.026
boat-0.025
eway-0.024
ull-0.023
Token I
Token ID314
Feature activation+9.83e-01

Pos logit contributions
joy+0.059
 fault+0.058
 loses+0.055
 underwear+0.051
 blood+0.050
Neg logit contributions
igator-0.073
boat-0.063
 Amen-0.060
works-0.059
ull-0.058
Token'm
Token ID1101
Feature activation-6.55e-01

Pos logit contributions
igator+0.100
 Amen+0.084
boat+0.083
igators+0.081
eway+0.080
Neg logit contributions
 fault-0.089
 loses-0.087
udd-0.079
joy-0.078
 underwear-0.078
Token so
Token ID523
Feature activation+1.67e+00

Pos logit contributions
 fault+0.057
 loses+0.051
joy+0.050
 blood+0.049
 underwear+0.047
Neg logit contributions
igator-0.071
boat-0.064
 Amen-0.060
eway-0.058
works-0.057
Token proud
Token ID6613
Feature activation-1.04e+00

Pos logit contributions
igator+0.194
boat+0.180
eway+0.171
works+0.169
 Amen+0.168
Neg logit contributions
 fault-0.119
 loses-0.115
joy-0.113
udd-0.109
 forg-0.103
Token of
Token ID286
Feature activation+1.86e+00

Pos logit contributions
 fault+0.104
 loses+0.102
joy+0.097
 blood+0.095
udd+0.094
Neg logit contributions
igator-0.094
 Amen-0.082
boat-0.081
eway-0.073
ull-0.072
Token you
Token ID345
Feature activation+9.48e-01

Pos logit contributions
igator+0.193
boat+0.169
 Amen+0.163
ull+0.152
man+0.151
Neg logit contributions
 fault-0.167
joy-0.157
 loses-0.157
 blood-0.152
 underwear-0.144
Token for
Token ID329
Feature activation-1.30e+00

Pos logit contributions
igator+0.100
 Amen+0.084
boat+0.084
igators+0.080
ull+0.080
Neg logit contributions
 fault-0.084
 loses-0.079
joy-0.076
udd-0.072
 underwear-0.071
Token taking
Token ID2263
Feature activation-1.93e+00

Pos logit contributions
 fault+0.112
 loses+0.106
joy+0.103
 blood+0.103
 injuries+0.097
Neg logit contributions
igator-0.144
boat-0.124
 Amen-0.120
ull-0.112
eway-0.111
Token such
Token ID884
Feature activation-3.48e+00

Pos logit contributions
 fault+0.184
 loses+0.175
joy+0.170
 blood+0.164
 underwear+0.161
Neg logit contributions
igator-0.195
 Amen-0.164
boat-0.161
ull-0.149
eway-0.148
Token good
Token ID922
Feature activation-2.47e+00

Pos logit contributions
 fault+0.332
 loses+0.298
joy+0.295
 blood+0.289
 underwear+0.281
Neg logit contributions
igator-0.359
 Amen-0.306
boat-0.302
eway-0.276
ull-0.275
Token care
Token ID1337
Feature activation+5.69e-01

Pos logit contributions
 fault+0.244
 loses+0.226
joy+0.221
 blood+0.215
 underwear+0.213
Neg logit contributions
igator-0.246
 Amen-0.208
boat-0.202
eway-0.188
ull-0.187
Token."
Token ID526
Feature activation+7.26e-01

Pos logit contributions
igator+0.200
 Amen+0.160
boat+0.155
igators+0.141
 Mill+0.138
Neg logit contributions
 fault-0.249
 loses-0.235
joy-0.232
ooming-0.228
 blood-0.228
Token
Token ID198
Feature activation-1.28e+00

Pos logit contributions
igator+0.062
 Amen+0.054
boat+0.051
 Mill+0.048
ull+0.047
Neg logit contributions
 fault-0.078
 loses-0.074
joy-0.070
 blood-0.070
ooming-0.069
Token
Token ID198
Feature activation-1.29e+00

Pos logit contributions
 fault+0.124
 loses+0.116
joy+0.112
 underwear+0.109
 blood+0.108
Neg logit contributions
igator-0.126
 Amen-0.108
boat-0.105
ull-0.098
eway-0.098
TokenAfter
Token ID3260
Feature activation-7.84e-01

Pos logit contributions
udd+0.100
 fault+0.099
 loses+0.097
ooming+0.096
joy+0.093
Neg logit contributions
igator-0.145
 Amen-0.123
igators-0.115
boat-0.114
eway-0.112
Token spending
Token ID4581
Feature activation-2.76e+00

Pos logit contributions
 fault+0.071
 loses+0.066
joy+0.065
 blood+0.063
 underwear+0.062
Neg logit contributions
igator-0.083
 Amen-0.070
boat-0.069
eway-0.064
ull-0.064
Token some
Token ID617
Feature activation+3.32e-01

Pos logit contributions
 fault+0.271
 loses+0.255
joy+0.249
 blood+0.242
 underwear+0.237
Neg logit contributions
igator-0.269
 Amen-0.227
boat-0.220
ull-0.205
eway-0.202
Token time
Token ID640
Feature activation-4.15e-02

Pos logit contributions
igator+0.032
 Amen+0.027
boat+0.026
eway+0.024
ull+0.024
Neg logit contributions
 fault-0.033
 loses-0.031
joy-0.030
 blood-0.029
udd-0.029
Token with
Token ID351
Feature activation+2.97e+00

Pos logit contributions
 fault+0.005
 loses+0.004
joy+0.004
 blood+0.004
udd+0.004
Neg logit contributions
igator-0.003
boat-0.003
 Amen-0.003
 Mill-0.002
ull-0.002
Token his
Token ID465
Feature activation+1.52e+00

Pos logit contributions
igator+0.267
 Amen+0.219
boat+0.214
eway+0.197
ull+0.197
Neg logit contributions
 fault-0.315
 loses-0.297
joy-0.287
udd-0.280
 blood-0.280
Token grandma
Token ID49890
Feature activation-2.12e+00

Pos logit contributions
igator+0.150
 Amen+0.128
boat+0.123
 Mill+0.119
 particular+0.118
Neg logit contributions
 fault-0.139
 loses-0.135
udd-0.127
joy-0.123
ooming-0.123
Token,
Token ID11
Feature activation+3.88e-01

Pos logit contributions
 fault+0.224
 loses+0.210
joy+0.204
 blood+0.200
udd+0.199
Neg logit contributions
igator-0.190
 Amen-0.157
boat-0.153
eway-0.139
ull-0.139
Token help
Token ID1037
Feature activation+4.11e-01

Pos logit contributions
 fault+0.071
 blood+0.065
 loses+0.065
 injuries+0.062
 underwear+0.062
Neg logit contributions
igator-0.060
 Amen-0.049
boat-0.047
eway-0.047
igators-0.044
Token others
Token ID1854
Feature activation+9.00e-01

Pos logit contributions
igator+0.038
 Amen+0.032
boat+0.031
eway+0.028
ull+0.028
Neg logit contributions
 fault-0.043
 loses-0.041
 blood-0.039
joy-0.039
udd-0.038
Token when
Token ID618
Feature activation-8.39e-02

Pos logit contributions
igator+0.089
 Amen+0.076
boat+0.073
eway+0.069
ull+0.068
Neg logit contributions
 fault-0.087
 loses-0.081
joy-0.078
 blood-0.076
udd-0.076
Token they
Token ID484
Feature activation-9.33e-03

Pos logit contributions
 fault+0.008
 loses+0.008
joy+0.007
 blood+0.007
udd+0.007
Neg logit contributions
igator-0.008
 Amen-0.007
boat-0.007
eway-0.006
ull-0.006
Token need
Token ID761
Feature activation+1.04e+00

Pos logit contributions
 fault+0.001
 loses+0.001
joy+0.001
udd+0.001
 underwear+0.001
Neg logit contributions
igator-0.001
 Amen-0.001
boat-0.001
ull-0.001
igators-0.001
Token it
Token ID340
Feature activation+4.19e-02

Pos logit contributions
igator+0.107
 Amen+0.089
boat+0.088
eway+0.082
ull+0.080
Neg logit contributions
 fault-0.100
 loses-0.093
 blood-0.090
joy-0.089
 underwear-0.085
Token,
Token ID11
Feature activation+3.45e-02

Pos logit contributions
igator+0.004
boat+0.003
 Amen+0.003
ull+0.003
eway+0.003
Neg logit contributions
 fault-0.004
 loses-0.004
joy-0.004
 blood-0.004
 underwear-0.004
Token even
Token ID772
Feature activation-6.39e-01

Pos logit contributions
igator+0.003
 Amen+0.003
boat+0.003
eway+0.003
ull+0.003
Neg logit contributions
 fault-0.003
 loses-0.003
joy-0.003
 blood-0.003
 underwear-0.003
Token if
Token ID611
Feature activation-1.11e+00

Pos logit contributions
 fault+0.058
 loses+0.055
 blood+0.052
joy+0.052
 underwear+0.050
Neg logit contributions
igator-0.066
 Amen-0.057
boat-0.055
eway-0.053
ull-0.052
Token it
Token ID340
Feature activation+1.36e-01

Pos logit contributions
 fault+0.105
 loses+0.099
joy+0.094
 blood+0.094
 underwear+0.090
Neg logit contributions
igator-0.113
 Amen-0.095
boat-0.093
eway-0.088
ull-0.086
Token means
Token ID1724
Feature activation+2.90e-01

Pos logit contributions
igator+0.014
 Amen+0.012
boat+0.012
igators+0.011
ull+0.011
Neg logit contributions
 fault-0.012
joy-0.011
 loses-0.011
udd-0.011
 blood-0.011
Token and
Token ID290
Feature activation-3.95e-01

Pos logit contributions
igator+0.053
boat+0.044
 Amen+0.042
 Mill+0.039
ull+0.039
Neg logit contributions
 fault-0.061
 loses-0.058
joy-0.057
ooming-0.056
udd-0.055
Token that
Token ID326
Feature activation-1.84e+00

Pos logit contributions
 fault+0.035
 loses+0.034
 blood+0.032
 underwear+0.031
joy+0.030
Neg logit contributions
igator-0.041
 Amen-0.038
eway-0.035
boat-0.034
ull-0.034
Token Tom
Token ID4186
Feature activation-3.50e+00

Pos logit contributions
 fault+0.179
 loses+0.168
joy+0.162
 blood+0.158
udd+0.157
Neg logit contributions
igator-0.179
 Amen-0.151
boat-0.147
eway-0.137
ull-0.136
Token was
Token ID373
Feature activation+5.37e-01

Pos logit contributions
 fault+0.373
joy+0.351
 loses+0.347
 blood+0.334
ooming+0.334
Neg logit contributions
igator-0.310
boat-0.249
 Amen-0.247
ull-0.226
igators-0.220
Token not
Token ID407
Feature activation+1.68e+00

Pos logit contributions
igator+0.056
 Amen+0.048
boat+0.047
eway+0.045
ull+0.044
Neg logit contributions
 fault-0.050
 loses-0.046
joy-0.044
 blood-0.044
 underwear-0.042
Token ready
Token ID3492
Feature activation+2.81e-01

Pos logit contributions
igator+0.171
 Amen+0.150
boat+0.142
eway+0.138
ull+0.132
Neg logit contributions
 fault-0.158
 loses-0.146
joy-0.141
 blood-0.139
 underwear-0.136
Token for
Token ID329
Feature activation-9.49e-01

Pos logit contributions
igator+0.027
 Amen+0.023
boat+0.022
eway+0.021
ull+0.021
Neg logit contributions
 fault-0.027
 loses-0.025
joy-0.025
udd-0.024
 blood-0.024
Token it
Token ID340
Feature activation+3.02e-01

Pos logit contributions
 fault+0.096
 loses+0.090
udd+0.089
joy+0.086
ooming+0.086
Neg logit contributions
igator-0.085
 Amen-0.072
boat-0.069
ull-0.065
 Mill-0.065
Token.
Token ID13
Feature activation-2.04e-01

Pos logit contributions
igator+0.028
boat+0.022
 Amen+0.021
eway+0.020
igators+0.020
Neg logit contributions
 fault-0.031
joy-0.029
 loses-0.029
ooming-0.028
 blood-0.028
Token
Token ID198
Feature activation-1.33e+00

Pos logit contributions
 fault+0.023
 loses+0.022
joy+0.021
ooming+0.021
 underwear+0.021
Neg logit contributions
igator-0.017
 Amen-0.014
boat-0.013
ull-0.012
eway-0.012
Token
Token ID198
Feature activation-1.33e+00

Pos logit contributions
 fault+0.130
 loses+0.122
joy+0.119
 underwear+0.116
ooming+0.114
Neg logit contributions
igator-0.129
 Amen-0.109
boat-0.106
ull-0.100
eway-0.100
Token
Token ID198
Feature activation-1.28e+00

Pos logit contributions
 fault+0.128
 loses+0.119
joy+0.114
 underwear+0.111
 blood+0.110
Neg logit contributions
igator-0.121
 Amen-0.105
boat-0.101
ull-0.094
eway-0.093
TokenL
Token ID43
Feature activation-2.17e-01

Pos logit contributions
 fault+0.105
 loses+0.098
joy+0.094
 blood+0.091
udd+0.091
Neg logit contributions
igator-0.144
 Amen-0.124
boat-0.121
eway-0.114
ull-0.114
Tokenily
Token ID813
Feature activation-5.10e-01

Pos logit contributions
 fault+0.023
 loses+0.022
joy+0.022
 underwear+0.021
 blood+0.020
Neg logit contributions
igator-0.020
boat-0.015
 Amen-0.015
ull-0.015
eway-0.015
Token and
Token ID290
Feature activation-3.77e-01

Pos logit contributions
 fault+0.055
 loses+0.050
joy+0.049
 blood+0.048
ooming+0.047
Neg logit contributions
igator-0.045
 Amen-0.037
boat-0.036
ull-0.033
man-0.033
Token Max
Token ID5436
Feature activation-3.88e+00

Pos logit contributions
 fault+0.032
 loses+0.030
udd+0.030
joy+0.028
ooming+0.028
Neg logit contributions
igator-0.042
 Amen-0.037
boat-0.035
 Mill-0.035
 Ally-0.034
Token continued
Token ID3767
Feature activation-3.63e+00

Pos logit contributions
 fault+0.403
 loses+0.370
joy+0.361
 blood+0.353
udd+0.347
Neg logit contributions
igator-0.362
 Amen-0.300
boat-0.295
 Mill-0.268
ull-0.267
Token to
Token ID284
Feature activation+2.49e-03

Pos logit contributions
 fault+0.340
 loses+0.313
joy+0.310
 blood+0.296
ooming+0.295
Neg logit contributions
igator-0.375
 Amen-0.316
boat-0.311
eway-0.290
ull-0.287
Token be
Token ID307
Feature activation+1.87e+00

Pos logit contributions
igator+0.000
boat+0.000
eway+0.000
 Amen+0.000
ull+0.000
Neg logit contributions
 fault-0.000
 loses-0.000
 underwear-0.000
ooming-0.000
joy-0.000
Token best
Token ID1266
Feature activation-4.22e+00

Pos logit contributions
igator+0.200
 Amen+0.172
boat+0.166
eway+0.158
ull+0.154
Neg logit contributions
 fault-0.166
 loses-0.154
joy-0.152
udd-0.146
 blood-0.144
Token friends
Token ID2460
Feature activation-1.91e+00

Pos logit contributions
 fault+0.411
 loses+0.383
 underwear+0.360
 blood+0.359
joy+0.358
Neg logit contributions
igator-0.382
 Amen-0.344
 Mill-0.313
boat-0.306
ot-0.300
Token and
Token ID290
Feature activation-3.81e-01

Pos logit contributions
 fault+0.222
 loses+0.208
 blood+0.206
 underwear+0.204
ooming+0.200
Neg logit contributions
igator-0.141
 Amen-0.119
boat-0.113
 Mill-0.102
ull-0.099
Token was
Token ID373
Feature activation+4.98e-01

Pos logit contributions
 fault+0.295
 underwear+0.273
joy+0.272
 loses+0.269
 blood+0.268
Neg logit contributions
igator-0.353
 Amen-0.303
boat-0.290
igators-0.286
eway-0.283
Token a
Token ID257
Feature activation+2.19e-01

Pos logit contributions
igator+0.046
 Amen+0.037
boat+0.036
ull+0.034
 Mill+0.034
Neg logit contributions
 fault-0.051
 loses-0.048
joy-0.047
ooming-0.046
udd-0.046
Token new
Token ID649
Feature activation-4.31e+00

Pos logit contributions
igator+0.022
 Amen+0.019
boat+0.018
eway+0.017
ull+0.017
Neg logit contributions
 fault-0.021
 loses-0.019
joy-0.019
 blood-0.018
 underwear-0.018
Token toy
Token ID13373
Feature activation-1.74e+00

Pos logit contributions
 fault+0.388
 loses+0.351
joy+0.350
 underwear+0.335
 blood+0.335
Neg logit contributions
igator-0.458
 Amen-0.390
boat-0.380
eway-0.360
igators-0.357
Token.
Token ID13
Feature activation-1.84e-01

Pos logit contributions
 fault+0.164
 loses+0.153
joy+0.148
 blood+0.144
 underwear+0.143
Neg logit contributions
igator-0.176
 Amen-0.149
boat-0.145
eway-0.136
ull-0.135
Token She
Token ID1375
Feature activation-3.31e-01

Pos logit contributions
 fault+0.019
 loses+0.017
joy+0.017
ooming+0.016
 blood+0.016
Neg logit contributions
igator-0.017
 Amen-0.015
boat-0.014
 Mill-0.013
eway-0.013
Token loved
Token ID6151
Feature activation+2.37e-02

Pos logit contributions
 fault+0.034
 loses+0.033
joy+0.031
 underwear+0.031
udd+0.031
Neg logit contributions
igator-0.031
 Amen-0.026
boat-0.025
eway-0.023
ull-0.023
Token it
Token ID340
Feature activation+2.59e-01

Pos logit contributions
igator+0.002
 Amen+0.002
boat+0.002
eway+0.002
ull+0.002
Neg logit contributions
 fault-0.002
 loses-0.002
joy-0.002
 blood-0.002
udd-0.002
Token so
Token ID523
Feature activation+1.82e+00

Pos logit contributions
igator+0.022
 Amen+0.018
boat+0.017
eway+0.016
ull+0.016
Neg logit contributions
 fault-0.029
 loses-0.027
joy-0.027
 blood-0.026
udd-0.026
Token much
Token ID881
Feature activation-2.97e-01

Pos logit contributions
igator+0.114
 Amen+0.089
 Mill+0.086
 particular+0.082
ull+0.079
Neg logit contributions
 fault-0.232
 loses-0.216
ooming-0.215
joy-0.215
 underwear-0.209
Token that
Token ID326
Feature activation-1.92e+00

Pos logit contributions
 fault+0.031
 loses+0.029
joy+0.029
ooming+0.029
 underwear+0.028
Neg logit contributions
igator-0.026
boat-0.021
 Amen-0.021
 Mill-0.020
eway-0.019
Token around
Token ID1088
Feature activation+2.22e+00

Pos logit contributions
igator+0.154
 Amen+0.143
boat+0.127
igators+0.120
ull+0.117
Neg logit contributions
 fault-0.144
 loses-0.135
joy-0.135
 underwear-0.128
 blood-0.128
Token with
Token ID351
Feature activation+2.84e+00

Pos logit contributions
igator+0.230
 Amen+0.201
boat+0.191
eway+0.177
igators+0.177
Neg logit contributions
 fault-0.201
joy-0.189
 loses-0.187
 blood-0.179
 underwear-0.175
Token excitement
Token ID14067
Feature activation+2.15e+00

Pos logit contributions
igator+0.264
 Amen+0.221
boat+0.214
eway+0.198
ull+0.196
Neg logit contributions
 fault-0.293
 loses-0.275
joy-0.269
 blood-0.262
 underwear-0.259
Token.
Token ID13
Feature activation-2.81e-01

Pos logit contributions
igator+0.220
 Amen+0.189
boat+0.181
eway+0.168
ull+0.168
Neg logit contributions
 fault-0.201
 loses-0.186
joy-0.182
 underwear-0.175
udd-0.175
Token
Token ID220
Feature activation+2.70e+00

Pos logit contributions
 fault+0.028
 loses+0.026
joy+0.025
 blood+0.024
udd+0.024
Neg logit contributions
igator-0.027
 Amen-0.023
boat-0.022
eway-0.021
ull-0.020
Token
Token ID198
Feature activation-1.34e+00

Pos logit contributions
igator+0.236
 Amen+0.195
boat+0.194
eway+0.188
ull+0.187
Neg logit contributions
 fault-0.275
 loses-0.267
joy-0.259
 underwear-0.256
 blood-0.249
Token
Token ID198
Feature activation-1.35e+00

Pos logit contributions
 fault+0.107
 loses+0.100
joy+0.100
udd+0.095
 blood+0.094
Neg logit contributions
igator-0.152
 Amen-0.129
boat-0.126
igators-0.119
works-0.116
TokenM
Token ID44
Feature activation+2.08e+00

Pos logit contributions
joy+0.108
 fault+0.107
 loses+0.107
udd+0.102
ooming+0.100
Neg logit contributions
igator-0.143
 Amen-0.122
boat-0.115
works-0.112
 Mill-0.111
Tokenia
Token ID544
Feature activation-2.34e-01

Pos logit contributions
igator+0.201
 Amen+0.168
boat+0.164
ull+0.153
eway+0.153
Neg logit contributions
 fault-0.206
 loses-0.194
joy-0.188
 blood-0.183
 underwear-0.182
Token watched
Token ID7342
Feature activation-1.72e+00

Pos logit contributions
 fault+0.022
 loses+0.021
joy+0.020
udd+0.020
 underwear+0.020
Neg logit contributions
igator-0.023
 Amen-0.020
boat-0.019
eway-0.018
ull-0.018
Token him
Token ID683
Feature activation-1.41e+00

Pos logit contributions
 fault+0.164
joy+0.153
 loses+0.151
 blood+0.147
ooming+0.146
Neg logit contributions
igator-0.171
 Amen-0.146
boat-0.141
igators-0.131
eway-0.128
Token help
Token ID1037
Feature activation+9.39e-01

Pos logit contributions
 fault+0.104
 loses+0.098
joy+0.095
 blood+0.094
 underwear+0.092
Neg logit contributions
igator-0.075
 Amen-0.061
boat-0.059
eway-0.054
ull-0.053
Token,
Token ID11
Feature activation+3.87e-01

Pos logit contributions
igator+0.103
 Amen+0.095
boat+0.085
igators+0.081
eway+0.079
Neg logit contributions
 fault-0.081
 loses-0.074
 blood-0.072
joy-0.068
 injuries-0.068
Token but
Token ID475
Feature activation-8.27e-01

Pos logit contributions
igator+0.041
 Amen+0.035
boat+0.034
eway+0.032
ull+0.032
Neg logit contributions
 fault-0.035
 loses-0.032
joy-0.031
 blood-0.030
udd-0.030
Token no
Token ID645
Feature activation-1.01e+00

Pos logit contributions
 fault+0.067
 loses+0.062
 blood+0.061
joy+0.059
 injuries+0.057
Neg logit contributions
igator-0.093
 Amen-0.085
boat-0.078
eway-0.075
igators-0.074
Token one
Token ID530
Feature activation+6.52e-01

Pos logit contributions
 fault+0.107
 loses+0.101
joy+0.098
udd+0.098
ooming+0.095
Neg logit contributions
igator-0.090
boat-0.073
 Amen-0.073
ull-0.068
eway-0.066
Token heard
Token ID2982
Feature activation-1.38e+00

Pos logit contributions
igator+0.060
 Amen+0.049
boat+0.048
ull+0.045
eway+0.044
Neg logit contributions
 fault-0.068
 loses-0.064
joy-0.062
udd-0.061
 blood-0.060
Token him
Token ID683
Feature activation-1.40e+00

Pos logit contributions
 fault+0.131
 loses+0.122
joy+0.118
 blood+0.116
udd+0.114
Neg logit contributions
igator-0.139
 Amen-0.118
boat-0.114
eway-0.106
ull-0.106
Token.
Token ID13
Feature activation-1.34e-01

Pos logit contributions
 fault+0.145
joy+0.136
 loses+0.135
udd+0.132
 blood+0.129
Neg logit contributions
igator-0.125
boat-0.101
 Amen-0.101
eway-0.095
ull-0.094
Token Tim
Token ID5045
Feature activation+1.32e-01

Pos logit contributions
 fault+0.014
 loses+0.014
joy+0.013
 blood+0.013
udd+0.013
Neg logit contributions
igator-0.012
 Amen-0.010
boat-0.010
eway-0.009
ull-0.009
Token was
Token ID373
Feature activation+5.16e-01

Pos logit contributions
igator+0.011
boat+0.009
 Amen+0.008
ull+0.008
man+0.008
Neg logit contributions
 fault-0.015
joy-0.014
 loses-0.013
 underwear-0.013
ooming-0.013
Token stuck
Token ID7819
Feature activation-2.27e+00

Pos logit contributions
igator+0.048
 Amen+0.040
boat+0.038
ull+0.036
eway+0.035
Neg logit contributions
 fault-0.053
 loses-0.049
udd-0.049
joy-0.048
ooming-0.047
Token on
Token ID319
Feature activation-5.98e-01

Pos logit contributions
igator+0.008
 Amen+0.006
boat+0.006
ull+0.006
eway+0.006
Neg logit contributions
 fault-0.006
 loses-0.006
joy-0.006
 blood-0.005
ooming-0.005
Token,
Token ID11
Feature activation+1.72e-01

Pos logit contributions
 fault+0.056
 loses+0.053
joy+0.052
ooming+0.050
 blood+0.049
Neg logit contributions
igator-0.061
 Amen-0.051
boat-0.049
ull-0.046
eway-0.046
Token Peter
Token ID5613
Feature activation+3.97e+00

Pos logit contributions
igator+0.014
 Amen+0.011
boat+0.010
eway+0.010
igators+0.010
Neg logit contributions
 fault-0.020
 loses-0.019
joy-0.019
ooming-0.018
 blood-0.018
Token vowed
Token ID19982
Feature activation+9.74e-01

Pos logit contributions
igator+0.349
 Amen+0.286
boat+0.284
ull+0.258
eway+0.253
Neg logit contributions
 fault-0.426
 loses-0.397
joy-0.388
 blood-0.381
 underwear-0.378
Token to
Token ID284
Feature activation-2.05e-01

Pos logit contributions
igator+0.084
boat+0.071
 Amen+0.071
eway+0.064
 Mill+0.063
Neg logit contributions
 fault-0.101
 loses-0.096
joy-0.093
 underwear-0.092
udd-0.091
Token always
Token ID1464
Feature activation-4.12e-01

Pos logit contributions
 fault+0.020
 loses+0.018
 blood+0.017
 injuries+0.017
 forg+0.017
Neg logit contributions
igator-0.021
boat-0.016
 Amen-0.016
eway-0.016
igators-0.016
Token listen
Token ID6004
Feature activation-6.74e-01

Pos logit contributions
 fault+0.042
 loses+0.040
joy+0.038
 blood+0.038
 injuries+0.037
Neg logit contributions
igator-0.039
boat-0.030
 Amen-0.030
eway-0.029
ull-0.029
Token to
Token ID284
Feature activation-2.15e-01

Pos logit contributions
 fault+0.063
 loses+0.059
joy+0.057
 blood+0.055
udd+0.055
Neg logit contributions
igator-0.069
 Amen-0.059
boat-0.057
eway-0.053
ull-0.053
Token grown
Token ID7334
Feature activation-1.31e+00

Pos logit contributions
 fault+0.023
 loses+0.021
joy+0.020
 blood+0.020
 underwear+0.019
Neg logit contributions
igator-0.020
 Amen-0.016
boat-0.016
eway-0.015
ull-0.014
Token-
Token ID12
Feature activation+2.25e+00

Pos logit contributions
 fault+0.130
 loses+0.122
joy+0.119
udd+0.115
 blood+0.115
Neg logit contributions
igator-0.128
 Amen-0.107
boat-0.104
eway-0.096
ull-0.096
Tokenups
Token ID4739
Feature activation+6.20e-01

Pos logit contributions
igator+0.276
 Amen+0.242
boat+0.235
eway+0.223
ull+0.222
Neg logit contributions
 fault-0.164
 loses-0.151
joy-0.144
udd-0.139
 blood-0.139
Token!
Token ID0
Feature activation-1.03e+00

Pos logit contributions
 fault+0.145
 loses+0.137
joy+0.136
 underwear+0.131
udd+0.130
Neg logit contributions
igator-0.129
boat-0.104
 Amen-0.101
eway-0.094
igators-0.093
Token He
Token ID679
Feature activation+1.08e+00

Pos logit contributions
 fault+0.105
 loses+0.099
joy+0.097
 blood+0.094
udd+0.091
Neg logit contributions
igator-0.096
 Amen-0.080
boat-0.078
ull-0.071
eway-0.071
Token tried
Token ID3088
Feature activation-2.15e+00

Pos logit contributions
igator+0.105
 Amen+0.087
boat+0.086
ull+0.079
eway+0.079
Neg logit contributions
 fault-0.108
 loses-0.099
joy-0.098
udd-0.095
 blood-0.094
Token again
Token ID757
Feature activation-8.78e+00

Pos logit contributions
udd+0.238
 fault+0.235
 loses+0.231
ooming+0.226
 underwear+0.225
Neg logit contributions
igator-0.147
 Joey-0.113
boat-0.113
 Mill-0.112
ull-0.111
Token and
Token ID290
Feature activation-3.16e-01

Pos logit contributions
 fault+0.871
 loses+0.808
joy+0.787
udd+0.768
 underwear+0.766
Neg logit contributions
igator-0.847
 Amen-0.695
boat-0.694
eway-0.645
ull-0.643
Token again
Token ID757
Feature activation-8.78e+00

Pos logit contributions
 fault+0.032
udd+0.029
joy+0.027
 underwear+0.027
ooming+0.027
Neg logit contributions
igator-0.031
boat-0.026
 Joey-0.025
 Mill-0.025
ull-0.023
Token,
Token ID11
Feature activation+4.86e-01

Pos logit contributions
 fault+0.952
 loses+0.880
joy+0.857
udd+0.850
 blood+0.839
Neg logit contributions
igator-0.770
boat-0.628
 Amen-0.612
ull-0.573
 Mill-0.571
Token but
Token ID475
Feature activation-8.28e-01

Pos logit contributions
igator+0.042
boat+0.034
 Mill+0.032
 Joey+0.031
eway+0.030
Neg logit contributions
 fault-0.051
udd-0.048
 loses-0.047
ooming-0.046
 underwear-0.046
Token he
Token ID339
Feature activation-9.91e-01

Pos logit contributions
 fault+0.082
 loses+0.077
joy+0.075
 blood+0.073
 underwear+0.072
Neg logit contributions
igator-0.080
 Amen-0.068
boat-0.065
eway-0.061
ull-0.060
Token just
Token ID655
Feature activation-1.85e+00

Pos logit contributions
 fault+0.113
joy+0.104
udd+0.101
ooming+0.101
 loses+0.100
Neg logit contributions
igator-0.083
boat-0.066
ull-0.062
man-0.056
 type-0.056
Token couldn
Token ID3521
Feature activation-7.44e-02

Pos logit contributions
 fault+0.198
 loses+0.181
joy+0.180
udd+0.176
ooming+0.176
Neg logit contributions
igator-0.168
boat-0.134
 Amen-0.129
ull-0.123
 Mill-0.121
TokenThe
Token ID464
Feature activation+5.14e-02

Pos logit contributions
 loses+0.104
udd+0.101
ooming+0.095
joy+0.093
 blood+0.091
Neg logit contributions
igator-0.191
 Amen-0.167
works-0.163
ull-0.163
boat-0.159
Token stranger
Token ID16195
Feature activation+8.82e-01

Pos logit contributions
igator+0.005
 Amen+0.004
boat+0.004
igators+0.003
 particular+0.003
Neg logit contributions
 fault-0.006
 loses-0.005
udd-0.005
joy-0.005
 underwear-0.005
Token looked
Token ID3114
Feature activation+1.35e+00

Pos logit contributions
igator+0.081
 Amen+0.068
boat+0.066
eway+0.061
ull+0.061
Neg logit contributions
 fault-0.091
 loses-0.085
joy-0.083
 blood-0.081
udd-0.080
Token at
Token ID379
Feature activation-3.33e+00

Pos logit contributions
igator+0.149
 Amen+0.126
boat+0.123
 Mill+0.114
ull+0.114
Neg logit contributions
 fault-0.118
 loses-0.107
joy-0.102
 blood-0.100
ooming-0.100
Token the
Token ID262
Feature activation+8.59e-02

Pos logit contributions
 fault+0.379
 loses+0.361
joy+0.345
ooming+0.341
udd+0.341
Neg logit contributions
igator-0.281
 Amen-0.218
boat-0.218
 Mill-0.200
ull-0.198
Token nap
Token ID25422
Feature activation-7.06e+00

Pos logit contributions
igator+0.006
 Amen+0.004
boat+0.004
 sound+0.003
 particular+0.003
Neg logit contributions
 fault-0.011
ooming-0.011
 loses-0.011
okes-0.010
udd-0.010
Tokenkin
Token ID5116
Feature activation+5.12e+00

Pos logit contributions
 fault+0.922
 loses+0.876
joy+0.857
 blood+0.840
udd+0.837
Neg logit contributions
igator-0.461
 Amen-0.352
boat-0.336
eway-0.296
ull-0.294
Token and
Token ID290
Feature activation-6.65e-01

Pos logit contributions
igator+0.506
boat+0.418
 Amen+0.413
eway+0.384
ull+0.384
Neg logit contributions
 fault-0.496
 loses-0.461
joy-0.449
udd-0.435
 blood-0.433
Token said
Token ID531
Feature activation+7.46e-01

Pos logit contributions
 fault+0.070
 loses+0.064
joy+0.063
udd+0.061
ooming+0.061
Neg logit contributions
igator-0.061
 Amen-0.050
boat-0.049
 Mill-0.045
ull-0.045
Token,
Token ID11
Feature activation+2.41e-02

Pos logit contributions
igator+0.076
boat+0.065
 Amen+0.064
eway+0.061
igators+0.060
Neg logit contributions
 fault-0.068
 loses-0.064
joy-0.064
 blood-0.060
ooming-0.059
Token "
Token ID366
Feature activation+7.34e-01

Pos logit contributions
igator+0.003
boat+0.002
 Amen+0.002
igators+0.002
eway+0.002
Neg logit contributions
 fault-0.002
joy-0.002
 loses-0.002
 blood-0.002
der-0.002
Token finding
Token ID4917
Feature activation+3.96e-01

Pos logit contributions
 fault+0.046
 loses+0.042
joy+0.041
 blood+0.040
udd+0.040
Neg logit contributions
igator-0.051
 Amen-0.043
boat-0.042
eway-0.039
ull-0.039
Token each
Token ID1123
Feature activation-2.22e+00

Pos logit contributions
igator+0.034
 sorts+0.029
 Mill+0.027
eway+0.027
igators+0.027
Neg logit contributions
 fault-0.041
 loses-0.038
ooming-0.038
 injuries-0.037
 elbow-0.037
Token other
Token ID584
Feature activation-3.18e+00

Pos logit contributions
 fault+0.200
 loses+0.180
joy+0.179
udd+0.178
ooming+0.175
Neg logit contributions
igator-0.244
boat-0.197
igators-0.190
 particular-0.188
eway-0.188
Token.
Token ID13
Feature activation-3.37e-01

Pos logit contributions
 fault+0.327
joy+0.305
 blood+0.302
 loses+0.301
ooming+0.298
Neg logit contributions
igator-0.293
boat-0.230
igators-0.222
eway-0.221
 Amen-0.213
Token Z
Token ID1168
Feature activation-1.09e+00

Pos logit contributions
 fault+0.041
 loses+0.039
joy+0.038
 blood+0.037
udd+0.037
Neg logit contributions
igator-0.025
 Amen-0.020
boat-0.019
eway-0.017
ull-0.017
Tokenara
Token ID3301
Feature activation-6.33e+00

Pos logit contributions
 fault+0.083
 injuries+0.073
 blood+0.072
 loses+0.070
 elbow+0.069
Neg logit contributions
igator-0.123
boat-0.109
ull-0.109
 particular-0.104
ot-0.102
Token was
Token ID373
Feature activation+4.58e-01

Pos logit contributions
 fault+0.689
joy+0.636
 blood+0.621
 injuries+0.609
 loses+0.608
Neg logit contributions
igator-0.542
boat-0.430
 Amen-0.413
ull-0.400
man-0.396
Token very
Token ID845
Feature activation+2.69e+00

Pos logit contributions
igator+0.036
 Amen+0.029
boat+0.028
ull+0.025
eway+0.025
Neg logit contributions
 fault-0.053
 loses-0.050
joy-0.049
udd-0.049
 blood-0.048
Token good
Token ID922
Feature activation-2.35e+00

Pos logit contributions
igator+0.286
 Amen+0.255
boat+0.246
eway+0.234
ull+0.227
Neg logit contributions
 fault-0.232
 loses-0.229
joy-0.214
udd-0.207
 underwear-0.204
Token at
Token ID379
Feature activation-3.20e+00

Pos logit contributions
 fault+0.252
 blood+0.241
 injuries+0.237
 elbow+0.231
 loses+0.227
Neg logit contributions
igator-0.157
boat-0.126
man-0.123
 called-0.123
ull-0.119
Token the
Token ID262
Feature activation+1.61e-01

Pos logit contributions
 fault+0.289
udd+0.271
 loses+0.270
 underwear+0.256
joy+0.255
Neg logit contributions
igator-0.330
 Amen-0.273
boat-0.264
eway-0.264
 Mill-0.256
Token time
Token ID640
Feature activation-1.25e-02

Pos logit contributions
igator+0.031
 Amen+0.025
 particular+0.024
 type+0.022
boat+0.021
Neg logit contributions
 fault-0.050
 loses-0.049
 blood-0.047
 underwear-0.047
ooming-0.046
Token,
Token ID11
Feature activation+4.53e-01

Pos logit contributions
 fault+0.001
 loses+0.001
joy+0.001
 blood+0.001
udd+0.001
Neg logit contributions
igator-0.001
 Amen-0.001
boat-0.001
eway-0.001
ull-0.001
Token there
Token ID612
Feature activation+1.15e+00

Pos logit contributions
igator+0.049
 Amen+0.044
boat+0.044
works+0.039
eway+0.039
Neg logit contributions
 fault-0.035
 loses-0.033
joy-0.033
 blood-0.032
ooming-0.031
Token was
Token ID373
Feature activation+7.00e-01

Pos logit contributions
igator+0.102
 Amen+0.085
boat+0.082
eway+0.075
ull+0.074
Neg logit contributions
 fault-0.123
 loses-0.116
joy-0.113
 blood-0.110
udd-0.109
Token a
Token ID257
Feature activation+4.38e-01

Pos logit contributions
igator+0.063
 Amen+0.053
boat+0.050
ull+0.048
eway+0.047
Neg logit contributions
 fault-0.074
 loses-0.070
joy-0.067
udd-0.066
ooming-0.066
Token fle
Token ID5104
Feature activation-6.56e+00

Pos logit contributions
igator+0.043
 Amen+0.036
boat+0.035
eway+0.032
ull+0.032
Neg logit contributions
 fault-0.043
 loses-0.040
joy-0.039
 blood-0.038
udd-0.038
Tokena
Token ID64
Feature activation+2.50e+00

Pos logit contributions
 fault+0.656
 loses+0.615
joy+0.596
 blood+0.582
udd+0.581
Neg logit contributions
igator-0.625
 Amen-0.525
boat-0.508
eway-0.472
ull-0.467
Token called
Token ID1444
Feature activation+6.97e+00

Pos logit contributions
igator+0.199
 Amen+0.164
boat+0.156
eway+0.151
igators+0.144
Neg logit contributions
 fault-0.276
 loses-0.268
udd-0.261
joy-0.259
 blood-0.255
Token Ho
Token ID9544
Feature activation-3.32e+00

Pos logit contributions
igator+0.794
 Amen+0.687
boat+0.673
eway+0.633
ull+0.630
Neg logit contributions
 fault-0.570
 loses-0.524
joy-0.508
 blood-0.490
 underwear-0.484
Tokenppy
Token ID14097
Feature activation-4.82e-01

Pos logit contributions
 fault+0.318
 loses+0.302
 blood+0.295
joy+0.289
 underwear+0.277
Neg logit contributions
igator-0.307
boat-0.269
 Amen-0.266
ull-0.256
man-0.246
Token.
Token ID13
Feature activation-1.04e-01

Pos logit contributions
 fault+0.040
joy+0.036
 loses+0.035
udd+0.035
 blood+0.034
Neg logit contributions
igator-0.053
 Amen-0.047
boat-0.045
eway-0.042
igators-0.042
Token.
Token ID13
Feature activation-1.40e-01

Pos logit contributions
 fault+0.072
joy+0.068
 loses+0.067
ooming+0.064
 underwear+0.064
Neg logit contributions
igator-0.053
 Amen-0.043
boat-0.040
ull-0.039
 Mill-0.038
Token But
Token ID887
Feature activation+8.31e-01

Pos logit contributions
 fault+0.014
 loses+0.013
joy+0.012
 blood+0.012
udd+0.012
Neg logit contributions
igator-0.014
boat-0.012
eway-0.011
ull-0.011
 Amen-0.011
Token sorry
Token ID7926
Feature activation-5.94e-01

Pos logit contributions
igator+0.082
 Amen+0.069
boat+0.068
eway+0.063
ull+0.063
Neg logit contributions
 fault-0.081
 loses-0.075
joy-0.073
 blood-0.072
 underwear-0.070
Token is
Token ID318
Feature activation-7.28e-01

Pos logit contributions
 fault+0.065
joy+0.061
 loses+0.060
ooming+0.058
 blood+0.058
Neg logit contributions
igator-0.051
 Amen-0.041
boat-0.040
ull-0.037
eway-0.037
Token not
Token ID407
Feature activation+1.70e+00

Pos logit contributions
 fault+0.073
 loses+0.069
joy+0.067
udd+0.065
 blood+0.065
Neg logit contributions
igator-0.070
 Amen-0.059
boat-0.057
eway-0.053
ull-0.053
Token enough
Token ID1576
Feature activation-6.69e+00

Pos logit contributions
igator+0.154
 Amen+0.123
boat+0.120
ull+0.113
igators+0.111
Neg logit contributions
 fault-0.174
 loses-0.166
joy-0.163
ooming-0.161
udd-0.160
Token.
Token ID13
Feature activation-1.34e-01

Pos logit contributions
 fault+0.656
 loses+0.614
joy+0.595
 blood+0.578
udd+0.577
Neg logit contributions
igator-0.653
 Amen-0.548
boat-0.533
eway-0.496
ull-0.494
Token You
Token ID921
Feature activation+1.38e+00

Pos logit contributions
 fault+0.013
 loses+0.012
joy+0.011
 blood+0.011
udd+0.011
Neg logit contributions
igator-0.014
boat-0.012
 Amen-0.011
eway-0.011
ull-0.011
Token need
Token ID761
Feature activation+1.70e+00

Pos logit contributions
igator+0.126
 Amen+0.100
boat+0.098
igators+0.091
ull+0.089
Neg logit contributions
 fault-0.146
joy-0.141
 loses-0.133
ooming-0.131
udd-0.130
Token to
Token ID284
Feature activation-7.54e-03

Pos logit contributions
igator+0.158
 Amen+0.129
boat+0.126
ull+0.118
 Mill+0.117
Neg logit contributions
 fault-0.171
 loses-0.162
joy-0.159
ooming-0.155
udd-0.155
Token make
Token ID787
Feature activation+1.23e+00

Pos logit contributions
 fault+0.001
 loses+0.001
 blood+0.001
 underwear+0.001
 injuries+0.001
Neg logit contributions
igator-0.001
 Amen-0.001
boat-0.001
eway-0.001
ull-0.001