TOP ACTIVATIONS
MAX = 5.486

com / watch ? v = 2 g 7 p k
00 65 E & for = count y : * &
). This b odes well for pulse j ets
These frustrated p oth oles tweet complaints straight to the
one could puzzle a bit over which form of lying is
to remember with an a ching need that has her sob
. 2 . [ color = red ][ b ] U
cohort of patients ( n = 91 ) only received trans
A lot of public domain works are also available on
Irvine , California . Hide Caption 9 of 15 Photos :
Pasadena , California . Hide Caption 12 of 15 Photos :
20 , 2015 . Hide Caption 8 of 15 Photos :
: " I Can Think Of No Reason Why In A
Are there more p oth oles in New Jersey than other
25 26 27 # loop over the input image paths for
? Dark horse Profile Blog Joined December 2011 United
, motor ized wheelchair ( Figure 2 A , [ Action
questions gay girls still get asked MORE : Restaurant
Pasadena , California . Hide Caption 11 of 15 Photos :
Hills , California . Hide Caption 14 of 15 Photos :

MIN ACTIVATIONS
MIN = -3.048

high court s door expressing concern over the growing
remaining minutes were unable to break the dead lock and the
, shit , piss , brush teeth and hair , and
in 2002 , his net worth was estimated at $ 850
, Hulu , and Amazon Prime among others .
J arl never thought he 'd be a hockey dad when
beneficial outcome would be a draw . In the case of
presidential election ( or , heck , any political event of
speed pulse jet engine suddenly starts making a lot
to get out . Either way , Kam al had spent
as well , but was drawn to the speed and physical
cultural issues . Update : The Hill reports ,
all . ( UPDATE : Sherman suffered a rupt
remarks he made about his fellow GOP presidential contender in a
Hulu Plus , and Amazon Prime offer much of the same
be able to get green cards for their spouses and minor
to - female ( M TF ) transgender people are born
that Tal ent hits a target no one else
at 2 : 21 ? Depending on where the diss ents
. Then the groups were drawn , and it got way

INTERVAL 3.353 - 5.486
CONTAINS 0.002%

INTERVAL 1.219 - 3.353
CONTAINS 0.571%

who played behind Hall on Wednesday , didn t
their final game against Saudi Arabia . If that
President Men em ( 1989 99 ) turned to a
One photo shows Be b op and Rock stead y
: [/ b ] 00 : 47 : 03 , 78

INTERVAL -0.915 - 1.219
CONTAINS 97.102%

be taken and that such adjud ication can be acceptable in
the past four decades to estimate the lake s
old . More about this story After
around arbitrarily ; the separation wall cuts people off , and
understands our unique campus culture as opposed to a national [

INTERVAL -3.048 - -0.915
CONTAINS 2.324%

and Inner Mongolia , the Mong ols also use clan names
their client . Asked why she thought the prosecutors
Engineering office . If a homeowner s
Kernel cannot correctly mount it , it will panic and reboot
L anda says , ' We don 't have any
Tokencom
Token ID785
Feature activation+1.90e-01

Pos logit contributions
�醒+0.389
olit+0.330
ult+0.330
sted+0.325
adr+0.309
Neg logit contributions
DX-0.481
 Fathers-0.473
 resolves-0.470
 DX-0.470
 cow-0.464
Token/
Token ID14
Feature activation+7.00e-01

Pos logit contributions
�醒+0.190
ult+0.171
olit+0.171
sted+0.169
adr+0.164
Neg logit contributions
DX-0.083
 Fathers-0.081
 resolves-0.080
 DX-0.080
 cow-0.078
Tokenwatch
Token ID8340
Feature activation-3.14e-01

Pos logit contributions
�醒+0.552
olit+0.486
ult+0.484
sted+0.480
adr+0.461
Neg logit contributions
DX-0.451
 Fathers-0.435
 DX-0.433
 resolves-0.433
 cow-0.428
Token?
Token ID30
Feature activation+3.99e-01

Pos logit contributions
DX+0.211
 Fathers+0.207
 resolves+0.206
 DX+0.206
 cow+0.203
Neg logit contributions
�醒-0.238
olit-0.208
ult-0.208
sted-0.206
adr-0.197
Tokenv
Token ID85
Feature activation+1.80e-02

Pos logit contributions
�醒+0.306
olit+0.266
ult+0.260
sted+0.260
adr+0.250
Neg logit contributions
DX-0.268
 resolves-0.262
 DX-0.260
 Fathers-0.259
 cow-0.259
Token=
Token ID28
Feature activation+3.34e+00

Pos logit contributions
�醒+0.014
olit+0.012
sted+0.012
ult+0.012
adr+0.011
Neg logit contributions
DX-0.012
 Fathers-0.011
 resolves-0.011
 DX-0.011
 cow-0.011
Token2
Token ID17
Feature activation-5.49e-02

Pos logit contributions
�醒+2.639
ult+2.371
olit+2.371
sted+2.355
adr+2.251
Neg logit contributions
DX-2.102
 Fathers-2.051
 resolves-2.043
 DX-2.035
 cow-2.003
Tokeng
Token ID70
Feature activation+8.04e-02

Pos logit contributions
DX+0.036
 DX+0.034
 Fathers+0.033
 resolves+0.033
 cow+0.033
Neg logit contributions
�醒-0.044
olit-0.038
sted-0.038
ult-0.038
adr-0.036
Token7
Token ID22
Feature activation+6.10e-02

Pos logit contributions
�醒+0.066
olit+0.058
sted+0.057
ult+0.057
adr+0.054
Neg logit contributions
DX-0.051
 DX-0.048
 Fathers-0.048
 resolves-0.048
 cow-0.047
Tokenp
Token ID79
Feature activation-4.01e-02

Pos logit contributions
�醒+0.049
olit+0.043
sted+0.043
ult+0.043
adr+0.041
Neg logit contributions
DX-0.039
 DX-0.037
 Fathers-0.037
 resolves-0.037
 cow-0.036
Tokenk
Token ID74
Feature activation+5.26e-01

Pos logit contributions
DX+0.025
 DX+0.024
 Fathers+0.024
 resolves+0.024
 cow+0.023
Neg logit contributions
�醒-0.033
olit-0.029
sted-0.029
ult-0.028
adr-0.027
Token00
Token ID405
Feature activation-3.68e-01

Pos logit contributions
DX+0.327
 resolves+0.313
 DX+0.312
 Fathers+0.308
 cow+0.304
Neg logit contributions
�醒-0.446
olit-0.402
ult-0.399
sted-0.396
adr-0.381
Token65
Token ID2996
Feature activation-7.28e-01

Pos logit contributions
DX+0.310
 Fathers+0.300
 DX+0.300
 resolves+0.297
 cow+0.290
Neg logit contributions
�醒-0.220
olit-0.185
ult-0.183
sted-0.183
adr-0.172
TokenE
Token ID36
Feature activation+1.68e-01

Pos logit contributions
DX+0.284
 Fathers+0.275
 resolves+0.273
 DX+0.271
 cow+0.264
Neg logit contributions
�醒-0.746
ult-0.690
olit-0.689
sted-0.686
adr-0.663
Token&
Token ID5
Feature activation-2.42e-01

Pos logit contributions
�醒+0.155
olit+0.142
ult+0.142
sted+0.141
adr+0.136
Neg logit contributions
DX-0.082
 Fathers-0.080
 DX-0.080
 resolves-0.080
 cow-0.078
Tokenfor
Token ID1640
Feature activation+3.93e-01

Pos logit contributions
DX+0.163
 DX+0.157
 resolves+0.156
 Fathers+0.154
 cow+0.152
Neg logit contributions
�醒-0.184
olit-0.164
sted-0.162
ult-0.161
adr-0.153
Token=
Token ID28
Feature activation+2.99e+00

Pos logit contributions
�醒+0.308
olit+0.278
sted+0.273
ult+0.272
adr+0.259
Neg logit contributions
DX-0.254
 DX-0.246
 Fathers-0.244
 resolves-0.244
 cow-0.241
Tokencount
Token ID9127
Feature activation-2.41e-01

Pos logit contributions
�醒+2.355
ult+2.127
olit+2.123
sted+2.110
adr+2.019
Neg logit contributions
DX-1.871
 Fathers-1.838
 resolves-1.830
 DX-1.818
 cow-1.793
Tokeny
Token ID88
Feature activation-7.54e-01

Pos logit contributions
DX+0.132
 Fathers+0.128
 resolves+0.127
 DX+0.127
 cow+0.124
Neg logit contributions
�醒-0.212
ult-0.192
olit-0.192
sted-0.190
adr-0.182
Token:
Token ID25
Feature activation-1.50e-01

Pos logit contributions
DX+0.414
 DX+0.400
 resolves+0.398
 Fathers+0.398
 cow+0.388
Neg logit contributions
�醒-0.663
olit-0.603
ult-0.595
sted-0.593
adr-0.569
Token*
Token ID9
Feature activation-2.82e-01

Pos logit contributions
DX+0.101
 DX+0.096
 resolves+0.096
 Fathers+0.095
 cow+0.094
Neg logit contributions
�醒-0.115
olit-0.103
ult-0.101
sted-0.101
adr-0.096
Token&
Token ID5
Feature activation+1.63e-01

Pos logit contributions
DX+0.164
 DX+0.158
 resolves+0.158
 Fathers+0.157
 cow+0.154
Neg logit contributions
�醒-0.239
olit-0.217
ult-0.215
sted-0.214
adr-0.205
Token).
Token ID737
Feature activation-4.21e-01

Pos logit contributions
�醒+0.785
olit+0.716
ult+0.715
sted+0.710
adr+0.685
Neg logit contributions
DX-0.387
 Fathers-0.378
 resolves-0.378
 DX-0.377
 cow-0.369
Token
Token ID198
Feature activation+5.97e-01

Pos logit contributions
DX+0.272
 Fathers+0.269
 DX+0.268
 resolves+0.262
 cow+0.257
Neg logit contributions
�醒-0.333
olit-0.297
ult-0.293
sted-0.291
adr-0.278
Token
Token ID198
Feature activation+1.80e-01

Pos logit contributions
�醒+0.449
olit+0.400
ult+0.399
sted+0.396
adr+0.378
Neg logit contributions
DX-0.399
 Fathers-0.392
 resolves-0.390
 DX-0.388
 cow-0.382
TokenThis
Token ID1212
Feature activation+1.31e-01

Pos logit contributions
�醒+0.142
olit+0.125
sted+0.123
ult+0.122
adr+0.117
Neg logit contributions
DX-0.120
 DX-0.113
 Fathers-0.113
 resolves-0.112
 cow-0.109
Token b
Token ID275
Feature activation+5.61e-01

Pos logit contributions
�醒+0.106
olit+0.095
ult+0.094
sted+0.093
adr+0.089
Neg logit contributions
DX-0.081
 resolves-0.081
 DX-0.080
 Fathers-0.080
 cow-0.078
Tokenodes
Token ID4147
Feature activation+2.78e+00

Pos logit contributions
�醒+0.338
olit+0.281
sted+0.279
ult+0.275
adr+0.259
Neg logit contributions
DX-0.464
 resolves-0.460
 Fathers-0.457
 DX-0.453
 cow-0.447
Token well
Token ID880
Feature activation+5.90e-01

Pos logit contributions
�醒+2.434
ult+2.209
olit+2.208
sted+2.197
adr+2.113
Neg logit contributions
DX-1.502
 Fathers-1.468
 resolves-1.462
 DX-1.454
 cow-1.431
Token for
Token ID329
Feature activation+2.97e-01

Pos logit contributions
�醒+0.592
ult+0.538
olit+0.537
sted+0.536
adr+0.519
Neg logit contributions
DX-0.248
 resolves-0.244
 DX-0.242
 Fathers-0.241
 cow-0.236
Token pulse
Token ID19445
Feature activation+1.72e-01

Pos logit contributions
�醒+0.268
olit+0.243
ult+0.240
sted+0.240
adr+0.231
Neg logit contributions
DX-0.157
 DX-0.155
 resolves-0.154
 Fathers-0.153
 cow-0.151
Tokenj
Token ID73
Feature activation-5.85e-01

Pos logit contributions
�醒+0.147
olit+0.131
ult+0.130
sted+0.129
adr+0.125
Neg logit contributions
DX-0.099
 DX-0.097
 resolves-0.097
 cow-0.096
 Fathers-0.096
Tokenets
Token ID1039
Feature activation-1.56e-01

Pos logit contributions
DX+0.364
 Fathers+0.355
 resolves+0.354
 DX+0.354
 cow+0.348
Neg logit contributions
�醒-0.473
olit-0.416
sted-0.415
ult-0.414
adr-0.397
Token
Token ID198
Feature activation+1.49e-01

Pos logit contributions
�醒+0.462
olit+0.412
ult+0.411
sted+0.408
adr+0.389
Neg logit contributions
DX-0.415
 Fathers-0.408
 resolves-0.406
 DX-0.404
 cow-0.398
TokenThese
Token ID4711
Feature activation+9.46e-01

Pos logit contributions
�醒+0.118
olit+0.105
sted+0.104
ult+0.103
adr+0.099
Neg logit contributions
DX-0.097
 Fathers-0.092
 DX-0.092
 resolves-0.091
 cow-0.090
Token frustrated
Token ID14718
Feature activation+2.49e-01

Pos logit contributions
�醒+0.839
olit+0.751
ult+0.746
sted+0.746
adr+0.720
Neg logit contributions
DX-0.513
 Fathers-0.508
 DX-0.503
 resolves-0.501
 cow-0.497
Token p
Token ID279
Feature activation+9.27e-02

Pos logit contributions
�醒+0.220
olit+0.197
ult+0.196
sted+0.195
adr+0.189
Neg logit contributions
 Fathers-0.136
DX-0.135
 DX-0.134
 cow-0.134
 resolves-0.133
Tokenoth
Token ID849
Feature activation-2.03e-01

Pos logit contributions
�醒+0.078
sted+0.068
ult+0.068
olit+0.068
adr+0.066
Neg logit contributions
DX-0.054
 Fathers-0.054
 resolves-0.053
 DX-0.052
 cow-0.052
Tokenoles
Token ID4316
Feature activation+2.68e+00

Pos logit contributions
DX+0.071
 Fathers+0.070
 resolves+0.069
 DX+0.068
 cow+0.066
Neg logit contributions
�醒-0.216
sted-0.196
ult-0.196
olit-0.193
adr-0.190
Token tweet
Token ID6126
Feature activation+3.16e-01

Pos logit contributions
�醒+2.190
olit+1.966
ult+1.965
sted+1.953
adr+1.875
Neg logit contributions
DX-1.609
 Fathers-1.583
 resolves-1.580
 DX-1.570
 cow-1.550
Token complaints
Token ID9687
Feature activation+2.92e-01

Pos logit contributions
�醒+0.278
olit+0.252
ult+0.250
sted+0.249
adr+0.242
Neg logit contributions
DX-0.169
 Fathers-0.168
 resolves-0.168
 DX-0.167
 cow-0.166
Token straight
Token ID3892
Feature activation+4.44e-01

Pos logit contributions
�醒+0.268
olit+0.243
ult+0.241
sted+0.240
adr+0.233
Neg logit contributions
DX-0.148
 Fathers-0.146
 resolves-0.146
 DX-0.145
 cow-0.143
Token to
Token ID284
Feature activation-2.48e-01

Pos logit contributions
�醒+0.429
olit+0.393
ult+0.391
sted+0.390
adr+0.378
Neg logit contributions
DX-0.200
 resolves-0.196
 Fathers-0.195
 DX-0.194
 cow-0.192
Token the
Token ID262
Feature activation-6.83e-02

Pos logit contributions
 Fathers+0.146
 DX+0.146
 cow+0.145
DX+0.145
 resolves+0.145
Neg logit contributions
�醒-0.208
olit-0.185
ult-0.184
sted-0.180
adr-0.176
Token one
Token ID530
Feature activation+2.57e-01

Pos logit contributions
DX+0.040
 Fathers+0.040
 DX+0.039
 resolves+0.039
 cow+0.039
Neg logit contributions
�醒-0.066
olit-0.059
ult-0.059
sted-0.059
adr-0.057
Token could
Token ID714
Feature activation-1.40e-01

Pos logit contributions
�醒+0.194
ult+0.171
olit+0.171
sted+0.170
adr+0.162
Neg logit contributions
DX-0.173
 resolves-0.172
 Fathers-0.172
 DX-0.170
 cow-0.168
Token puzzle
Token ID15027
Feature activation-5.53e-01

Pos logit contributions
DX+0.085
 resolves+0.085
 Fathers+0.084
 cow+0.084
 DX+0.083
Neg logit contributions
�醒-0.114
sted-0.101
ult-0.101
olit-0.101
adr-0.097
Token a
Token ID257
Feature activation-1.78e-02

Pos logit contributions
 Fathers+0.286
DX+0.285
 resolves+0.282
 DX+0.282
 cow+0.280
Neg logit contributions
�醒-0.505
ult-0.453
olit-0.452
sted-0.449
adr-0.437
Token bit
Token ID1643
Feature activation+5.11e-01

Pos logit contributions
DX+0.011
 cow+0.010
 Fathers+0.010
 DX+0.010
 resolves+0.010
Neg logit contributions
�醒-0.015
ult-0.013
olit-0.013
sted-0.013
adr-0.013
Token over
Token ID625
Feature activation+2.62e+00

Pos logit contributions
�醒+0.460
ult+0.413
olit+0.412
sted+0.411
adr+0.397
Neg logit contributions
DX-0.270
 Fathers-0.266
 resolves-0.265
 DX-0.265
 cow-0.261
Token which
Token ID543
Feature activation+2.94e-01

Pos logit contributions
�醒+2.181
ult+1.989
olit+1.986
sted+1.974
adr+1.894
Neg logit contributions
DX-1.511
 Fathers-1.472
 resolves-1.468
 DX-1.456
 cow-1.432
Token form
Token ID1296
Feature activation-1.17e+00

Pos logit contributions
�醒+0.245
olit+0.219
ult+0.219
sted+0.218
adr+0.208
Neg logit contributions
DX-0.174
 Fathers-0.173
 resolves-0.173
 DX-0.172
 cow-0.171
Token of
Token ID286
Feature activation-2.26e-01

Pos logit contributions
 Fathers+0.568
DX+0.561
 resolves+0.560
 DX+0.559
 cow+0.551
Neg logit contributions
�醒-1.106
sted-0.986
olit-0.980
ult-0.972
adr-0.944
Token lying
Token ID9105
Feature activation+3.10e-01

Pos logit contributions
 Fathers+0.130
DX+0.130
 cow+0.130
 DX+0.130
 resolves+0.129
Neg logit contributions
�醒-0.192
olit-0.171
ult-0.170
sted-0.169
adr-0.162
Token is
Token ID318
Feature activation+6.87e-01

Pos logit contributions
�醒+0.240
olit+0.210
ult+0.210
sted+0.209
adr+0.200
Neg logit contributions
DX-0.204
 Fathers-0.203
 resolves-0.202
 DX-0.201
 cow-0.199
Token to
Token ID284
Feature activation+4.42e-01

Pos logit contributions
�醒+1.011
ult+0.918
olit+0.917
sted+0.911
adr+0.886
Neg logit contributions
DX-0.490
 Fathers-0.485
 resolves-0.482
 DX-0.476
 cow-0.471
Token remember
Token ID3505
Feature activation+5.45e-01

Pos logit contributions
�醒+0.345
olit+0.302
ult+0.302
sted+0.301
adr+0.288
Neg logit contributions
DX-0.286
 resolves-0.284
 Fathers-0.284
 cow-0.282
 DX-0.281
Token with
Token ID351
Feature activation+3.68e-01

Pos logit contributions
�醒+0.491
olit+0.445
ult+0.444
sted+0.440
adr+0.426
Neg logit contributions
DX-0.283
 Fathers-0.279
 resolves-0.278
 DX-0.276
 cow-0.272
Token an
Token ID281
Feature activation+6.15e-01

Pos logit contributions
�醒+0.306
olit+0.273
ult+0.270
sted+0.269
adr+0.260
Neg logit contributions
DX-0.218
 Fathers-0.217
 resolves-0.217
 DX-0.215
 cow-0.214
Token a
Token ID257
Feature activation-3.46e-01

Pos logit contributions
�醒+0.528
sted+0.473
olit+0.471
ult+0.469
adr+0.451
Neg logit contributions
DX-0.347
 resolves-0.343
 Fathers-0.337
 DX-0.337
 cow-0.333
Tokenching
Token ID10813
Feature activation+2.52e+00

Pos logit contributions
DX+0.228
 cow+0.224
 resolves+0.224
 Fathers+0.222
 DX+0.221
Neg logit contributions
�醒-0.263
olit-0.231
sted-0.229
ult-0.228
adr-0.217
Token need
Token ID761
Feature activation+5.52e-01

Pos logit contributions
�醒+2.099
ult+1.897
olit+1.894
sted+1.882
adr+1.806
Neg logit contributions
DX-1.477
 resolves-1.449
 Fathers-1.448
 DX-1.438
 cow-1.425
Token that
Token ID326
Feature activation+6.69e-01

Pos logit contributions
�醒+0.536
ult+0.491
olit+0.490
sted+0.488
adr+0.476
Neg logit contributions
 Fathers-0.240
DX-0.240
 resolves-0.240
 DX-0.236
 cow-0.234
Token has
Token ID468
Feature activation+5.62e-01

Pos logit contributions
�醒+0.566
olit+0.508
sted+0.502
ult+0.501
adr+0.484
Neg logit contributions
 resolves-0.391
DX-0.385
 Fathers-0.385
 cow-0.380
 DX-0.380
Token her
Token ID607
Feature activation-2.36e-01

Pos logit contributions
�醒+0.473
olit+0.423
ult+0.422
sted+0.418
adr+0.403
Neg logit contributions
DX-0.325
 resolves-0.324
 Fathers-0.322
 DX-0.320
 cow-0.319
Token sob
Token ID27355
Feature activation-3.92e-01

Pos logit contributions
 Fathers+0.132
 resolves+0.132
DX+0.131
 cow+0.131
 DX+0.130
Neg logit contributions
�醒-0.206
ult-0.183
olit-0.182
sted-0.181
adr-0.174
Token.
Token ID13
Feature activation-2.04e-01

Pos logit contributions
DX+0.016
 resolves+0.016
 DX+0.016
 Fathers+0.016
 cow+0.015
Neg logit contributions
�醒-0.032
olit-0.028
ult-0.028
sted-0.028
adr-0.027
Token 2
Token ID362
Feature activation+1.20e-02

Pos logit contributions
DX+0.128
 DX+0.125
 Fathers+0.123
 resolves+0.122
 cow+0.119
Neg logit contributions
�醒-0.168
olit-0.149
sted-0.148
ult-0.147
adr-0.141
Token.
Token ID13
Feature activation+4.36e-01

Pos logit contributions
�醒+0.012
olit+0.011
ult+0.011
sted+0.011
adr+0.010
Neg logit contributions
DX-0.005
 Fathers-0.005
 DX-0.005
 resolves-0.005
 cow-0.005
Token [
Token ID685
Feature activation+1.78e+00

Pos logit contributions
�醒+0.416
olit+0.380
sted+0.378
ult+0.376
adr+0.363
Neg logit contributions
DX-0.207
 DX-0.203
 Fathers-0.200
 resolves-0.198
 cow-0.195
Tokencolor
Token ID8043
Feature activation+1.38e+00

Pos logit contributions
�醒+1.387
olit+1.237
ult+1.233
sted+1.227
adr+1.173
Neg logit contributions
DX-1.151
 resolves-1.116
 Fathers-1.114
 DX-1.112
 cow-1.095
Token=
Token ID28
Feature activation+2.51e+00

Pos logit contributions
�醒+0.959
olit+0.841
ult+0.838
sted+0.833
adr+0.790
Neg logit contributions
DX-1.003
 Fathers-0.980
 resolves-0.979
 DX-0.976
 cow-0.962
Tokenred
Token ID445
Feature activation+3.98e-01

Pos logit contributions
�醒+1.755
olit+1.547
ult+1.537
sted+1.530
adr+1.454
Neg logit contributions
DX-1.817
 Fathers-1.774
 resolves-1.772
 DX-1.763
 cow-1.745
Token][
Token ID7131
Feature activation-2.40e-02

Pos logit contributions
�醒+0.405
olit+0.372
ult+0.372
sted+0.371
adr+0.358
Neg logit contributions
DX-0.160
 Fathers-0.154
 resolves-0.153
 DX-0.153
 cow-0.150
Tokenb
Token ID65
Feature activation-2.81e-01

Pos logit contributions
DX+0.018
 Fathers+0.018
 resolves+0.018
 DX+0.018
 cow+0.017
Neg logit contributions
�醒-0.016
olit-0.014
ult-0.014
sted-0.014
adr-0.013
Token]
Token ID60
Feature activation+3.07e-01

Pos logit contributions
DX+0.124
 Fathers+0.119
 DX+0.119
 resolves+0.118
 cow+0.115
Neg logit contributions
�醒-0.280
olit-0.253
ult-0.252
sted-0.251
adr-0.241
TokenU
Token ID52
Feature activation-4.55e-01

Pos logit contributions
�醒+0.246
olit+0.220
sted+0.218
ult+0.215
adr+0.208
Neg logit contributions
DX-0.197
 Fathers-0.187
 DX-0.187
 resolves-0.185
 cow-0.182
Token cohort
Token ID20812
Feature activation+2.81e-01

Pos logit contributions
�醒+0.127
olit+0.114
ult+0.113
sted+0.112
adr+0.108
Neg logit contributions
 DX-0.082
DX-0.082
 resolves-0.081
 Fathers-0.081
 cow-0.080
Token of
Token ID286
Feature activation+1.00e-01

Pos logit contributions
�醒+0.263
olit+0.232
sted+0.232
ult+0.232
adr+0.226
Neg logit contributions
 resolves-0.142
 DX-0.142
DX-0.140
 Fathers-0.139
 cow-0.137
Token patients
Token ID3871
Feature activation+3.01e-01

Pos logit contributions
�醒+0.087
olit+0.077
ult+0.077
sted+0.076
adr+0.074
Neg logit contributions
DX-0.057
 DX-0.057
 Fathers-0.057
 resolves-0.056
 cow-0.055
Token (
Token ID357
Feature activation+7.81e-01

Pos logit contributions
�醒+0.268
olit+0.238
ult+0.237
sted+0.237
adr+0.229
Neg logit contributions
 resolves-0.164
DX-0.163
 Fathers-0.162
 DX-0.161
 cow-0.158
Tokenn
Token ID77
Feature activation+3.90e-01

Pos logit contributions
�醒+0.570
olit+0.489
sted+0.484
ult+0.480
adr+0.461
Neg logit contributions
DX-0.564
 Fathers-0.541
 resolves-0.537
 DX-0.537
 cow-0.528
Token=
Token ID28
Feature activation+2.46e+00

Pos logit contributions
�醒+0.337
olit+0.296
sted+0.295
ult+0.294
adr+0.285
Neg logit contributions
DX-0.225
 Fathers-0.219
 DX-0.215
 resolves-0.214
 cow-0.213
Token91
Token ID6420
Feature activation+6.09e-01

Pos logit contributions
�醒+1.861
olit+1.642
ult+1.629
sted+1.619
adr+1.548
Neg logit contributions
DX-1.670
 Fathers-1.628
 resolves-1.616
 DX-1.611
 cow-1.588
Token)
Token ID8
Feature activation+6.53e-01

Pos logit contributions
�醒+0.586
ult+0.532
olit+0.531
sted+0.529
adr+0.512
Neg logit contributions
DX-0.283
 Fathers-0.276
 resolves-0.273
 DX-0.272
 cow-0.266
Token only
Token ID691
Feature activation-1.15e-01

Pos logit contributions
�醒+0.564
olit+0.500
ult+0.499
sted+0.498
adr+0.481
Neg logit contributions
 resolves-0.370
DX-0.370
 Fathers-0.368
 DX-0.365
 cow-0.359
Token received
Token ID2722
Feature activation-2.12e-01

Pos logit contributions
 resolves+0.058
 Fathers+0.058
DX+0.058
 DX+0.057
 cow+0.056
Neg logit contributions
�醒-0.108
olit-0.095
ult-0.095
sted-0.094
adr-0.092
Token trans
Token ID1007
Feature activation-2.54e-02

Pos logit contributions
DX+0.124
 DX+0.123
 Fathers+0.122
 resolves+0.122
 cow+0.121
Neg logit contributions
�醒-0.177
olit-0.159
ult-0.159
sted-0.158
adr-0.153
Token
Token ID198
Feature activation-8.31e-02

Pos logit contributions
�醒+0.133
olit+0.117
ult+0.116
sted+0.115
adr+0.110
Neg logit contributions
DX-0.110
 Fathers-0.108
 DX-0.107
 resolves-0.107
 cow-0.105
TokenA
Token ID32
Feature activation+7.29e-02

Pos logit contributions
DX+0.056
 Fathers+0.053
 DX+0.053
 resolves+0.052
 cow+0.052
Neg logit contributions
�醒-0.064
olit-0.056
sted-0.055
ult-0.055
adr-0.053
Token lot
Token ID1256
Feature activation+2.12e-01

Pos logit contributions
�醒+0.061
olit+0.055
ult+0.054
sted+0.054
adr+0.052
Neg logit contributions
DX-0.043
 Fathers-0.042
 DX-0.042
 cow-0.042
 resolves-0.041
Token of
Token ID286
Feature activation-6.54e-01

Pos logit contributions
�醒+0.193
ult+0.176
olit+0.176
sted+0.174
adr+0.169
Neg logit contributions
DX-0.107
 Fathers-0.106
 resolves-0.105
 DX-0.104
 cow-0.103
Token public
Token ID1171
Feature activation+3.97e-01

Pos logit contributions
 Fathers+0.325
DX+0.324
 DX+0.318
 cow+0.316
 resolves+0.315
Neg logit contributions
�醒-0.615
olit-0.553
ult-0.543
sted-0.539
adr-0.528
Token domain
Token ID7386
Feature activation+2.45e+00

Pos logit contributions
�醒+0.357
olit+0.317
ult+0.311
sted+0.309
adr+0.305
Neg logit contributions
DX-0.215
 Fathers-0.215
 DX-0.210
 resolves-0.209
 cow-0.208
Token works
Token ID2499
Feature activation+8.16e-01

Pos logit contributions
�醒+2.325
olit+2.126
ult+2.119
sted+2.111
adr+2.041
Neg logit contributions
DX-1.150
 Fathers-1.128
 resolves-1.118
 DX-1.113
 cow-1.096
Token are
Token ID389
Feature activation-2.76e-01

Pos logit contributions
�醒+0.658
olit+0.584
sted+0.581
ult+0.580
adr+0.560
Neg logit contributions
DX-0.504
 Fathers-0.497
 resolves-0.493
 DX-0.491
 cow-0.488
Token also
Token ID635
Feature activation-3.60e-01

Pos logit contributions
DX+0.149
 Fathers+0.147
 DX+0.147
 cow+0.147
 resolves+0.145
Neg logit contributions
�醒-0.242
ult-0.217
olit-0.217
sted-0.217
adr-0.207
Token available
Token ID1695
Feature activation-2.82e-01

Pos logit contributions
DX+0.201
 Fathers+0.198
 DX+0.198
 cow+0.197
 resolves+0.195
Neg logit contributions
�醒-0.312
ult-0.280
olit-0.279
sted-0.278
adr-0.265
Token on
Token ID319
Feature activation-4.21e-01

Pos logit contributions
DX+0.137
 DX+0.135
 Fathers+0.134
 resolves+0.133
 cow+0.132
Neg logit contributions
�醒-0.264
ult-0.238
olit-0.238
sted-0.237
adr-0.229
Token Irvine
Token ID37277
Feature activation-2.14e-01

Pos logit contributions
�醒+0.471
olit+0.414
ult+0.410
sted+0.406
adr+0.389
Neg logit contributions
DX-0.462
 Fathers-0.457
 DX-0.455
 resolves-0.455
 cow-0.452
Token,
Token ID11
Feature activation-4.21e-01

Pos logit contributions
DX+0.095
 Fathers+0.093
 DX+0.092
 resolves+0.092
 cow+0.091
Neg logit contributions
�醒-0.206
olit-0.190
ult-0.189
sted-0.188
adr-0.182
Token California
Token ID3442
Feature activation+1.54e-01

Pos logit contributions
DX+0.253
 resolves+0.251
 Fathers+0.250
 DX+0.248
 cow+0.248
Neg logit contributions
�醒-0.352
olit-0.312
ult-0.305
sted-0.304
adr-0.298
Token.
Token ID13
Feature activation-9.66e-02

Pos logit contributions
�醒+0.146
ult+0.134
olit+0.134
sted+0.133
adr+0.128
Neg logit contributions
DX-0.072
 Fathers-0.070
 resolves-0.069
 DX-0.069
 cow-0.067
Token Hide
Token ID10415
Feature activation+1.01e+00

Pos logit contributions
 Fathers+0.055
DX+0.055
 DX+0.055
 resolves+0.053
 cow+0.052
Neg logit contributions
�醒-0.083
ult-0.074
sted-0.074
olit-0.074
adr-0.071
Token Caption
Token ID11260
Feature activation+2.43e+00

Pos logit contributions
�醒+0.792
ult+0.725
olit+0.721
sted+0.721
adr+0.688
Neg logit contributions
DX-0.624
 resolves-0.609
 Fathers-0.607
 DX-0.601
 cow-0.596
Token 9
Token ID860
Feature activation-5.09e-01

Pos logit contributions
�醒+1.846
olit+1.704
sted+1.692
ult+1.686
adr+1.617
Neg logit contributions
DX-1.520
 resolves-1.478
 Fathers-1.461
 cow-1.449
 advancements-1.440
Token of
Token ID286
Feature activation+4.64e-01

Pos logit contributions
DX+0.248
 Fathers+0.242
 resolves+0.240
 DX+0.240
 cow+0.235
Neg logit contributions
�醒-0.478
olit-0.433
ult-0.431
sted-0.429
adr-0.415
Token 15
Token ID1315
Feature activation+7.80e-01

Pos logit contributions
�醒+0.342
ult+0.308
olit+0.308
sted+0.307
adr+0.291
Neg logit contributions
DX-0.311
 Fathers-0.305
 resolves-0.304
 DX-0.302
 cow-0.299
Token Photos
Token ID9434
Feature activation+1.51e+00

Pos logit contributions
�醒+0.490
olit+0.438
ult+0.438
sted+0.436
adr+0.410
Neg logit contributions
DX-0.602
 resolves-0.590
 Fathers-0.589
 DX-0.583
 cow-0.580
Token:
Token ID25
Feature activation+7.02e-01

Pos logit contributions
�醒+1.219
ult+1.131
sted+1.122
olit+1.121
adr+1.070
Neg logit contributions
DX-0.881
 resolves-0.861
 Fathers-0.860
 DX-0.849
 cow-0.841
Token Pasadena
Token ID41010
Feature activation-6.72e-01

Pos logit contributions
DX+0.281
 DX+0.279
 Fathers+0.279
 resolves+0.275
 cow+0.274
Neg logit contributions
�醒-0.343
olit-0.302
ult-0.301
sted-0.297
adr-0.288
Token,
Token ID11
Feature activation-3.93e-01

Pos logit contributions
DX+0.314
 Fathers+0.304
 DX+0.303
 resolves+0.301
 cow+0.295
Neg logit contributions
�醒-0.638
olit-0.586
ult-0.585
sted-0.581
adr-0.563
Token California
Token ID3442
Feature activation-3.00e-01

Pos logit contributions
DX+0.240
 resolves+0.235
 DX+0.235
 Fathers+0.235
 cow+0.234
Neg logit contributions
�醒-0.319
olit-0.286
ult-0.282
sted-0.280
adr-0.274
Token.
Token ID13
Feature activation-4.14e-02

Pos logit contributions
DX+0.136
 Fathers+0.133
 resolves+0.132
 DX+0.131
 cow+0.128
Neg logit contributions
�醒-0.288
ult-0.264
olit-0.264
sted-0.263
adr-0.254
Token Hide
Token ID10415
Feature activation+8.74e-01

Pos logit contributions
 Fathers+0.019
DX+0.019
 DX+0.019
 resolves+0.018
 cow+0.018
Neg logit contributions
�醒-0.040
ult-0.036
olit-0.036
sted-0.036
adr-0.035
Token Caption
Token ID11260
Feature activation+2.33e+00

Pos logit contributions
�醒+0.683
ult+0.626
olit+0.622
sted+0.622
adr+0.594
Neg logit contributions
DX-0.542
 resolves-0.528
 Fathers-0.527
 DX-0.521
 cow-0.518
Token 12
Token ID1105
Feature activation-1.83e-01

Pos logit contributions
�醒+1.587
ult+1.498
olit+1.470
sted+1.462
adr+1.410
Neg logit contributions
DX-1.596
 Fathers-1.562
 resolves-1.553
 cow-1.543
 advancements-1.538
Token of
Token ID286
Feature activation+2.82e-02

Pos logit contributions
DX+0.090
 Fathers+0.088
 resolves+0.088
 DX+0.087
 cow+0.086
Neg logit contributions
�醒-0.170
olit-0.155
ult-0.154
sted-0.153
adr-0.148
Token 15
Token ID1315
Feature activation+6.60e-01

Pos logit contributions
�醒+0.021
ult+0.019
olit+0.019
sted+0.019
adr+0.018
Neg logit contributions
DX-0.019
 Fathers-0.018
 resolves-0.018
 DX-0.018
 cow-0.018
Token Photos
Token ID9434
Feature activation+1.50e+00

Pos logit contributions
�醒+0.417
olit+0.372
ult+0.372
sted+0.370
adr+0.348
Neg logit contributions
DX-0.507
 resolves-0.497
 Fathers-0.497
 DX-0.492
 cow-0.490
Token:
Token ID25
Feature activation+7.19e-01

Pos logit contributions
�醒+1.215
ult+1.128
sted+1.119
olit+1.118
adr+1.068
Neg logit contributions
DX-0.881
 resolves-0.862
 Fathers-0.860
 DX-0.849
 cow-0.842
Token 20
Token ID1160
Feature activation-2.58e-02

Pos logit contributions
DX+0.213
 Fathers+0.209
 resolves+0.208
 DX+0.207
 cow+0.204
Neg logit contributions
�醒-0.259
ult-0.233
olit-0.233
sted-0.231
adr-0.221
Token,
Token ID11
Feature activation-2.55e-01

Pos logit contributions
DX+0.012
 Fathers+0.012
 resolves+0.012
 DX+0.012
 cow+0.012
Neg logit contributions
�醒-0.024
ult-0.022
olit-0.022
sted-0.022
adr-0.021
Token 2015
Token ID1853
Feature activation+3.98e-01

Pos logit contributions
DX+0.144
 Fathers+0.143
 DX+0.142
 resolves+0.141
 cow+0.140
Neg logit contributions
�醒-0.220
olit-0.196
ult-0.194
sted-0.193
adr-0.188
Token.
Token ID13
Feature activation-2.22e-01

Pos logit contributions
�醒+0.374
ult+0.344
olit+0.343
sted+0.341
adr+0.329
Neg logit contributions
DX-0.188
 Fathers-0.183
 resolves-0.182
 DX-0.180
 cow-0.177
Token Hide
Token ID10415
Feature activation+8.37e-01

Pos logit contributions
 Fathers+0.103
DX+0.101
 DX+0.101
 resolves+0.098
 cow+0.096
Neg logit contributions
�醒-0.215
ult-0.195
olit-0.195
sted-0.195
adr-0.188
Token Caption
Token ID11260
Feature activation+2.32e+00

Pos logit contributions
�醒+0.657
ult+0.601
olit+0.598
sted+0.597
adr+0.570
Neg logit contributions
DX-0.518
 resolves-0.505
 Fathers-0.504
 DX-0.498
 cow-0.494
Token 8
Token ID807
Feature activation+3.98e-02

Pos logit contributions
�醒+1.680
ult+1.571
olit+1.554
sted+1.551
adr+1.495
Neg logit contributions
DX-1.509
 Fathers-1.490
 resolves-1.467
 advancements-1.452
 cow-1.451
Token of
Token ID286
Feature activation+2.45e-01

Pos logit contributions
�醒+0.037
olit+0.033
ult+0.033
sted+0.033
adr+0.032
Neg logit contributions
DX-0.020
 Fathers-0.019
 resolves-0.019
 DX-0.019
 cow-0.019
Token 15
Token ID1315
Feature activation+9.58e-01

Pos logit contributions
�醒+0.183
ult+0.164
olit+0.164
sted+0.163
adr+0.156
Neg logit contributions
DX-0.163
 Fathers-0.160
 resolves-0.159
 DX-0.158
 cow-0.156
Token Photos
Token ID9434
Feature activation+1.49e+00

Pos logit contributions
�醒+0.593
olit+0.534
ult+0.533
sted+0.532
adr+0.499
Neg logit contributions
DX-0.742
 resolves-0.728
 Fathers-0.726
 DX-0.719
 cow-0.716
Token:
Token ID25
Feature activation+6.54e-01

Pos logit contributions
�醒+1.205
ult+1.117
sted+1.108
olit+1.108
adr+1.057
Neg logit contributions
DX-0.870
 resolves-0.851
 Fathers-0.850
 DX-0.839
 cow-0.831
Token:
Token ID25
Feature activation+6.46e-01

Pos logit contributions
 Fathers+0.125
DX+0.124
 DX+0.122
 resolves+0.122
 cow+0.121
Neg logit contributions
�醒-0.182
ult-0.165
olit-0.164
sted-0.163
adr-0.158
Token "
Token ID366
Feature activation+4.24e-01

Pos logit contributions
�醒+0.539
ult+0.487
olit+0.485
sted+0.483
adr+0.461
Neg logit contributions
DX-0.376
 Fathers-0.374
 DX-0.370
 resolves-0.364
 cow-0.364
TokenI
Token ID40
Feature activation+3.81e-01

Pos logit contributions
�醒+0.326
olit+0.290
sted+0.287
ult+0.286
adr+0.275
Neg logit contributions
DX-0.281
 Fathers-0.274
 DX-0.270
 resolves-0.268
 cow-0.266
Token Can
Token ID1680
Feature activation+4.93e-01

Pos logit contributions
�醒+0.304
olit+0.264
ult+0.262
sted+0.260
adr+0.253
Neg logit contributions
DX-0.244
 Fathers-0.242
 cow-0.240
 resolves-0.240
 DX-0.239
Token Think
Token ID11382
Feature activation+1.08e+00

Pos logit contributions
�醒+0.390
ult+0.347
sted+0.346
olit+0.345
adr+0.333
Neg logit contributions
DX-0.311
 Fathers-0.306
 DX-0.303
 resolves-0.301
 cow-0.299
Token Of
Token ID3226
Feature activation+2.30e+00

Pos logit contributions
�醒+0.868
ult+0.782
olit+0.778
sted+0.773
adr+0.747
Neg logit contributions
DX-0.656
 Fathers-0.653
 DX-0.643
 resolves-0.641
 cow-0.632
Token No
Token ID1400
Feature activation+7.38e-01

Pos logit contributions
�醒+1.714
ult+1.533
olit+1.532
sted+1.520
adr+1.451
Neg logit contributions
DX-1.538
 Fathers-1.512
 resolves-1.502
 DX-1.497
 cow-1.476
Token Reason
Token ID23219
Feature activation+4.03e-01

Pos logit contributions
�醒+0.595
ult+0.534
olit+0.531
sted+0.528
adr+0.509
Neg logit contributions
 Fathers-0.451
DX-0.451
 DX-0.442
 resolves-0.438
 cow-0.435
Token Why
Token ID4162
Feature activation-3.89e-01

Pos logit contributions
�醒+0.322
ult+0.290
olit+0.287
sted+0.287
adr+0.277
Neg logit contributions
 Fathers-0.248
DX-0.247
 DX-0.244
 cow-0.240
 resolves-0.240
Token In
Token ID554
Feature activation+4.70e-01

Pos logit contributions
 Fathers+0.242
 DX+0.236
DX+0.235
 cow+0.232
 resolves+0.231
Neg logit contributions
�醒-0.318
ult-0.281
olit-0.280
sted-0.277
adr-0.270
Token A
Token ID317
Feature activation+4.65e-01

Pos logit contributions
�醒+0.380
olit+0.337
ult+0.337
sted+0.335
adr+0.324
Neg logit contributions
 Fathers-0.285
DX-0.285
 DX-0.281
 resolves-0.276
 cow-0.276
Token Are
Token ID4231
Feature activation+4.34e-01

Pos logit contributions
�醒+0.218
olit+0.193
sted+0.191
ult+0.190
adr+0.182
Neg logit contributions
DX-0.169
 Fathers-0.168
 DX-0.167
 resolves-0.166
 cow-0.163
Token there
Token ID612
Feature activation+4.30e-01

Pos logit contributions
�醒+0.377
olit+0.340
ult+0.337
sted+0.335
adr+0.325
Neg logit contributions
DX-0.240
 Fathers-0.237
 DX-0.235
 cow-0.235
 resolves-0.235
Token more
Token ID517
Feature activation-2.99e-01

Pos logit contributions
�醒+0.394
olit+0.356
ult+0.355
sted+0.353
adr+0.342
Neg logit contributions
DX-0.219
 Fathers-0.216
 resolves-0.214
 cow-0.214
 DX-0.213
Token p
Token ID279
Feature activation+3.93e-02

Pos logit contributions
 Fathers+0.151
DX+0.150
 cow+0.150
 resolves+0.149
 DX+0.148
Neg logit contributions
�醒-0.275
olit-0.248
ult-0.246
sted-0.244
adr-0.238
Tokenoth
Token ID849
Feature activation+6.36e-01

Pos logit contributions
�醒+0.033
olit+0.029
sted+0.029
ult+0.029
adr+0.028
Neg logit contributions
DX-0.023
 Fathers-0.023
 resolves-0.022
 DX-0.022
 cow-0.022
Tokenoles
Token ID4316
Feature activation+2.29e+00

Pos logit contributions
�醒+0.659
ult+0.602
sted+0.600
olit+0.599
adr+0.581
Neg logit contributions
DX-0.244
 Fathers-0.239
 resolves-0.236
 DX-0.233
 cow-0.228
Token in
Token ID287
Feature activation+1.78e-01

Pos logit contributions
�醒+2.123
olit+1.928
ult+1.925
sted+1.907
adr+1.854
Neg logit contributions
DX-1.137
 resolves-1.112
 Fathers-1.112
 DX-1.103
 cow-1.092
Token New
Token ID968
Feature activation+1.05e+00

Pos logit contributions
�醒+0.153
olit+0.137
ult+0.137
sted+0.135
adr+0.131
Neg logit contributions
DX-0.101
 Fathers-0.100
 DX-0.100
 resolves-0.099
 cow-0.098
Token Jersey
Token ID8221
Feature activation+4.12e-01

Pos logit contributions
�醒+0.866
ult+0.782
olit+0.781
sted+0.772
adr+0.747
Neg logit contributions
DX-0.621
 Fathers-0.611
 resolves-0.607
 DX-0.605
 cow-0.597
Token than
Token ID621
Feature activation+5.01e-02

Pos logit contributions
�醒+0.361
olit+0.325
ult+0.323
sted+0.318
adr+0.313
Neg logit contributions
DX-0.224
 Fathers-0.220
 resolves-0.220
 DX-0.219
 cow-0.218
Token other
Token ID584
Feature activation-6.42e-01

Pos logit contributions
�醒+0.047
olit+0.043
ult+0.042
sted+0.042
adr+0.041
Neg logit contributions
DX-0.024
 Fathers-0.024
 resolves-0.024
 cow-0.024
 DX-0.024
Token 25
Token ID1679
Feature activation-7.70e-01

Pos logit contributions
 DX+0.559
DX+0.556
 Fathers+0.553
 resolves+0.553
 changing+0.546
Neg logit contributions
�醒-0.731
ult-0.665
olit-0.662
sted-0.651
adr-0.633
Token 26
Token ID2608
Feature activation-7.35e-01

Pos logit contributions
 resolves+0.452
DX+0.451
 DX+0.449
 Fathers+0.446
 changing+0.442
Neg logit contributions
�醒-0.638
ult-0.578
olit-0.572
sted-0.569
adr-0.547
Token 27
Token ID2681
Feature activation-5.53e-01

Pos logit contributions
DX+0.467
 resolves+0.462
 DX+0.461
 Fathers+0.460
 cow+0.453
Neg logit contributions
�醒-0.567
ult-0.519
olit-0.517
sted-0.516
adr-0.493
Token #
Token ID1303
Feature activation+1.58e+00

Pos logit contributions
DX+0.319
 resolves+0.314
 DX+0.313
 cow+0.309
 changing+0.301
Neg logit contributions
�醒-0.472
olit-0.432
sted-0.427
ult-0.417
adr-0.400
Token loop
Token ID9052
Feature activation+1.29e+00

Pos logit contributions
�醒+1.347
olit+1.221
sted+1.216
ult+1.215
adr+1.164
Neg logit contributions
DX-0.893
 resolves-0.872
 Fathers-0.871
 DX-0.865
 cow-0.850
Token over
Token ID625
Feature activation+2.27e+00

Pos logit contributions
�醒+1.149
olit+1.045
ult+1.040
sted+1.031
adr+1.001
Neg logit contributions
DX-0.688
 resolves-0.675
 DX-0.672
 Fathers-0.671
 cow-0.660
Token the
Token ID262
Feature activation+1.07e+00

Pos logit contributions
�醒+1.978
ult+1.802
olit+1.799
sted+1.791
adr+1.722
Neg logit contributions
DX-1.232
 Fathers-1.202
 resolves-1.196
 DX-1.188
 cow-1.168
Token input
Token ID5128
Feature activation+4.48e-01

Pos logit contributions
�醒+0.982
olit+0.900
ult+0.900
sted+0.894
adr+0.859
Neg logit contributions
DX-0.531
 Fathers-0.519
 resolves-0.517
 DX-0.513
 cow-0.504
Token image
Token ID2939
Feature activation+1.88e+00

Pos logit contributions
�醒+0.373
olit+0.339
ult+0.338
sted+0.337
adr+0.322
Neg logit contributions
DX-0.261
 resolves-0.255
 Fathers-0.254
 DX-0.254
 cow-0.250
Token paths
Token ID13532
Feature activation+1.23e+00

Pos logit contributions
�醒+1.615
ult+1.471
olit+1.469
sted+1.460
adr+1.403
Neg logit contributions
DX-1.040
 Fathers-1.014
 resolves-1.008
 DX-1.004
 cow-0.987
Token for
Token ID329
Feature activation+5.59e-01

Pos logit contributions
�醒+1.210
olit+1.114
ult+1.112
sted+1.106
adr+1.066
Neg logit contributions
DX-0.534
 resolves-0.521
 Fathers-0.520
 DX-0.517
 cow-0.506
Token?
Token ID30
Feature activation+4.65e-01

Pos logit contributions
�醒+0.640
olit+0.573
sted+0.570
ult+0.570
adr+0.547
Neg logit contributions
DX-0.451
 DX-0.439
 Fathers-0.437
 resolves-0.434
 cow-0.429
Token
Token ID198
Feature activation+1.28e-01

Pos logit contributions
�醒+0.398
olit+0.358
sted+0.356
ult+0.355
adr+0.341
Neg logit contributions
DX-0.269
 DX-0.261
 Fathers-0.259
 resolves-0.259
 cow-0.255
Token
Token ID198
Feature activation+1.49e-01

Pos logit contributions
�醒+0.099
olit+0.088
ult+0.087
sted+0.086
adr+0.083
Neg logit contributions
DX-0.084
 Fathers-0.082
 DX-0.081
 resolves-0.081
 cow-0.080
TokenDark
Token ID17367
Feature activation+9.65e-01

Pos logit contributions
�醒+0.116
olit+0.101
sted+0.100
ult+0.098
adr+0.095
Neg logit contributions
DX-0.100
 DX-0.094
 Fathers-0.094
 resolves-0.093
 cow-0.093
Tokenhorse
Token ID30527
Feature activation+9.00e-01

Pos logit contributions
�醒+0.772
olit+0.679
sted+0.674
ult+0.672
adr+0.643
Neg logit contributions
DX-0.620
 Fathers-0.596
 resolves-0.593
 DX-0.591
 cow-0.584
Token Profile
Token ID13118
Feature activation+2.25e+00

Pos logit contributions
�醒+0.727
olit+0.642
sted+0.638
ult+0.637
adr+0.610
Neg logit contributions
DX-0.568
 Fathers-0.547
 DX-0.544
 resolves-0.542
 cow-0.533
Token Blog
Token ID14001
Feature activation+2.69e-01

Pos logit contributions
�醒+1.413
ult+1.226
olit+1.226
sted+1.215
adr+1.146
Neg logit contributions
DX-1.781
 Fathers-1.752
 DX-1.749
 resolves-1.742
 cow-1.723
Token Joined
Token ID16709
Feature activation+5.79e-01

Pos logit contributions
�醒+0.186
olit+0.162
ult+0.161
sted+0.159
adr+0.151
Neg logit contributions
DX-0.199
 Fathers-0.197
 DX-0.196
 resolves-0.195
 cow-0.192
Token December
Token ID3426
Feature activation+6.49e-01

Pos logit contributions
�醒+0.524
olit+0.471
ult+0.469
sted+0.465
adr+0.450
Neg logit contributions
DX-0.307
 Fathers-0.303
 resolves-0.299
 DX-0.299
 cow-0.292
Token 2011
Token ID2813
Feature activation+8.66e-01

Pos logit contributions
�醒+0.552
olit+0.492
ult+0.487
sted+0.485
adr+0.467
Neg logit contributions
DX-0.382
 Fathers-0.376
 DX-0.373
 resolves-0.371
 cow-0.364
Token United
Token ID1578
Feature activation+1.19e+00

Pos logit contributions
�醒+0.764
olit+0.686
ult+0.680
sted+0.677
adr+0.651
Neg logit contributions
DX-0.482
 DX-0.475
 Fathers-0.474
 resolves-0.466
 cow-0.459
Token,
Token ID11
Feature activation-4.14e-02

Pos logit contributions
�醒+0.127
ult+0.115
olit+0.114
sted+0.113
adr+0.109
Neg logit contributions
DX-0.076
 DX-0.075
 cow-0.074
 resolves-0.074
 Fathers-0.073
Token motor
Token ID5584
Feature activation-9.90e-03

Pos logit contributions
DX+0.022
 DX+0.021
 cow+0.021
 resolves+0.021
 Fathers+0.021
Neg logit contributions
�醒-0.038
olit-0.034
ult-0.034
sted-0.034
adr-0.032
Tokenized
Token ID1143
Feature activation+1.08e+00

Pos logit contributions
DX+0.005
 DX+0.005
 cow+0.005
 resolves+0.005
 Fathers+0.005
Neg logit contributions
�醒-0.009
olit-0.008
ult-0.008
sted-0.008
adr-0.008
Token wheelchair
Token ID27181
Feature activation+1.20e-01

Pos logit contributions
�醒+0.962
olit+0.874
ult+0.870
sted+0.864
adr+0.833
Neg logit contributions
DX-0.574
 DX-0.563
 cow-0.556
 resolves-0.555
 Fathers-0.553
Token (
Token ID357
Feature activation+8.65e-01

Pos logit contributions
�醒+0.115
ult+0.105
olit+0.105
sted+0.104
adr+0.100
Neg logit contributions
DX-0.056
 DX-0.055
 resolves-0.054
 Fathers-0.054
 cow-0.054
TokenFigure
Token ID11337
Feature activation+2.23e+00

Pos logit contributions
�醒+0.672
olit+0.599
sted+0.595
ult+0.589
adr+0.564
Neg logit contributions
DX-0.571
 DX-0.544
 Fathers-0.543
 resolves-0.541
 cow-0.536
Token 2
Token ID362
Feature activation-2.06e-01

Pos logit contributions
�醒+1.937
ult+1.759
olit+1.754
sted+1.747
adr+1.678
Neg logit contributions
DX-1.235
 Fathers-1.205
 resolves-1.203
 DX-1.201
 cow-1.176
TokenA
Token ID32
Feature activation-1.72e-01

Pos logit contributions
DX+0.121
 resolves+0.117
 DX+0.117
 Fathers+0.117
 cow+0.116
Neg logit contributions
�醒-0.172
olit-0.155
ult-0.155
sted-0.154
adr-0.147
Token,
Token ID11
Feature activation-5.51e-01

Pos logit contributions
DX+0.084
 resolves+0.082
 DX+0.082
 Fathers+0.081
 cow+0.080
Neg logit contributions
�醒-0.160
olit-0.146
ult-0.145
sted-0.144
adr-0.139
Token [
Token ID685
Feature activation+9.25e-01

Pos logit contributions
DX+0.329
 DX+0.319
 Fathers+0.316
 resolves+0.316
 cow+0.315
Neg logit contributions
�醒-0.456
olit-0.416
ult-0.412
sted-0.408
adr-0.392
TokenAction
Token ID12502
Feature activation+1.36e+00

Pos logit contributions
�醒+0.715
olit+0.634
sted+0.629
ult+0.628
adr+0.597
Neg logit contributions
DX-0.613
 Fathers-0.591
 resolves-0.588
 DX-0.587
 cow-0.578
Token questions
Token ID2683
Feature activation-5.53e-01

Pos logit contributions
�醒+0.316
olit+0.284
ult+0.284
sted+0.282
adr+0.275
Neg logit contributions
 Fathers-0.168
DX-0.167
 cow-0.166
 DX-0.164
 resolves-0.163
Token gay
Token ID5650
Feature activation+7.51e-01

Pos logit contributions
 Fathers+0.273
DX+0.271
 DX+0.267
 cow+0.267
 resolves+0.264
Neg logit contributions
�醒-0.517
ult-0.468
olit-0.467
sted-0.461
adr-0.448
Token girls
Token ID4813
Feature activation+4.67e-02

Pos logit contributions
�醒+0.803
olit+0.738
ult+0.737
sted+0.730
adr+0.716
Neg logit contributions
 Fathers-0.271
DX-0.269
 DX-0.259
 resolves-0.258
 cow-0.258
Token still
Token ID991
Feature activation+1.88e-01

Pos logit contributions
�醒+0.037
olit+0.033
ult+0.032
sted+0.032
adr+0.031
Neg logit contributions
 Fathers-0.030
DX-0.030
 cow-0.029
 resolves-0.029
 DX-0.029
Token get
Token ID651
Feature activation+1.04e+00

Pos logit contributions
�醒+0.144
olit+0.125
ult+0.124
sted+0.123
adr+0.118
Neg logit contributions
 resolves-0.125
DX-0.125
 cow-0.125
 Fathers-0.124
 DX-0.123
Token asked
Token ID1965
Feature activation+2.23e+00

Pos logit contributions
�醒+0.922
olit+0.841
ult+0.831
sted+0.823
adr+0.799
Neg logit contributions
DX-0.546
 Fathers-0.538
 resolves-0.537
 DX-0.537
 cow-0.532
Token
Token ID198
Feature activation+1.00e-01

Pos logit contributions
�醒+1.915
ult+1.734
olit+1.733
sted+1.711
adr+1.654
Neg logit contributions
DX-1.249
 Fathers-1.234
 DX-1.221
 resolves-1.221
 cow-1.209
Token
Token ID198
Feature activation-1.84e-01

Pos logit contributions
�醒+0.078
olit+0.069
ult+0.068
sted+0.068
adr+0.065
Neg logit contributions
DX-0.065
 Fathers-0.064
 DX-0.064
 resolves-0.064
 cow-0.063
TokenMORE
Token ID23346
Feature activation+3.36e-01

Pos logit contributions
DX+0.121
 Fathers+0.116
 DX+0.114
 resolves+0.112
 cow+0.111
Neg logit contributions
�醒-0.145
olit-0.128
ult-0.126
sted-0.126
adr-0.119
Token:
Token ID25
Feature activation-3.62e-01

Pos logit contributions
�醒+0.293
olit+0.264
ult+0.264
sted+0.261
adr+0.252
Neg logit contributions
DX-0.186
 Fathers-0.182
 DX-0.181
 resolves-0.180
 cow-0.177
Token Restaurant
Token ID26078
Feature activation+4.11e-01

Pos logit contributions
 Fathers+0.226
DX+0.221
 DX+0.219
 resolves+0.213
 cow+0.212
Neg logit contributions
�醒-0.298
olit-0.266
ult-0.266
sted-0.259
adr-0.251
Token Pasadena
Token ID41010
Feature activation-2.83e-01

Pos logit contributions
�醒+0.352
olit+0.311
ult+0.311
sted+0.307
adr+0.297
Neg logit contributions
DX-0.267
 Fathers-0.265
 DX-0.264
 resolves-0.262
 cow-0.261
Token,
Token ID11
Feature activation-6.52e-01

Pos logit contributions
DX+0.132
 Fathers+0.128
 DX+0.128
 resolves+0.127
 cow+0.125
Neg logit contributions
�醒-0.267
olit-0.246
ult-0.245
sted-0.244
adr-0.236
Token California
Token ID3442
Feature activation-1.32e-02

Pos logit contributions
DX+0.389
 resolves+0.380
 DX+0.379
 cow+0.379
 Fathers+0.379
Neg logit contributions
�醒-0.547
olit-0.484
ult-0.476
sted-0.472
adr-0.468
Token.
Token ID13
Feature activation-2.19e-02

Pos logit contributions
DX+0.006
 Fathers+0.006
 resolves+0.006
 DX+0.006
 cow+0.006
Neg logit contributions
�醒-0.013
ult-0.012
olit-0.011
sted-0.011
adr-0.011
Token Hide
Token ID10415
Feature activation+8.83e-01

Pos logit contributions
DX+0.011
 Fathers+0.011
 DX+0.011
 resolves+0.011
 cow+0.011
Neg logit contributions
�醒-0.020
ult-0.018
olit-0.018
sted-0.018
adr-0.017
Token Caption
Token ID11260
Feature activation+2.22e+00

Pos logit contributions
�醒+0.693
ult+0.634
olit+0.631
sted+0.630
adr+0.602
Neg logit contributions
DX-0.547
 resolves-0.533
 Fathers-0.532
 DX-0.526
 cow-0.522
Token 11
Token ID1367
Feature activation-1.23e-01

Pos logit contributions
�醒+1.418
olit+1.317
ult+1.299
sted+1.298
adr+1.247
Neg logit contributions
DX-1.628
 resolves-1.586
 cow-1.575
 Fathers-1.566
 advancements-1.557
Token of
Token ID286
Feature activation+2.19e-01

Pos logit contributions
DX+0.061
 Fathers+0.060
 resolves+0.060
 DX+0.059
 cow+0.058
Neg logit contributions
�醒-0.114
olit-0.104
ult-0.103
sted-0.103
adr-0.099
Token 15
Token ID1315
Feature activation+6.10e-01

Pos logit contributions
�醒+0.162
ult+0.146
olit+0.145
sted+0.145
adr+0.138
Neg logit contributions
DX-0.147
 Fathers-0.144
 resolves-0.143
 DX-0.142
 cow-0.141
Token Photos
Token ID9434
Feature activation+1.25e+00

Pos logit contributions
�醒+0.387
olit+0.345
ult+0.345
sted+0.343
adr+0.323
Neg logit contributions
DX-0.469
 resolves-0.459
 Fathers-0.459
 DX-0.455
 cow-0.452
Token:
Token ID25
Feature activation+7.08e-01

Pos logit contributions
�醒+1.026
ult+0.947
olit+0.941
sted+0.940
adr+0.898
Neg logit contributions
DX-0.729
 resolves-0.712
 Fathers-0.712
 DX-0.703
 cow-0.696
Token Hills
Token ID14379
Feature activation-1.34e+00

Pos logit contributions
DX+0.307
 Fathers+0.302
 DX+0.299
 resolves+0.298
 cow+0.292
Neg logit contributions
�醒-0.660
sted-0.600
ult-0.599
olit-0.599
adr-0.575
Token,
Token ID11
Feature activation-5.59e-01

Pos logit contributions
DX+0.557
 DX+0.555
 Fathers+0.550
 resolves+0.539
 cow+0.536
Neg logit contributions
�醒-1.334
ult-1.195
olit-1.193
sted-1.193
adr-1.149
Token California
Token ID3442
Feature activation-5.00e-02

Pos logit contributions
DX+0.332
 Fathers+0.329
 resolves+0.328
 DX+0.326
 cow+0.326
Neg logit contributions
�醒-0.471
olit-0.413
sted-0.406
ult-0.406
adr-0.398
Token.
Token ID13
Feature activation-3.25e-01

Pos logit contributions
DX+0.023
 Fathers+0.023
 resolves+0.023
 DX+0.022
 cow+0.022
Neg logit contributions
�醒-0.047
ult-0.043
olit-0.043
sted-0.043
adr-0.042
Token Hide
Token ID10415
Feature activation+9.26e-01

Pos logit contributions
 Fathers+0.163
DX+0.161
 DX+0.160
 resolves+0.156
 cow+0.153
Neg logit contributions
�醒-0.303
ult-0.272
sted-0.272
olit-0.272
adr-0.262
Token Caption
Token ID11260
Feature activation+2.22e+00

Pos logit contributions
�醒+0.720
ult+0.661
sted+0.657
olit+0.657
adr+0.627
Neg logit contributions
DX-0.576
 resolves-0.561
 Fathers-0.559
 DX-0.553
 cow-0.550
Token 14
Token ID1478
Feature activation-7.23e-01

Pos logit contributions
�醒+1.483
ult+1.363
olit+1.353
sted+1.352
adr+1.288
Neg logit contributions
DX-1.585
 Fathers-1.553
 resolves-1.547
 cow-1.532
 DX-1.527
Token of
Token ID286
Feature activation-1.47e-01

Pos logit contributions
DX+0.351
 Fathers+0.344
 resolves+0.341
 DX+0.341
 cow+0.334
Neg logit contributions
�醒-0.682
olit-0.617
ult-0.614
sted-0.611
adr-0.591
Token 15
Token ID1315
Feature activation+3.60e-01

Pos logit contributions
DX+0.098
 Fathers+0.096
 resolves+0.096
 DX+0.095
 cow+0.094
Neg logit contributions
�醒-0.111
ult-0.099
olit-0.099
sted-0.098
adr-0.094
Token Photos
Token ID9434
Feature activation+1.35e+00

Pos logit contributions
�醒+0.232
olit+0.206
ult+0.206
sted+0.205
adr+0.193
Neg logit contributions
DX-0.274
 Fathers-0.269
 resolves-0.269
 DX-0.267
 cow-0.265
Token:
Token ID25
Feature activation+6.25e-01

Pos logit contributions
�醒+1.094
ult+1.013
sted+1.005
olit+1.005
adr+0.959
Neg logit contributions
DX-0.786
 resolves-0.768
 Fathers-0.767
 DX-0.757
 cow-0.750
Token high
Token ID1029
Feature activation+1.63e-01

Pos logit contributions
�醒+0.284
olit+0.252
ult+0.251
sted+0.246
adr+0.236
Neg logit contributions
 Fathers-0.224
 cow-0.222
DX-0.220
 resolves-0.220
 DX-0.218
Token court
Token ID2184
Feature activation+5.36e-01

Pos logit contributions
�醒+0.144
ult+0.130
olit+0.130
sted+0.129
adr+0.124
Neg logit contributions
DX-0.087
 resolves-0.087
 Fathers-0.086
 cow-0.086
 DX-0.084
Token
Token ID447
Feature activation-6.89e-02

Pos logit contributions
�醒+0.488
olit+0.443
ult+0.440
sted+0.436
adr+0.423
Neg logit contributions
 Fathers-0.275
DX-0.274
 resolves-0.274
 cow-0.270
 DX-0.269
Token
Token ID247
Feature activation-1.47e-01

Pos logit contributions
DX+0.052
 Fathers+0.051
 DX+0.051
 resolves+0.050
 cow+0.050
Neg logit contributions
�醒-0.045
ult-0.041
olit-0.040
sted-0.040
adr-0.038
Tokens
Token ID82
Feature activation-2.63e-03

Pos logit contributions
DX+0.093
 Fathers+0.091
 resolves+0.091
 cow+0.090
 DX+0.090
Neg logit contributions
�醒-0.116
olit-0.103
ult-0.101
sted-0.101
adr-0.098
Token door
Token ID3420
Feature activation-2.49e+00

Pos logit contributions
 Fathers+0.002
 resolves+0.002
 cow+0.002
DX+0.002
 DX+0.002
Neg logit contributions
�醒-0.002
olit-0.002
ult-0.002
sted-0.002
adr-0.002
Token expressing
Token ID16621
Feature activation+1.92e-01

Pos logit contributions
 cow+1.140
 Fathers+1.139
 resolves+1.126
 changing+1.121
 DX+1.093
Neg logit contributions
�醒-2.362
olit-2.156
ult-2.138
sted-2.112
adr-2.062
Token concern
Token ID2328
Feature activation+7.82e-01

Pos logit contributions
�醒+0.167
olit+0.150
ult+0.149
sted+0.148
adr+0.143
Neg logit contributions
 resolves-0.106
 cow-0.106
DX-0.106
 Fathers-0.106
 DX-0.104
Token over
Token ID625
Feature activation+2.60e-01

Pos logit contributions
�醒+0.719
olit+0.651
ult+0.646
sted+0.643
adr+0.625
Neg logit contributions
DX-0.391
 Fathers-0.388
 resolves-0.386
 cow-0.382
 DX-0.382
Token the
Token ID262
Feature activation-4.42e-01

Pos logit contributions
�醒+0.235
olit+0.214
ult+0.214
sted+0.212
adr+0.204
Neg logit contributions
DX-0.132
 Fathers-0.131
 resolves-0.130
 DX-0.129
 cow-0.129
Token growing
Token ID3957
Feature activation-6.89e-02

Pos logit contributions
DX+0.216
 Fathers+0.216
 cow+0.215
 resolves+0.215
 DX+0.214
Neg logit contributions
�醒-0.412
olit-0.372
ult-0.372
sted-0.368
adr-0.354
Token remaining
Token ID5637
Feature activation-3.64e-01

Pos logit contributions
 Fathers+0.075
 DX+0.073
DX+0.073
 resolves+0.073
 cow+0.073
Neg logit contributions
�醒-0.132
sted-0.119
olit-0.118
ult-0.117
adr-0.114
Token minutes
Token ID2431
Feature activation+6.08e-01

Pos logit contributions
 Fathers+0.207
 DX+0.204
 resolves+0.204
 cow+0.203
DX+0.202
Neg logit contributions
�醒-0.317
olit-0.282
sted-0.280
ult-0.279
adr-0.269
Token were
Token ID547
Feature activation-2.13e-02

Pos logit contributions
�醒+0.547
olit+0.490
sted+0.486
ult+0.483
adr+0.469
Neg logit contributions
 resolves-0.320
 cow-0.319
 DX-0.318
DX-0.318
 Fathers-0.318
Token unable
Token ID5906
Feature activation-4.44e-01

Pos logit contributions
DX+0.012
 Fathers+0.012
 resolves+0.012
 cow+0.012
 DX+0.012
Neg logit contributions
�醒-0.018
olit-0.016
ult-0.016
sted-0.016
adr-0.016
Token to
Token ID284
Feature activation-5.18e-01

Pos logit contributions
 resolves+0.180
DX+0.180
 DX+0.179
 Fathers+0.178
 cow+0.174
Neg logit contributions
�醒-0.449
ult-0.409
olit-0.408
sted-0.404
adr-0.394
Token break
Token ID2270
Feature activation-2.46e+00

Pos logit contributions
 resolves+0.304
 cow+0.302
 DX+0.299
 Fathers+0.298
DX+0.298
Neg logit contributions
�醒-0.435
ult-0.387
olit-0.386
sted-0.384
adr-0.373
Token the
Token ID262
Feature activation-3.15e-01

Pos logit contributions
 resolves+1.142
 DX+1.125
 Fathers+1.116
DX+1.112
 cow+1.109
Neg logit contributions
�醒-2.369
olit-2.143
ult-2.091
sted-2.069
adr-2.051
Token dead
Token ID2636
Feature activation-2.95e-01

Pos logit contributions
 Fathers+0.177
 resolves+0.176
 DX+0.175
 cow+0.175
DX+0.174
Neg logit contributions
�醒-0.278
olit-0.247
sted-0.243
ult-0.242
adr-0.235
Tokenlock
Token ID5354
Feature activation-3.84e-01

Pos logit contributions
DX+0.219
 resolves+0.218
 cow+0.217
 DX+0.216
 Fathers+0.215
Neg logit contributions
�醒-0.198
ult-0.173
olit-0.172
sted-0.171
adr-0.165
Token and
Token ID290
Feature activation-2.28e-01

Pos logit contributions
 resolves+0.167
 Fathers+0.166
DX+0.165
 DX+0.163
 cow+0.162
Neg logit contributions
�醒-0.381
olit-0.345
sted-0.343
ult-0.342
adr-0.333
Token the
Token ID262
Feature activation-1.77e-01

Pos logit contributions
 Fathers+0.127
 resolves+0.125
 DX+0.124
DX+0.124
 cow+0.123
Neg logit contributions
�醒-0.201
olit-0.177
sted-0.177
ult-0.176
adr-0.171
Token,
Token ID11
Feature activation-2.09e-01

Pos logit contributions
�醒+0.061
olit+0.056
ult+0.056
sted+0.055
adr+0.053
Neg logit contributions
DX-0.037
 cow-0.037
 DX-0.036
 Fathers-0.036
 resolves-0.036
Token shit
Token ID7510
Feature activation-8.78e-02

Pos logit contributions
DX+0.112
 Fathers+0.111
 DX+0.110
 cow+0.110
 resolves+0.110
Neg logit contributions
�醒-0.185
sted-0.167
olit-0.167
ult-0.166
adr-0.160
Token,
Token ID11
Feature activation-5.23e-01

Pos logit contributions
DX+0.045
 cow+0.044
 Fathers+0.044
 DX+0.044
 resolves+0.043
Neg logit contributions
�醒-0.080
olit-0.072
ult-0.071
sted-0.071
adr-0.070
Token piss
Token ID18314
Feature activation+2.48e-01

Pos logit contributions
DX+0.280
 Fathers+0.279
 cow+0.278
 DX+0.277
 resolves+0.276
Neg logit contributions
�醒-0.463
olit-0.417
sted-0.416
ult-0.413
adr-0.399
Token,
Token ID11
Feature activation-2.19e-01

Pos logit contributions
�醒+0.236
olit+0.215
sted+0.214
ult+0.214
adr+0.208
Neg logit contributions
DX-0.116
 DX-0.114
 cow-0.114
 Fathers-0.113
 resolves-0.112
Token brush
Token ID14093
Feature activation-2.43e+00

Pos logit contributions
DX+0.119
 Fathers+0.118
 cow+0.117
 DX+0.117
 resolves+0.117
Neg logit contributions
�醒-0.192
olit-0.173
sted-0.173
ult-0.172
adr-0.165
Token teeth
Token ID9941
Feature activation-7.53e-01

Pos logit contributions
 cow+1.237
DX+1.228
 DX+1.224
 Fathers+1.210
 resolves+1.197
Neg logit contributions
�醒-2.173
ult-1.979
olit-1.957
sted-1.931
adr-1.903
Token and
Token ID290
Feature activation-3.85e-02

Pos logit contributions
DX+0.324
 cow+0.322
 resolves+0.322
 Fathers+0.321
 DX+0.319
Neg logit contributions
�醒-0.742
olit-0.674
ult-0.669
sted-0.669
adr-0.647
Token hair
Token ID4190
Feature activation-9.31e-01

Pos logit contributions
DX+0.022
 Fathers+0.022
 DX+0.022
 resolves+0.022
 cow+0.022
Neg logit contributions
�醒-0.033
ult-0.029
olit-0.029
sted-0.029
adr-0.028
Token,
Token ID11
Feature activation-1.88e-01

Pos logit contributions
DX+0.467
 Fathers+0.461
 resolves+0.459
 changing+0.458
 DX+0.457
Neg logit contributions
�醒-0.851
ult-0.766
olit-0.765
sted-0.762
adr-0.731
Token and
Token ID290
Feature activation+1.61e-01

Pos logit contributions
DX+0.100
 Fathers+0.100
 cow+0.100
 resolves+0.100
 DX+0.099
Neg logit contributions
�醒-0.167
olit-0.150
sted-0.149
ult-0.149
adr-0.143
Token in
Token ID287
Feature activation+7.65e-01

Pos logit contributions
�醒+0.115
olit+0.103
sted+0.101
ult+0.101
adr+0.097
Neg logit contributions
 Fathers-0.088
DX-0.087
 DX-0.086
 cow-0.086
 resolves-0.086
Token 2002
Token ID6244
Feature activation+2.06e-01

Pos logit contributions
�醒+0.667
olit+0.593
sted+0.586
ult+0.584
adr+0.564
Neg logit contributions
DX-0.430
 Fathers-0.429
 DX-0.425
 cow-0.424
 resolves-0.419
Token,
Token ID11
Feature activation+7.14e-01

Pos logit contributions
�醒+0.189
olit+0.172
ult+0.170
sted+0.169
adr+0.163
Neg logit contributions
 Fathers-0.103
DX-0.102
 cow-0.100
 DX-0.100
 resolves-0.100
Token his
Token ID465
Feature activation+1.24e+00

Pos logit contributions
�醒+0.596
olit+0.534
sted+0.527
ult+0.527
adr+0.505
Neg logit contributions
 Fathers-0.422
DX-0.420
 DX-0.413
 cow-0.412
 resolves-0.411
Token net
Token ID2010
Feature activation-8.96e-01

Pos logit contributions
�醒+1.047
olit+0.925
ult+0.914
sted+0.913
adr+0.875
Neg logit contributions
DX-0.732
 Fathers-0.729
 cow-0.727
 DX-0.720
 resolves-0.719
Token worth
Token ID2861
Feature activation-2.40e+00

Pos logit contributions
 resolves+0.397
DX+0.396
 cow+0.389
 Fathers+0.388
 changing+0.380
Neg logit contributions
�醒-0.889
ult-0.800
olit-0.795
sted-0.782
adr-0.764
Token was
Token ID373
Feature activation+1.24e-01

Pos logit contributions
 cow+1.364
 resolves+1.334
 drops+1.331
 DX+1.329
 Fathers+1.328
Neg logit contributions
�醒-2.087
olit-1.856
ult-1.778
sted-1.770
adr-1.761
Token estimated
Token ID6108
Feature activation-8.33e-02

Pos logit contributions
�醒+0.101
olit+0.089
ult+0.088
sted+0.087
adr+0.084
Neg logit contributions
DX-0.076
 Fathers-0.076
 resolves-0.075
 DX-0.075
 cow-0.075
Token at
Token ID379
Feature activation+5.20e-02

Pos logit contributions
DX+0.037
 Fathers+0.035
 DX+0.035
 resolves+0.035
 cow+0.035
Neg logit contributions
�醒-0.081
olit-0.075
ult-0.074
sted-0.074
adr-0.072
Token $
Token ID720
Feature activation-1.83e-01

Pos logit contributions
�醒+0.045
olit+0.041
ult+0.040
sted+0.040
adr+0.039
Neg logit contributions
DX-0.029
 Fathers-0.029
 DX-0.029
 cow-0.029
 resolves-0.028
Token850
Token ID25764
Feature activation-1.84e-01

Pos logit contributions
DX+0.120
 Fathers+0.116
 resolves+0.115
 DX+0.114
 cow+0.113
Neg logit contributions
�醒-0.146
olit-0.127
sted-0.124
ult-0.123
adr-0.118
Token,
Token ID11
Feature activation+5.17e-01

Pos logit contributions
DX+0.052
 Fathers+0.050
 resolves+0.050
 DX+0.050
 cow+0.049
Neg logit contributions
�醒-0.121
olit-0.111
ult-0.110
sted-0.110
adr-0.106
Token Hulu
Token ID39739
Feature activation+3.42e-01

Pos logit contributions
�醒+0.416
olit+0.370
sted+0.368
ult+0.366
adr+0.353
Neg logit contributions
DX-0.324
 Fathers-0.319
 DX-0.319
 resolves-0.316
 cow-0.312
Token,
Token ID11
Feature activation+1.22e-01

Pos logit contributions
�醒+0.332
olit+0.304
ult+0.303
sted+0.302
adr+0.292
Neg logit contributions
DX-0.155
 DX-0.149
 Fathers-0.149
 resolves-0.149
 cow-0.145
Token and
Token ID290
Feature activation+6.03e-01

Pos logit contributions
�醒+0.115
olit+0.105
sted+0.104
ult+0.103
adr+0.101
Neg logit contributions
DX-0.059
 Fathers-0.058
 DX-0.058
 resolves-0.057
 cow-0.056
Token Amazon
Token ID6186
Feature activation-1.45e+00

Pos logit contributions
�醒+0.507
olit+0.452
sted+0.450
ult+0.449
adr+0.435
Neg logit contributions
DX-0.354
 Fathers-0.351
 DX-0.350
 resolves-0.347
 cow-0.342
Token Prime
Token ID5537
Feature activation-2.39e+00

Pos logit contributions
DX+0.830
 resolves+0.810
 Fathers+0.810
 DX+0.804
 cow+0.793
Neg logit contributions
�醒-1.230
olit-1.116
ult-1.106
sted-1.098
adr-1.063
Token among
Token ID1871
Feature activation-2.56e-01

Pos logit contributions
DX+1.280
 Fathers+1.248
 DX+1.233
 resolves+1.219
 cow+1.213
Neg logit contributions
�醒-2.152
olit-1.937
ult-1.925
sted-1.903
adr-1.877
Token others
Token ID1854
Feature activation+3.76e-01

Pos logit contributions
DX+0.119
 DX+0.115
 Fathers+0.115
 resolves+0.115
 cow+0.113
Neg logit contributions
�醒-0.245
ult-0.224
olit-0.224
sted-0.222
adr-0.216
Token.
Token ID13
Feature activation+2.56e-01

Pos logit contributions
�醒+0.372
olit+0.341
ult+0.339
sted+0.338
adr+0.328
Neg logit contributions
DX-0.162
 DX-0.157
 Fathers-0.157
 resolves-0.156
 cow-0.154
Token
Token ID198
Feature activation+2.94e-01

Pos logit contributions
�醒+0.203
olit+0.182
ult+0.180
sted+0.179
adr+0.171
Neg logit contributions
 Fathers-0.162
DX-0.160
 DX-0.160
 resolves-0.157
 cow-0.153
Token
Token ID198
Feature activation-9.44e-02

Pos logit contributions
�醒+0.227
olit+0.201
ult+0.200
sted+0.198
adr+0.190
Neg logit contributions
DX-0.194
 Fathers-0.190
 resolves-0.189
 DX-0.189
 cow-0.185
Token J
Token ID449
Feature activation-2.05e-01

Pos logit contributions
�醒+0.438
olit+0.392
ult+0.390
sted+0.385
adr+0.368
Neg logit contributions
 Fathers-0.349
DX-0.348
 DX-0.344
 resolves-0.339
 cow-0.332
Tokenarl
Token ID7063
Feature activation+1.02e+00

Pos logit contributions
DX+0.144
 Fathers+0.141
 DX+0.140
 resolves+0.139
 cow+0.137
Neg logit contributions
�醒-0.148
sted-0.127
ult-0.127
olit-0.127
adr-0.118
Token never
Token ID1239
Feature activation+4.86e-01

Pos logit contributions
�醒+0.808
olit+0.721
ult+0.715
sted+0.700
adr+0.682
Neg logit contributions
 Fathers-0.635
DX-0.633
 resolves-0.632
 DX-0.626
 cow-0.618
Token thought
Token ID1807
Feature activation-9.30e-01

Pos logit contributions
�醒+0.399
olit+0.352
ult+0.351
sted+0.347
adr+0.335
Neg logit contributions
 resolves-0.299
 Fathers-0.297
DX-0.294
 cow-0.292
 DX-0.291
Token he
Token ID339
Feature activation-3.00e-01

Pos logit contributions
 Fathers+0.480
DX+0.479
 DX+0.478
 resolves+0.474
 cow+0.469
Neg logit contributions
�醒-0.847
olit-0.762
sted-0.752
ult-0.751
adr-0.736
Token'd
Token ID1549
Feature activation-2.37e+00

Pos logit contributions
DX+0.160
 Fathers+0.160
 resolves+0.159
 cow+0.157
 DX+0.156
Neg logit contributions
�醒-0.267
olit-0.239
ult-0.238
sted-0.237
adr-0.229
Token be
Token ID307
Feature activation+3.69e-01

Pos logit contributions
 Fathers+1.473
 cow+1.471
 resolves+1.468
DX+1.439
 changing+1.438
Neg logit contributions
�醒-1.937
olit-1.672
ult-1.649
sted-1.638
adr-1.605
Token a
Token ID257
Feature activation-3.06e-02

Pos logit contributions
�醒+0.321
olit+0.289
ult+0.288
sted+0.284
adr+0.275
Neg logit contributions
DX-0.204
 Fathers-0.203
 resolves-0.201
 DX-0.201
 cow-0.200
Token hockey
Token ID12217
Feature activation+1.42e-01

Pos logit contributions
 Fathers+0.017
DX+0.016
 DX+0.016
 cow+0.016
 resolves+0.016
Neg logit contributions
�醒-0.027
olit-0.024
ult-0.024
sted-0.024
adr-0.023
Token dad
Token ID9955
Feature activation+8.33e-01

Pos logit contributions
�醒+0.132
olit+0.119
ult+0.119
sted+0.118
adr+0.114
Neg logit contributions
DX-0.072
 cow-0.071
 DX-0.070
 Fathers-0.070
 resolves-0.068
Token when
Token ID618
Feature activation-7.25e-02

Pos logit contributions
�醒+0.800
olit+0.729
ult+0.727
sted+0.723
adr+0.702
Neg logit contributions
DX-0.381
 Fathers-0.377
 resolves-0.374
 DX-0.371
 cow-0.369
Token beneficial
Token ID13205
Feature activation-7.51e-01

Pos logit contributions
�醒+0.086
olit+0.077
ult+0.077
sted+0.076
adr+0.074
Neg logit contributions
DX-0.053
 Fathers-0.052
 resolves-0.052
 DX-0.052
 cow-0.051
Token outcome
Token ID8055
Feature activation+6.86e-01

Pos logit contributions
 resolves+0.411
 Fathers+0.409
DX+0.409
 DX+0.407
 cow+0.401
Neg logit contributions
�醒-0.664
olit-0.591
sted-0.589
ult-0.589
adr-0.570
Token would
Token ID561
Feature activation+2.27e-01

Pos logit contributions
�醒+0.576
olit+0.512
sted+0.510
ult+0.508
adr+0.489
Neg logit contributions
 resolves-0.408
 Fathers-0.401
DX-0.398
 DX-0.394
 cow-0.392
Token be
Token ID307
Feature activation+8.52e-02

Pos logit contributions
�醒+0.176
sted+0.156
olit+0.156
ult+0.154
adr+0.150
Neg logit contributions
DX-0.145
 resolves-0.144
 cow-0.143
 Fathers-0.142
 DX-0.142
Token a
Token ID257
Feature activation+5.80e-02

Pos logit contributions
�醒+0.077
olit+0.069
ult+0.069
sted+0.068
adr+0.066
Neg logit contributions
DX-0.045
 resolves-0.044
 Fathers-0.044
 DX-0.044
 cow-0.043
Token draw
Token ID3197
Feature activation-2.36e+00

Pos logit contributions
�醒+0.048
ult+0.043
olit+0.043
sted+0.043
adr+0.041
Neg logit contributions
DX-0.035
 Fathers-0.034
 resolves-0.034
 DX-0.034
 cow-0.033
Token.
Token ID13
Feature activation-7.15e-02

Pos logit contributions
 resolves+1.017
DX+1.003
 DX+0.996
 Fathers+0.993
 cow+0.986
Neg logit contributions
�醒-2.351
olit-2.114
sted-2.110
ult-2.102
adr-2.047
Token In
Token ID554
Feature activation+6.16e-02

Pos logit contributions
DX+0.045
 Fathers+0.045
 DX+0.045
 resolves+0.044
 cow+0.043
Neg logit contributions
�醒-0.057
olit-0.050
ult-0.050
sted-0.050
adr-0.048
Token the
Token ID262
Feature activation+4.15e-01

Pos logit contributions
�醒+0.055
olit+0.049
ult+0.049
sted+0.049
adr+0.047
Neg logit contributions
DX-0.033
 DX-0.032
 Fathers-0.032
 resolves-0.032
 cow-0.031
Token case
Token ID1339
Feature activation-9.51e-02

Pos logit contributions
�醒+0.338
olit+0.303
ult+0.300
sted+0.299
adr+0.287
Neg logit contributions
DX-0.253
 Fathers-0.251
 DX-0.251
 resolves-0.249
 cow-0.246
Token of
Token ID286
Feature activation+2.64e-01

Pos logit contributions
DX+0.046
 Fathers+0.044
 resolves+0.044
 DX+0.044
 cow+0.043
Neg logit contributions
�醒-0.089
olit-0.081
ult-0.081
sted-0.081
adr-0.078
Token presidential
Token ID4787
Feature activation-7.93e-02

Pos logit contributions
 Fathers+0.160
DX+0.160
 resolves+0.159
 DX+0.159
 cow+0.157
Neg logit contributions
�醒-0.272
olit-0.245
ult-0.244
sted-0.243
adr-0.235
Token election
Token ID3071
Feature activation-1.03e-01

Pos logit contributions
 Fathers+0.047
 resolves+0.047
DX+0.047
 DX+0.047
 cow+0.047
Neg logit contributions
�醒-0.065
olit-0.058
ult-0.058
sted-0.058
adr-0.056
Token (
Token ID357
Feature activation-4.76e-01

Pos logit contributions
DX+0.048
 resolves+0.048
 Fathers+0.047
 DX+0.047
 cow+0.046
Neg logit contributions
�醒-0.098
sted-0.089
ult-0.089
olit-0.089
adr-0.085
Tokenor
Token ID273
Feature activation-1.85e-01

Pos logit contributions
DX+0.330
 Fathers+0.319
 resolves+0.317
 DX+0.316
 cow+0.315
Neg logit contributions
�醒-0.355
sted-0.305
olit-0.305
ult-0.297
adr-0.288
Token,
Token ID11
Feature activation-1.58e-01

Pos logit contributions
DX+0.100
 Fathers+0.100
 resolves+0.099
 DX+0.099
 cow+0.098
Neg logit contributions
�醒-0.162
olit-0.146
ult-0.145
sted-0.145
adr-0.140
Token heck
Token ID22574
Feature activation-2.34e+00

Pos logit contributions
DX+0.078
 Fathers+0.077
 resolves+0.076
 DX+0.076
 cow+0.075
Neg logit contributions
�醒-0.147
ult-0.133
olit-0.133
sted-0.132
adr-0.127
Token,
Token ID11
Feature activation-1.65e-01

Pos logit contributions
DX+1.070
 Fathers+1.057
 DX+1.042
 cow+1.033
 resolves+1.032
Neg logit contributions
�醒-2.216
olit-2.022
ult-2.019
sted-2.003
adr-1.957
Token any
Token ID597
Feature activation-2.36e-02

Pos logit contributions
DX+0.090
 Fathers+0.090
 resolves+0.089
 DX+0.089
 cow+0.088
Neg logit contributions
�醒-0.144
olit-0.130
ult-0.129
sted-0.128
adr-0.124
Token political
Token ID1964
Feature activation-4.30e-01

Pos logit contributions
DX+0.012
 Fathers+0.012
 resolves+0.012
 DX+0.012
 cow+0.012
Neg logit contributions
�醒-0.021
olit-0.019
ult-0.019
sted-0.019
adr-0.019
Token event
Token ID1785
Feature activation+5.43e-01

Pos logit contributions
DX+0.239
 resolves+0.238
 Fathers+0.238
 DX+0.237
 cow+0.237
Neg logit contributions
�醒-0.373
olit-0.334
sted-0.333
ult-0.331
adr-0.320
Token of
Token ID286
Feature activation-7.22e-02

Pos logit contributions
�醒+0.513
ult+0.465
olit+0.464
sted+0.462
adr+0.447
Neg logit contributions
DX-0.258
 Fathers-0.254
 resolves-0.252
 DX-0.251
 cow-0.248
Tokenspeed
Token ID12287
Feature activation-9.69e-02

Pos logit contributions
�醒+0.258
olit+0.226
sted+0.221
ult+0.220
adr+0.212
Neg logit contributions
DX-0.250
 DX-0.244
 resolves-0.241
 Fathers-0.241
 cow-0.240
Token pulse
Token ID19445
Feature activation-4.41e-01

Pos logit contributions
DX+0.055
 DX+0.054
 resolves+0.054
 cow+0.053
 Fathers+0.053
Neg logit contributions
�醒-0.084
olit-0.075
sted-0.075
ult-0.074
adr-0.072
Tokenjet
Token ID31173
Feature activation-2.52e-02

Pos logit contributions
DX+0.274
 resolves+0.267
 DX+0.266
 Fathers+0.265
 cow+0.263
Neg logit contributions
�醒-0.352
olit-0.315
ult-0.313
sted-0.312
adr-0.299
Token engine
Token ID3113
Feature activation-4.20e-01

Pos logit contributions
DX+0.015
 resolves+0.015
 DX+0.015
 Fathers+0.015
 cow+0.014
Neg logit contributions
�醒-0.021
olit-0.019
ult-0.019
sted-0.019
adr-0.018
Token suddenly
Token ID6451
Feature activation-8.88e-01

Pos logit contributions
DX+0.251
 resolves+0.250
 DX+0.248
 Fathers+0.247
 cow+0.244
Neg logit contributions
�醒-0.353
olit-0.314
sted-0.312
ult-0.311
adr-0.297
Token starts
Token ID4940
Feature activation-2.32e+00

Pos logit contributions
 resolves+0.497
 Fathers+0.486
DX+0.483
 DX+0.480
 cow+0.479
Neg logit contributions
�醒-0.788
olit-0.701
ult-0.694
sted-0.689
adr-0.669
Token
Token ID198
Feature activation-3.01e-01

Pos logit contributions
 changing+1.068
 DX+1.055
 cow+1.051
 resolves+1.046
 Fathers+1.038
Neg logit contributions
�醒-2.230
olit-2.038
ult-1.980
sted-1.975
adr-1.962
Token
Token ID198
Feature activation-2.22e-01

Pos logit contributions
DX+0.196
 Fathers+0.192
 resolves+0.191
 DX+0.191
 cow+0.187
Neg logit contributions
�醒-0.237
olit-0.208
ult-0.206
sted-0.205
adr-0.196
Tokenmaking
Token ID8601
Feature activation+2.74e-01

Pos logit contributions
DX+0.134
 Fathers+0.128
 DX+0.127
 resolves+0.127
 changing+0.126
Neg logit contributions
�醒-0.186
olit-0.164
sted-0.161
ult-0.157
adr-0.155
Token a
Token ID257
Feature activation+1.02e-01

Pos logit contributions
�醒+0.236
olit+0.213
ult+0.211
sted+0.210
adr+0.204
Neg logit contributions
DX-0.156
 DX-0.154
 Fathers-0.153
 resolves-0.153
 cow-0.151
Token lot
Token ID1256
Feature activation+3.60e-01

Pos logit contributions
�醒+0.088
olit+0.080
ult+0.079
sted+0.078
adr+0.076
Neg logit contributions
DX-0.057
 DX-0.056
 Fathers-0.056
 resolves-0.056
 cow-0.056
Token to
Token ID284
Feature activation-6.52e-01

Pos logit contributions
�醒+0.107
ult+0.097
olit+0.097
sted+0.097
adr+0.093
Neg logit contributions
 resolves-0.055
DX-0.055
 DX-0.054
 Fathers-0.054
 cow-0.053
Token get
Token ID651
Feature activation-2.97e-01

Pos logit contributions
 resolves+0.394
DX+0.387
 cow+0.386
 Fathers+0.384
 DX+0.383
Neg logit contributions
�醒-0.536
olit-0.474
sted-0.470
ult-0.469
adr-0.454
Token out
Token ID503
Feature activation-2.09e-01

Pos logit contributions
DX+0.152
 Fathers+0.150
 resolves+0.150
 DX+0.149
 cow+0.146
Neg logit contributions
�醒-0.267
olit-0.243
ult-0.242
sted-0.240
adr-0.233
Token.
Token ID13
Feature activation-5.88e-01

Pos logit contributions
 Fathers+0.094
 resolves+0.093
DX+0.093
 DX+0.093
 cow+0.091
Neg logit contributions
�醒-0.203
olit-0.183
ult-0.182
sted-0.181
adr-0.176
Token Either
Token ID15467
Feature activation+1.89e-01

Pos logit contributions
DX+0.390
 Fathers+0.382
 DX+0.377
 resolves+0.369
 Allaah+0.364
Neg logit contributions
�醒-0.454
olit-0.404
ult-0.401
sted-0.401
adr-0.379
Token way
Token ID835
Feature activation-2.30e+00

Pos logit contributions
�醒+0.135
olit+0.116
ult+0.116
sted+0.114
adr+0.110
Neg logit contributions
DX-0.136
 Fathers-0.135
 DX-0.135
 resolves-0.135
 cow-0.134
Token,
Token ID11
Feature activation-1.45e-01

Pos logit contributions
 resolves+0.979
DX+0.978
 DX+0.974
 Fathers+0.972
 cow+0.948
Neg logit contributions
�醒-2.278
olit-2.071
ult-2.060
sted-2.042
adr-2.001
Token Kam
Token ID12670
Feature activation+4.09e-01

Pos logit contributions
DX+0.078
 resolves+0.077
 Fathers+0.077
 DX+0.076
 cow+0.075
Neg logit contributions
�醒-0.130
olit-0.116
ult-0.116
sted-0.115
adr-0.111
Tokenal
Token ID282
Feature activation+2.12e-01

Pos logit contributions
�醒+0.266
olit+0.223
ult+0.222
sted+0.221
adr+0.208
Neg logit contributions
DX-0.317
 resolves-0.312
 Fathers-0.312
 DX-0.309
 cow-0.307
Token had
Token ID550
Feature activation-3.99e-01

Pos logit contributions
�醒+0.183
olit+0.163
ult+0.162
sted+0.160
adr+0.155
Neg logit contributions
 resolves-0.120
DX-0.119
 Fathers-0.118
 DX-0.118
 cow-0.117
Token spent
Token ID3377
Feature activation+2.63e-01

Pos logit contributions
DX+0.224
 Fathers+0.222
 resolves+0.222
 DX+0.222
 cow+0.219
Neg logit contributions
�醒-0.342
olit-0.308
ult-0.306
sted-0.305
adr-0.293
Token as
Token ID355
Feature activation-3.45e-02

Pos logit contributions
�醒+0.362
olit+0.329
ult+0.328
sted+0.327
adr+0.316
Neg logit contributions
DX-0.173
 Fathers-0.169
 resolves-0.168
 DX-0.168
 cow-0.165
Token well
Token ID880
Feature activation-3.80e-01

Pos logit contributions
DX+0.021
 Fathers+0.021
 DX+0.021
 resolves+0.021
 cow+0.021
Neg logit contributions
�醒-0.027
olit-0.025
ult-0.025
sted-0.024
adr-0.023
Token,
Token ID11
Feature activation+2.88e-01

Pos logit contributions
DX+0.170
 Fathers+0.168
 resolves+0.166
 DX+0.166
 cow+0.164
Neg logit contributions
�醒-0.369
olit-0.336
ult-0.333
sted-0.333
adr-0.323
Token but
Token ID475
Feature activation+5.37e-02

Pos logit contributions
�醒+0.274
olit+0.250
sted+0.247
ult+0.246
adr+0.238
Neg logit contributions
DX-0.136
 Fathers-0.136
 resolves-0.134
 DX-0.134
 cow-0.132
Token was
Token ID373
Feature activation+3.13e-02

Pos logit contributions
�醒+0.047
olit+0.042
ult+0.041
sted+0.041
adr+0.040
Neg logit contributions
 Fathers-0.030
DX-0.030
 resolves-0.030
 DX-0.030
 cow-0.029
Token drawn
Token ID7428
Feature activation-2.30e+00

Pos logit contributions
�醒+0.027
olit+0.024
ult+0.024
sted+0.024
adr+0.023
Neg logit contributions
DX-0.018
 Fathers-0.018
 resolves-0.017
 DX-0.017
 cow-0.017
Token to
Token ID284
Feature activation-1.23e+00

Pos logit contributions
 Fathers+0.950
 cow+0.950
 DX+0.943
DX+0.943
 resolves+0.932
Neg logit contributions
�醒-2.305
ult-2.100
olit-2.096
sted-2.088
adr-2.043
Token the
Token ID262
Feature activation-4.51e-01

Pos logit contributions
 Fathers+0.619
 DX+0.616
DX+0.615
 cow+0.612
 resolves+0.610
Neg logit contributions
�醒-1.129
olit-1.022
sted-1.012
ult-1.009
adr-0.977
Token speed
Token ID2866
Feature activation-7.09e-01

Pos logit contributions
 Fathers+0.224
DX+0.222
 DX+0.222
 cow+0.219
 resolves+0.217
Neg logit contributions
�醒-0.421
olit-0.380
sted-0.377
ult-0.376
adr-0.363
Token and
Token ID290
Feature activation+4.39e-01

Pos logit contributions
DX+0.336
 Fathers+0.328
 DX+0.325
 resolves+0.324
 cow+0.321
Neg logit contributions
�醒-0.672
olit-0.611
ult-0.608
sted-0.607
adr-0.585
Token physical
Token ID3518
Feature activation+1.59e-01

Pos logit contributions
�醒+0.367
olit+0.326
ult+0.325
sted+0.324
adr+0.310
Neg logit contributions
DX-0.260
 Fathers-0.258
 resolves-0.258
 DX-0.257
 cow-0.255
Tokencultural
Token ID30844
Feature activation+8.02e-01

Pos logit contributions
DX+0.307
 Fathers+0.299
 resolves+0.294
 DX+0.294
 cow+0.293
Neg logit contributions
�醒-0.341
olit-0.299
sted-0.298
ult-0.295
adr-0.283
Token issues
Token ID2428
Feature activation-8.60e-02

Pos logit contributions
�醒+1.006
olit+0.941
ult+0.938
sted+0.936
adr+0.913
Neg logit contributions
DX-0.134
 resolves-0.125
 Fathers-0.124
 DX-0.123
 cow-0.119
Token.
Token ID13
Feature activation-2.15e-01

Pos logit contributions
DX+0.035
 Fathers+0.035
 resolves+0.034
 cow+0.034
 DX+0.034
Neg logit contributions
�醒-0.087
olit-0.079
ult-0.079
sted-0.079
adr-0.076
Token
Token ID198
Feature activation+6.18e-02

Pos logit contributions
 Fathers+0.139
 DX+0.134
DX+0.134
 Downs+0.130
 resolves+0.130
Neg logit contributions
�醒-0.171
olit-0.153
ult-0.152
sted-0.149
adr-0.144
Token
Token ID198
Feature activation-1.82e-01

Pos logit contributions
�醒+0.048
olit+0.042
ult+0.042
sted+0.042
adr+0.040
Neg logit contributions
DX-0.040
 Fathers-0.040
 resolves-0.039
 DX-0.039
 cow-0.039
TokenUpdate
Token ID10260
Feature activation-2.25e+00

Pos logit contributions
DX+0.124
 Fathers+0.118
 DX+0.116
 resolves+0.115
 cow+0.114
Neg logit contributions
�醒-0.139
olit-0.122
sted-0.119
ult-0.119
adr-0.114
Token:
Token ID25
Feature activation-9.45e-01

Pos logit contributions
DX+1.095
 DX+1.091
 resolves+1.084
 Fathers+1.081
 cow+1.066
Neg logit contributions
�醒-2.093
ult-1.880
olit-1.862
sted-1.857
adr-1.811
Token The
Token ID383
Feature activation-3.91e-01

Pos logit contributions
 Fathers+0.612
 DX+0.605
DX+0.604
 resolves+0.596
 cow+0.594
Neg logit contributions
�醒-0.737
ult-0.651
olit-0.647
sted-0.637
adr-0.619
Token Hill
Token ID3327
Feature activation+9.40e-01

Pos logit contributions
 Fathers+0.237
 DX+0.235
DX+0.234
 cow+0.234
 resolves+0.230
Neg logit contributions
�醒-0.322
olit-0.287
ult-0.284
sted-0.282
adr-0.273
Token reports
Token ID3136
Feature activation-8.31e-01

Pos logit contributions
�醒+0.767
ult+0.688
olit+0.688
sted+0.678
adr+0.655
Neg logit contributions
DX-0.571
 resolves-0.566
 Fathers-0.564
 DX-0.558
 cow-0.550
Token,
Token ID11
Feature activation-1.58e-01

Pos logit contributions
 Fathers+0.377
DX+0.374
 DX+0.373
 resolves+0.368
 cow+0.366
Neg logit contributions
�醒-0.794
ult-0.727
olit-0.725
sted-0.721
adr-0.704
Token all
Token ID477
Feature activation-1.67e-01

Pos logit contributions
�醒+0.158
olit+0.144
ult+0.143
sted+0.142
adr+0.140
Neg logit contributions
DX-0.077
 DX-0.075
 resolves-0.075
 Fathers-0.075
 cow-0.074
Token.
Token ID13
Feature activation-2.60e-01

Pos logit contributions
DX+0.070
 resolves+0.069
 Fathers+0.069
 DX+0.069
 cow+0.068
Neg logit contributions
�醒-0.167
sted-0.153
olit-0.152
ult-0.152
adr-0.148
Token
Token ID198
Feature activation-9.20e-02

Pos logit contributions
 Fathers+0.164
DX+0.163
 DX+0.163
 resolves+0.159
 Downs+0.156
Neg logit contributions
�醒-0.208
olit-0.186
ult-0.185
sted-0.182
adr-0.175
Token
Token ID198
Feature activation-2.32e-01

Pos logit contributions
DX+0.060
 Fathers+0.059
 resolves+0.059
 DX+0.059
 cow+0.058
Neg logit contributions
�醒-0.071
olit-0.063
ult-0.062
sted-0.062
adr-0.059
Token(
Token ID7
Feature activation+4.36e-01

Pos logit contributions
DX+0.126
 DX+0.116
 Fathers+0.115
 resolves+0.114
 cow+0.111
Neg logit contributions
�醒-0.209
olit-0.190
ult-0.185
sted-0.185
adr-0.178
Token UPDATE
Token ID35717
Feature activation-2.24e+00

Pos logit contributions
�醒+0.337
olit+0.301
ult+0.298
sted+0.297
adr+0.285
Neg logit contributions
DX-0.289
 Fathers-0.278
 DX-0.276
 resolves-0.275
 cow-0.269
Token:
Token ID25
Feature activation-1.12e+00

Pos logit contributions
DX+1.135
 DX+1.134
 resolves+1.102
 Fathers+1.094
 cow+1.078
Neg logit contributions
�醒-2.053
ult-1.852
olit-1.852
sted-1.841
adr-1.772
Token Sherman
Token ID23198
Feature activation-6.98e-01

Pos logit contributions
DX+0.690
 DX+0.685
 Fathers+0.685
 resolves+0.675
 cow+0.659
Neg logit contributions
�醒-0.911
olit-0.808
ult-0.805
sted-0.798
adr-0.773
Token suffered
Token ID6989
Feature activation-5.02e-01

Pos logit contributions
 resolves+0.409
DX+0.401
 DX+0.401
 Fathers+0.400
 cow+0.397
Neg logit contributions
�醒-0.590
olit-0.527
ult-0.520
sted-0.518
adr-0.505
Token a
Token ID257
Feature activation-1.87e-01

Pos logit contributions
DX+0.307
 resolves+0.305
 DX+0.304
 Fathers+0.303
 cow+0.301
Neg logit contributions
�醒-0.404
olit-0.362
ult-0.362
sted-0.359
adr-0.345
Token rupt
Token ID31580
Feature activation+4.26e-01

Pos logit contributions
DX+0.102
 DX+0.101
 Fathers+0.100
 resolves+0.100
 cow+0.100
Neg logit contributions
�醒-0.163
ult-0.148
olit-0.148
sted-0.147
adr-0.141
Token remarks
Token ID10252
Feature activation-2.18e-01

Pos logit contributions
 Fathers+0.130
 cow+0.128
 DX+0.128
DX+0.127
 changing+0.126
Neg logit contributions
�醒-0.184
olit-0.165
sted-0.163
ult-0.162
adr-0.157
Token he
Token ID339
Feature activation-9.03e-01

Pos logit contributions
 Fathers+0.098
DX+0.097
 resolves+0.096
 DX+0.096
 cow+0.096
Neg logit contributions
�醒-0.211
olit-0.191
sted-0.190
ult-0.190
adr-0.185
Token made
Token ID925
Feature activation-1.11e+00

Pos logit contributions
DX+0.444
 resolves+0.442
 cow+0.440
 Fathers+0.439
 DX+0.438
Neg logit contributions
�醒-0.838
olit-0.756
sted-0.750
ult-0.749
adr-0.724
Token about
Token ID546
Feature activation-7.57e-01

Pos logit contributions
 Fathers+0.525
DX+0.524
 resolves+0.524
 DX+0.524
 cow+0.521
Neg logit contributions
�醒-1.056
olit-0.946
sted-0.937
ult-0.934
adr-0.920
Token his
Token ID465
Feature activation-1.82e-01

Pos logit contributions
 Fathers+0.453
 cow+0.451
 DX+0.449
 changing+0.443
DX+0.443
Neg logit contributions
�醒-0.623
olit-0.562
ult-0.556
sted-0.551
adr-0.535
Token fellow
Token ID5891
Feature activation-2.22e+00

Pos logit contributions
 Fathers+0.106
 cow+0.103
 DX+0.103
 resolves+0.103
DX+0.103
Neg logit contributions
�醒-0.155
olit-0.139
ult-0.137
sted-0.137
adr-0.132
Token GOP
Token ID6796
Feature activation+1.05e-01

Pos logit contributions
 Fathers+1.168
 cow+1.138
 DX+1.114
 resolves+1.084
DX+1.081
Neg logit contributions
�醒-2.019
olit-1.832
ult-1.800
sted-1.781
adr-1.747
Token presidential
Token ID4787
Feature activation+1.14e+00

Pos logit contributions
�醒+0.091
olit+0.082
sted+0.082
ult+0.082
adr+0.080
Neg logit contributions
 Fathers-0.057
 cow-0.057
DX-0.057
 resolves-0.056
 DX-0.056
Token contender
Token ID24190
Feature activation+4.75e-01

Pos logit contributions
�醒+0.924
olit+0.826
sted+0.820
ult+0.819
adr+0.790
Neg logit contributions
 Fathers-0.694
 cow-0.687
 resolves-0.686
DX-0.685
 DX-0.682
Token in
Token ID287
Feature activation+3.90e-01

Pos logit contributions
�醒+0.442
olit+0.406
ult+0.400
sted+0.400
adr+0.391
Neg logit contributions
DX-0.230
 Fathers-0.229
 DX-0.226
 resolves-0.226
 cow-0.223
Token a
Token ID257
Feature activation+9.74e-02

Pos logit contributions
�醒+0.328
olit+0.296
sted+0.292
ult+0.291
adr+0.281
Neg logit contributions
DX-0.227
 Fathers-0.227
 DX-0.226
 resolves-0.224
 cow-0.223
Token Hulu
Token ID39739
Feature activation+7.31e-01

Pos logit contributions
�醒+0.012
olit+0.010
sted+0.010
ult+0.010
adr+0.010
Neg logit contributions
DX-0.017
 DX-0.017
 Fathers-0.017
 resolves-0.016
 cow-0.016
Token Plus
Token ID8227
Feature activation+4.67e-01

Pos logit contributions
�醒+0.672
ult+0.616
olit+0.615
sted+0.612
adr+0.588
Neg logit contributions
DX-0.361
 Fathers-0.352
 resolves-0.350
 DX-0.347
 cow-0.341
Token,
Token ID11
Feature activation+1.80e-01

Pos logit contributions
�醒+0.436
ult+0.400
olit+0.399
sted+0.397
adr+0.382
Neg logit contributions
DX-0.225
 Fathers-0.219
 resolves-0.218
 DX-0.216
 cow-0.212
Token and
Token ID290
Feature activation+5.81e-01

Pos logit contributions
�醒+0.162
olit+0.146
sted+0.145
ult+0.145
adr+0.140
Neg logit contributions
DX-0.095
 Fathers-0.095
 DX-0.094
 resolves-0.093
 cow-0.091
Token Amazon
Token ID6186
Feature activation-7.02e-01

Pos logit contributions
�醒+0.477
olit+0.424
ult+0.422
sted+0.421
adr+0.406
Neg logit contributions
DX-0.353
 Fathers-0.351
 DX-0.350
 resolves-0.347
 cow-0.342
Token Prime
Token ID5537
Feature activation-2.21e+00

Pos logit contributions
DX+0.451
 resolves+0.444
 DX+0.441
 Fathers+0.441
 cow+0.434
Neg logit contributions
�醒-0.558
olit-0.499
ult-0.491
sted-0.487
adr-0.476
Token offer
Token ID2897
Feature activation-8.83e-02

Pos logit contributions
DX+1.377
 DX+1.366
 Fathers+1.349
 resolves+1.346
 cow+1.336
Neg logit contributions
�醒-1.827
olit-1.603
ult-1.581
sted-1.572
adr-1.553
Token much
Token ID881
Feature activation-9.34e-02

Pos logit contributions
DX+0.048
 DX+0.048
 resolves+0.048
 Fathers+0.048
 cow+0.047
Neg logit contributions
�醒-0.078
olit-0.070
ult-0.070
sted-0.069
adr-0.067
Token of
Token ID286
Feature activation+6.71e-01

Pos logit contributions
DX+0.039
 Fathers+0.038
 DX+0.038
 resolves+0.038
 cow+0.037
Neg logit contributions
�醒-0.094
ult-0.086
olit-0.085
sted-0.085
adr-0.082
Token the
Token ID262
Feature activation-7.87e-02

Pos logit contributions
�醒+0.632
olit+0.574
ult+0.571
sted+0.568
adr+0.553
Neg logit contributions
DX-0.325
 DX-0.319
 Fathers-0.316
 resolves-0.313
 cow-0.310
Token same
Token ID976
Feature activation+1.49e-01

Pos logit contributions
DX+0.046
 DX+0.046
 Fathers+0.046
 resolves+0.045
 cow+0.045
Neg logit contributions
�醒-0.067
olit-0.060
ult-0.059
sted-0.059
adr-0.056
Token be
Token ID307
Feature activation+4.25e-01

Pos logit contributions
 cow+0.295
 Fathers+0.294
DX+0.292
 resolves+0.292
 DX+0.289
Neg logit contributions
�醒-0.368
olit-0.328
ult-0.324
sted-0.323
adr-0.310
Token able
Token ID1498
Feature activation-7.77e-01

Pos logit contributions
�醒+0.342
olit+0.306
ult+0.305
sted+0.300
adr+0.289
Neg logit contributions
 Fathers-0.260
DX-0.260
 cow-0.259
 resolves-0.258
 DX-0.258
Token to
Token ID284
Feature activation-3.84e-01

Pos logit contributions
DX+0.330
 Fathers+0.329
 resolves+0.326
 cow+0.323
 DX+0.322
Neg logit contributions
�醒-0.778
ult-0.701
olit-0.700
sted-0.694
adr-0.672
Token get
Token ID651
Feature activation-4.76e-01

Pos logit contributions
 cow+0.254
DX+0.254
 Fathers+0.254
 resolves+0.253
 DX+0.251
Neg logit contributions
�醒-0.289
olit-0.257
ult-0.255
sted-0.253
adr-0.242
Token green
Token ID4077
Feature activation-1.88e-01

Pos logit contributions
 Fathers+0.271
DX+0.267
 DX+0.266
 cow+0.265
 resolves+0.265
Neg logit contributions
�醒-0.404
olit-0.366
ult-0.364
sted-0.358
adr-0.348
Token cards
Token ID4116
Feature activation-2.20e+00

Pos logit contributions
 Fathers+0.054
 cow+0.053
 DX+0.052
 resolves+0.052
DX+0.052
Neg logit contributions
�醒-0.209
olit-0.196
ult-0.195
sted-0.193
adr-0.189
Token for
Token ID329
Feature activation-9.15e-01

Pos logit contributions
 resolves+0.989
 Fathers+0.989
 cow+0.979
DX+0.976
 DX+0.971
Neg logit contributions
�醒-2.134
olit-1.922
ult-1.912
sted-1.895
adr-1.852
Token their
Token ID511
Feature activation-5.03e-01

Pos logit contributions
 Fathers+0.486
 resolves+0.478
 cow+0.476
DX+0.475
 DX+0.475
Neg logit contributions
�醒-0.822
olit-0.738
ult-0.732
sted-0.722
adr-0.705
Token spouses
Token ID30250
Feature activation-1.79e-01

Pos logit contributions
 Fathers+0.229
 resolves+0.224
DX+0.223
 DX+0.222
 cow+0.222
Neg logit contributions
�醒-0.492
olit-0.442
ult-0.442
sted-0.439
adr-0.426
Token and
Token ID290
Feature activation+2.62e-01

Pos logit contributions
 Fathers+0.076
 resolves+0.075
DX+0.075
 cow+0.075
 DX+0.074
Neg logit contributions
�醒-0.179
olit-0.162
ult-0.161
sted-0.160
adr-0.156
Token minor
Token ID4159
Feature activation-4.29e-01

Pos logit contributions
�醒+0.268
ult+0.241
olit+0.239
sted+0.239
adr+0.233
Neg logit contributions
 Fathers-0.108
 resolves-0.107
DX-0.105
 cow-0.105
 DX-0.104
Tokento
Token ID1462
Feature activation+6.92e-01

Pos logit contributions
DX+0.053
 Fathers+0.051
 DX+0.051
 resolves+0.051
 cow+0.049
Neg logit contributions
�醒-0.131
olit-0.120
ult-0.119
sted-0.118
adr-0.116
Token-
Token ID12
Feature activation+6.37e-01

Pos logit contributions
�醒+0.571
ult+0.517
olit+0.517
sted+0.513
adr+0.492
Neg logit contributions
DX-0.408
 Fathers-0.399
 resolves-0.397
 DX-0.395
 cow-0.389
Tokenfemale
Token ID24724
Feature activation-9.58e-01

Pos logit contributions
�醒+0.486
olit+0.434
ult+0.432
sted+0.431
adr+0.412
Neg logit contributions
DX-0.418
 Fathers-0.408
 resolves-0.405
 DX-0.405
 cow-0.399
Token (
Token ID357
Feature activation-2.09e-01

Pos logit contributions
DX+0.536
 resolves+0.534
 DX+0.530
 Fathers+0.530
 cow+0.514
Neg logit contributions
�醒-0.831
olit-0.746
ult-0.740
sted-0.735
adr-0.718
TokenM
Token ID44
Feature activation-9.67e-01

Pos logit contributions
DX+0.141
 Fathers+0.136
 DX+0.134
 resolves+0.133
 cow+0.130
Neg logit contributions
�醒-0.158
olit-0.141
sted-0.141
ult-0.139
adr-0.133
TokenTF
Token ID10234
Feature activation-2.17e+00

Pos logit contributions
DX+0.688
 DX+0.664
 Fathers+0.661
 resolves+0.659
 cow+0.644
Neg logit contributions
�醒-0.708
olit-0.608
sted-0.608
ult-0.607
adr-0.576
Token)
Token ID8
Feature activation-7.63e-02

Pos logit contributions
DX+0.957
 DX+0.918
 Fathers+0.917
 resolves+0.914
 cow+0.889
Neg logit contributions
�醒-2.132
ult-1.950
olit-1.950
sted-1.939
adr-1.875
Token transgender
Token ID10637
Feature activation-9.08e-01

Pos logit contributions
DX+0.045
 resolves+0.044
 Fathers+0.044
 DX+0.044
 cow+0.043
Neg logit contributions
�醒-0.064
olit-0.057
ult-0.057
sted-0.057
adr-0.055
Token people
Token ID661
Feature activation-2.40e-01

Pos logit contributions
DX+0.400
 Fathers+0.391
 resolves+0.390
 DX+0.390
 cow+0.378
Neg logit contributions
�醒-0.893
ult-0.813
olit-0.811
sted-0.806
adr-0.788
Token are
Token ID389
Feature activation-6.96e-01

Pos logit contributions
DX+0.149
 resolves+0.148
 Fathers+0.148
 DX+0.146
 cow+0.145
Neg logit contributions
�醒-0.194
ult-0.172
olit-0.171
sted-0.171
adr-0.164
Token born
Token ID4642
Feature activation-8.73e-01

Pos logit contributions
DX+0.452
 Fathers+0.450
 DX+0.448
 resolves+0.445
 cow+0.440
Neg logit contributions
�醒-0.548
ult-0.479
olit-0.476
sted-0.472
adr-0.457
Token that
Token ID326
Feature activation+2.72e-01

Pos logit contributions
 Fathers+0.065
DX+0.065
 DX+0.064
 resolves+0.064
 cow+0.063
Neg logit contributions
�醒-0.111
olit-0.100
ult-0.099
sted-0.099
adr-0.096
Token
Token ID564
Feature activation-7.77e-01

Pos logit contributions
�醒+0.245
olit+0.222
sted+0.219
ult+0.218
adr+0.212
Neg logit contributions
DX-0.144
 Fathers-0.142
 DX-0.142
 resolves-0.140
 cow-0.139
Token
Token ID250
Feature activation-1.38e-02

Pos logit contributions
DX+0.543
 DX+0.530
 Fathers+0.529
 resolves+0.524
 cow+0.523
Neg logit contributions
�醒-0.541
olit-0.495
sted-0.494
ult-0.493
adr-0.465
TokenTal
Token ID31466
Feature activation-1.55e-01

Pos logit contributions
DX+0.009
 DX+0.009
 Fathers+0.009
 resolves+0.009
 cow+0.009
Neg logit contributions
�醒-0.011
olit-0.009
sted-0.009
ult-0.009
adr-0.009
Tokenent
Token ID298
Feature activation-7.61e-01

Pos logit contributions
DX+0.107
 DX+0.105
 Fathers+0.105
 resolves+0.103
 cow+0.102
Neg logit contributions
�醒-0.115
olit-0.100
ult-0.100
sted-0.099
adr-0.094
Token hits
Token ID7127
Feature activation-2.16e+00

Pos logit contributions
DX+0.474
 Fathers+0.458
 resolves+0.458
 DX+0.457
 cow+0.449
Neg logit contributions
�醒-0.615
olit-0.546
ult-0.544
sted-0.538
adr-0.520
Token a
Token ID257
Feature activation-2.91e-01

Pos logit contributions
 DX+1.183
 cow+1.173
DX+1.171
 resolves+1.159
 Fathers+1.153
Neg logit contributions
�醒-1.930
olit-1.698
ult-1.670
sted-1.654
adr-1.624
Token target
Token ID2496
Feature activation-5.02e-01

Pos logit contributions
DX+0.164
 Fathers+0.162
 DX+0.162
 cow+0.162
 resolves+0.159
Neg logit contributions
�醒-0.249
olit-0.225
ult-0.225
sted-0.220
adr-0.213
Token no
Token ID645
Feature activation-8.35e-02

Pos logit contributions
DX+0.269
 DX+0.263
 cow+0.259
 resolves+0.258
 Fathers+0.257
Neg logit contributions
�醒-0.448
olit-0.405
ult-0.404
sted-0.397
adr-0.387
Token one
Token ID530
Feature activation-6.33e-01

Pos logit contributions
DX+0.051
 DX+0.050
 cow+0.050
 resolves+0.049
 Fathers+0.049
Neg logit contributions
�醒-0.067
olit-0.061
sted-0.061
ult-0.060
adr-0.058
Token else
Token ID2073
Feature activation+3.69e-01

Pos logit contributions
 resolves+0.358
 Fathers+0.351
DX+0.348
 cow+0.347
 DX+0.346
Neg logit contributions
�醒-0.559
olit-0.493
ult-0.491
sted-0.487
adr-0.468
Token at
Token ID379
Feature activation-1.81e-01

Pos logit contributions
�醒+0.729
ult+0.660
olit+0.659
sted+0.654
adr+0.632
Neg logit contributions
DX-0.391
 resolves-0.383
 Fathers-0.382
 DX-0.381
 cow-0.376
Token 2
Token ID362
Feature activation+3.16e-02

Pos logit contributions
DX+0.089
 DX+0.088
 Fathers+0.088
 resolves+0.088
 cow+0.087
Neg logit contributions
�醒-0.168
ult-0.152
olit-0.152
sted-0.149
adr-0.147
Token:
Token ID25
Feature activation+6.06e-02

Pos logit contributions
�醒+0.028
olit+0.025
ult+0.025
sted+0.025
adr+0.024
Neg logit contributions
DX-0.017
 resolves-0.016
 Fathers-0.016
 DX-0.016
 cow-0.016
Token21
Token ID2481
Feature activation+6.37e-02

Pos logit contributions
�醒+0.048
olit+0.042
ult+0.041
sted+0.041
adr+0.039
Neg logit contributions
DX-0.040
 Fathers-0.039
 DX-0.039
 resolves-0.039
 cow-0.038
Token?
Token ID30
Feature activation-6.11e-01

Pos logit contributions
�醒+0.060
olit+0.055
ult+0.055
sted+0.054
adr+0.052
Neg logit contributions
DX-0.031
 resolves-0.030
 DX-0.030
 Fathers-0.029
 cow-0.029
Token Depending
Token ID23591
Feature activation-2.15e+00

Pos logit contributions
DX+0.400
 Fathers+0.391
 DX+0.391
 resolves+0.389
 cow+0.382
Neg logit contributions
�醒-0.474
olit-0.423
ult-0.417
sted-0.417
adr-0.395
Token on
Token ID319
Feature activation-2.00e-01

Pos logit contributions
DX+1.049
 resolves+1.019
 DX+1.008
 cow+1.005
 Fathers+1.002
Neg logit contributions
�醒-2.011
olit-1.815
ult-1.795
sted-1.793
adr-1.727
Token where
Token ID810
Feature activation-3.19e-01

Pos logit contributions
DX+0.101
 DX+0.099
 Fathers+0.099
 resolves+0.099
 cow+0.096
Neg logit contributions
�醒-0.186
olit-0.168
ult-0.167
sted-0.165
adr-0.160
Token the
Token ID262
Feature activation-5.90e-01

Pos logit contributions
DX+0.152
 DX+0.148
 Fathers+0.148
 resolves+0.148
 cow+0.145
Neg logit contributions
�醒-0.306
olit-0.276
ult-0.275
sted-0.274
adr-0.264
Token diss
Token ID6249
Feature activation-8.52e-01

Pos logit contributions
DX+0.324
 resolves+0.322
 Fathers+0.321
 DX+0.320
 cow+0.318
Neg logit contributions
�醒-0.518
olit-0.466
ult-0.465
sted-0.461
adr-0.443
Tokenents
Token ID658
Feature activation-3.65e-01

Pos logit contributions
DX+0.545
 resolves+0.542
 Fathers+0.538
 DX+0.525
 cow+0.522
Neg logit contributions
�醒-0.671
sted-0.591
olit-0.582
ult-0.571
adr-0.560
Token.
Token ID13
Feature activation-3.08e-01

Pos logit contributions
DX+0.165
 DX+0.161
 Fathers+0.159
 resolves+0.158
 cow+0.156
Neg logit contributions
�醒-0.394
olit-0.362
ult-0.360
sted-0.358
adr-0.346
Token Then
Token ID3244
Feature activation+1.96e-01

Pos logit contributions
DX+0.200
 DX+0.198
 Fathers+0.198
 resolves+0.192
 cow+0.190
Neg logit contributions
�醒-0.244
olit-0.216
ult-0.214
sted-0.211
adr-0.201
Token the
Token ID262
Feature activation-2.70e-01

Pos logit contributions
�醒+0.168
olit+0.150
ult+0.149
sted+0.148
adr+0.143
Neg logit contributions
DX-0.114
 DX-0.112
 Fathers-0.111
 resolves-0.111
 cow-0.109
Token groups
Token ID2628
Feature activation+1.76e-01

Pos logit contributions
DX+0.149
 Fathers+0.147
 DX+0.146
 resolves+0.145
 cow+0.144
Neg logit contributions
�醒-0.238
olit-0.213
sted-0.212
ult-0.211
adr-0.203
Token were
Token ID547
Feature activation-4.18e-01

Pos logit contributions
�醒+0.157
olit+0.141
ult+0.141
sted+0.140
adr+0.135
Neg logit contributions
DX-0.094
 DX-0.093
 Fathers-0.092
 resolves-0.091
 cow-0.091
Token drawn
Token ID7428
Feature activation-2.14e+00

Pos logit contributions
DX+0.210
 resolves+0.206
 Fathers+0.206
 DX+0.205
 cow+0.202
Neg logit contributions
�醒-0.383
ult-0.349
olit-0.348
sted-0.345
adr-0.333
Token,
Token ID11
Feature activation-3.64e-01

Pos logit contributions
DX+0.942
 DX+0.937
 resolves+0.933
 Fathers+0.919
 cow+0.910
Neg logit contributions
�醒-2.117
olit-1.905
ult-1.901
sted-1.872
adr-1.839
Token and
Token ID290
Feature activation-4.19e-01

Pos logit contributions
DX+0.170
 DX+0.167
 Fathers+0.166
 resolves+0.166
 cow+0.161
Neg logit contributions
�醒-0.350
olit-0.318
ult-0.317
sted-0.315
adr-0.304
Token it
Token ID340
Feature activation+8.34e-02

Pos logit contributions
DX+0.236
 DX+0.235
 Fathers+0.232
 resolves+0.230
 cow+0.228
Neg logit contributions
�醒-0.369
olit-0.329
ult-0.327
sted-0.324
adr-0.311
Token got
Token ID1392
Feature activation+7.00e-01

Pos logit contributions
�醒+0.067
olit+0.060
ult+0.058
sted+0.058
adr+0.057
Neg logit contributions
 resolves-0.052
DX-0.051
 cow-0.051
 Fathers-0.051
 DX-0.050
Token way
Token ID835
Feature activation-1.07e+00

Pos logit contributions
�醒+0.603
ult+0.545
olit+0.545
sted+0.540
adr+0.522
Neg logit contributions
DX-0.392
 Fathers-0.384
 resolves-0.382
 DX-0.382
 cow-0.375
Token who
Token ID508
Feature activation-1.08e-01

Pos logit contributions
�醒+0.183
olit+0.163
ult+0.162
sted+0.162
adr+0.156
Neg logit contributions
 Fathers-0.129
DX-0.129
 resolves-0.128
 DX-0.128
 cow-0.127
Token played
Token ID2826
Feature activation+5.53e-02

Pos logit contributions
 resolves+0.063
 Fathers+0.062
DX+0.062
 cow+0.062
 DX+0.061
Neg logit contributions
�醒-0.090
olit-0.080
sted-0.079
ult-0.079
adr-0.076
Token behind
Token ID2157
Feature activation-3.33e-01

Pos logit contributions
�醒+0.050
ult+0.045
olit+0.045
sted+0.045
adr+0.044
Neg logit contributions
DX-0.029
 DX-0.028
 resolves-0.028
 Fathers-0.028
 cow-0.028
Token Hall
Token ID4789
Feature activation+1.05e+00

Pos logit contributions
DX+0.196
 DX+0.195
 Fathers+0.194
 resolves+0.193
 cow+0.192
Neg logit contributions
�醒-0.274
olit-0.247
ult-0.246
sted-0.245
adr-0.236
Token on
Token ID319
Feature activation+3.80e-01

Pos logit contributions
�醒+1.013
olit+0.919
ult+0.918
sted+0.910
adr+0.886
Neg logit contributions
DX-0.479
 Fathers-0.472
 DX-0.467
 resolves-0.464
 cow-0.463
Token Wednesday
Token ID3583
Feature activation+1.41e+00

Pos logit contributions
�醒+0.345
olit+0.312
ult+0.311
sted+0.309
adr+0.301
Neg logit contributions
DX-0.195
 Fathers-0.192
 DX-0.192
 resolves-0.189
 cow-0.189
Token,
Token ID11
Feature activation+2.95e-01

Pos logit contributions
�醒+1.338
olit+1.223
ult+1.218
sted+1.216
adr+1.175
Neg logit contributions
DX-0.663
 Fathers-0.649
 resolves-0.645
 DX-0.643
 cow-0.633
Token didn
Token ID1422
Feature activation+5.05e-01

Pos logit contributions
�醒+0.239
olit+0.210
ult+0.209
sted+0.208
adr+0.201
Neg logit contributions
 resolves-0.182
 Fathers-0.180
DX-0.180
 DX-0.179
 cow-0.178
Token
Token ID447
Feature activation+4.63e-01

Pos logit contributions
�醒+0.275
olit+0.225
ult+0.222
sted+0.220
adr+0.207
Neg logit contributions
DX-0.448
 Fathers-0.444
 resolves-0.440
 DX-0.439
 cow-0.435
Token
Token ID247
Feature activation+5.24e-01

Pos logit contributions
�醒+0.266
olit+0.230
sted+0.228
ult+0.228
adr+0.212
Neg logit contributions
DX-0.389
 Fathers-0.384
 resolves-0.382
 DX-0.380
 cow-0.377
Tokent
Token ID83
Feature activation+8.81e-02

Pos logit contributions
�醒+0.416
olit+0.369
ult+0.366
sted+0.364
adr+0.350
Neg logit contributions
DX-0.332
 Fathers-0.325
 resolves-0.324
 DX-0.321
 cow-0.317
Token their
Token ID511
Feature activation+1.51e-01

Pos logit contributions
DX+0.066
 resolves+0.064
 DX+0.064
 Fathers+0.064
 cow+0.063
Neg logit contributions
�醒-0.115
olit-0.104
ult-0.104
sted-0.103
adr-0.100
Token final
Token ID2457
Feature activation-3.91e-01

Pos logit contributions
�醒+0.130
ult+0.117
olit+0.117
sted+0.116
adr+0.112
Neg logit contributions
DX-0.084
 Fathers-0.083
 resolves-0.083
 DX-0.083
 cow-0.081
Token game
Token ID983
Feature activation-1.33e-01

Pos logit contributions
DX+0.193
 DX+0.191
 resolves+0.190
 Fathers+0.190
 cow+0.188
Neg logit contributions
�醒-0.360
olit-0.328
ult-0.327
sted-0.325
adr-0.314
Token against
Token ID1028
Feature activation+6.54e-01

Pos logit contributions
DX+0.060
 resolves+0.060
 DX+0.060
 Fathers+0.059
 cow+0.059
Neg logit contributions
�醒-0.129
olit-0.117
ult-0.117
sted-0.116
adr-0.113
Token Saudi
Token ID7420
Feature activation+3.50e-01

Pos logit contributions
�醒+0.570
olit+0.512
ult+0.509
sted+0.506
adr+0.486
Neg logit contributions
DX-0.363
 Fathers-0.359
 DX-0.359
 resolves-0.357
 cow-0.352
Token Arabia
Token ID9671
Feature activation+1.45e+00

Pos logit contributions
�醒+0.380
olit+0.354
ult+0.351
sted+0.349
adr+0.339
Neg logit contributions
DX-0.115
 resolves-0.112
 Fathers-0.111
 DX-0.111
 cow-0.108
Token.
Token ID13
Feature activation+5.67e-02

Pos logit contributions
�醒+1.384
olit+1.265
ult+1.264
sted+1.258
adr+1.214
Neg logit contributions
DX-0.677
 Fathers-0.662
 resolves-0.660
 DX-0.655
 cow-0.643
Token
Token ID198
Feature activation+3.63e-01

Pos logit contributions
�醒+0.045
olit+0.040
ult+0.039
sted+0.039
adr+0.037
Neg logit contributions
DX-0.036
 Fathers-0.036
 DX-0.036
 resolves-0.036
 cow-0.035
Token
Token ID198
Feature activation+6.37e-02

Pos logit contributions
�醒+0.275
olit+0.244
ult+0.244
sted+0.242
adr+0.231
Neg logit contributions
DX-0.242
 Fathers-0.238
 resolves-0.236
 DX-0.236
 cow-0.232
TokenIf
Token ID1532
Feature activation-6.10e-01

Pos logit contributions
�醒+0.050
olit+0.044
sted+0.043
ult+0.043
adr+0.041
Neg logit contributions
DX-0.042
 Fathers-0.040
 DX-0.040
 resolves-0.040
 cow-0.039
Token that
Token ID326
Feature activation+4.57e-01

Pos logit contributions
DX+0.328
 resolves+0.325
 DX+0.324
 Fathers+0.323
 cow+0.318
Neg logit contributions
�醒-0.541
olit-0.487
ult-0.483
sted-0.481
adr-0.467
Token President
Token ID1992
Feature activation-3.29e-01

Pos logit contributions
 Fathers+0.020
DX+0.020
 resolves+0.020
 DX+0.020
 cow+0.019
Neg logit contributions
�醒-0.028
olit-0.025
ult-0.025
sted-0.025
adr-0.024
Token Men
Token ID6065
Feature activation+3.04e-01

Pos logit contributions
 Fathers+0.226
DX+0.224
 resolves+0.224
 DX+0.222
 cow+0.220
Neg logit contributions
�醒-0.244
olit-0.210
sted-0.210
ult-0.209
adr-0.202
Tokenem
Token ID368
Feature activation+3.09e-01

Pos logit contributions
�醒+0.191
ult+0.159
sted+0.157
olit+0.156
adr+0.148
Neg logit contributions
DX-0.242
 Fathers-0.242
 resolves-0.239
 cow-0.239
 DX-0.238
Token (
Token ID357
Feature activation+3.73e-02

Pos logit contributions
�醒+0.266
ult+0.234
sted+0.233
olit+0.233
adr+0.223
Neg logit contributions
DX-0.174
 resolves-0.173
 DX-0.172
 Fathers-0.170
 cow-0.170
Token1989
Token ID25475
Feature activation+5.27e-01

Pos logit contributions
�醒+0.028
olit+0.024
sted+0.024
ult+0.024
adr+0.023
Neg logit contributions
DX-0.026
 Fathers-0.025
 DX-0.025
 resolves-0.025
 cow-0.025
Token
Token ID1906
Feature activation+1.35e+00

Pos logit contributions
�醒+0.500
olit+0.455
ult+0.453
sted+0.450
adr+0.436
Neg logit contributions
DX-0.249
 Fathers-0.242
 DX-0.242
 resolves-0.241
 cow-0.237
Token99
Token ID2079
Feature activation+6.41e-01

Pos logit contributions
�醒+1.056
olit+0.934
ult+0.930
sted+0.926
adr+0.884
Neg logit contributions
DX-0.871
 Fathers-0.847
 resolves-0.843
 DX-0.841
 cow-0.828
Token)
Token ID8
Feature activation+8.28e-01

Pos logit contributions
�醒+0.623
ult+0.568
olit+0.568
sted+0.564
adr+0.546
Neg logit contributions
DX-0.288
 Fathers-0.280
 DX-0.279
 resolves-0.278
 cow-0.273
Token turned
Token ID2900
Feature activation+4.01e-01

Pos logit contributions
�醒+0.700
olit+0.621
ult+0.617
sted+0.613
adr+0.592
Neg logit contributions
 resolves-0.482
DX-0.481
 Fathers-0.481
 DX-0.475
 cow-0.472
Token to
Token ID284
Feature activation-1.27e-01

Pos logit contributions
�醒+0.352
olit+0.317
ult+0.315
sted+0.312
adr+0.305
Neg logit contributions
DX-0.218
 Fathers-0.217
 resolves-0.215
 cow-0.215
 DX-0.215
Token a
Token ID257
Feature activation-2.79e-01

Pos logit contributions
 Fathers+0.070
DX+0.070
 DX+0.069
 resolves+0.069
 cow+0.069
Neg logit contributions
�醒-0.111
olit-0.100
ult-0.099
sted-0.098
adr-0.095
Token One
Token ID1881
Feature activation+1.84e-01

Pos logit contributions
DX+0.095
 Fathers+0.094
 DX+0.094
 resolves+0.092
 cow+0.091
Neg logit contributions
�醒-0.118
olit-0.105
ult-0.104
sted-0.103
adr-0.099
Token photo
Token ID4590
Feature activation-6.45e-01

Pos logit contributions
�醒+0.170
olit+0.154
ult+0.153
sted+0.152
adr+0.148
Neg logit contributions
DX-0.093
 resolves-0.092
 DX-0.091
 Fathers-0.091
 cow-0.090
Token shows
Token ID2523
Feature activation-2.95e-01

Pos logit contributions
DX+0.342
 resolves+0.342
 DX+0.338
 Fathers+0.337
 cow+0.331
Neg logit contributions
�醒-0.579
olit-0.523
sted-0.516
ult-0.515
adr-0.499
Token Be
Token ID1355
Feature activation+8.31e-01

Pos logit contributions
DX+0.173
 DX+0.171
 Fathers+0.171
 cow+0.169
 resolves+0.168
Neg logit contributions
�醒-0.247
olit-0.223
ult-0.220
sted-0.219
adr-0.211
Tokenb
Token ID65
Feature activation+7.66e-01

Pos logit contributions
�醒+0.619
olit+0.535
ult+0.527
sted+0.524
adr+0.500
Neg logit contributions
DX-0.572
 Fathers-0.562
 DX-0.558
 resolves-0.557
 cow-0.555
Tokenop
Token ID404
Feature activation+1.53e+00

Pos logit contributions
�醒+0.553
olit+0.481
ult+0.480
sted+0.475
adr+0.457
Neg logit contributions
DX-0.533
 Fathers-0.530
 DX-0.526
 resolves-0.523
 cow-0.521
Token and
Token ID290
Feature activation+3.83e-01

Pos logit contributions
�醒+1.370
olit+1.238
ult+1.232
sted+1.226
adr+1.188
Neg logit contributions
DX-0.812
 Fathers-0.790
 DX-0.788
 resolves-0.783
 cow-0.777
Token Rock
Token ID4631
Feature activation+4.58e-01

Pos logit contributions
�醒+0.321
olit+0.287
ult+0.285
sted+0.284
adr+0.274
Neg logit contributions
DX-0.226
 Fathers-0.225
 DX-0.224
 resolves-0.221
 cow-0.221
Tokenstead
Token ID28044
Feature activation+3.13e-01

Pos logit contributions
�醒+0.342
olit+0.294
ult+0.292
sted+0.286
adr+0.280
Neg logit contributions
DX-0.316
 Fathers-0.311
 resolves-0.309
 DX-0.308
 cow-0.307
Tokeny
Token ID88
Feature activation-6.47e-01

Pos logit contributions
�醒+0.247
olit+0.218
ult+0.213
sted+0.213
adr+0.207
Neg logit contributions
DX-0.202
 DX-0.199
 Fathers-0.199
 cow-0.198
 resolves-0.198
Token
Token ID447
Feature activation+1.24e-01

Pos logit contributions
DX+0.338
 Fathers+0.333
 DX+0.332
 cow+0.332
 resolves+0.328
Neg logit contributions
�醒-0.587
olit-0.527
ult-0.520
sted-0.517
adr-0.501
Token:
Token ID25
Feature activation+1.48e+00

Pos logit contributions
�醒+0.229
olit+0.205
ult+0.204
sted+0.203
adr+0.196
Neg logit contributions
DX-0.141
 Fathers-0.138
 DX-0.137
 resolves-0.137
 cow-0.134
Token[/
Token ID13412
Feature activation-6.97e-01

Pos logit contributions
�醒+1.145
ult+1.026
olit+1.026
sted+1.019
adr+0.973
Neg logit contributions
DX-0.950
 Fathers-0.932
 resolves-0.928
 DX-0.924
 cow-0.910
Tokenb
Token ID65
Feature activation+4.85e-01

Pos logit contributions
DX+0.529
 Fathers+0.516
 resolves+0.515
 DX+0.513
 cow+0.507
Neg logit contributions
�醒-0.473
olit-0.402
ult-0.400
sted-0.397
adr-0.375
Token]
Token ID60
Feature activation+8.07e-01

Pos logit contributions
�醒+0.472
olit+0.430
ult+0.429
sted+0.426
adr+0.412
Neg logit contributions
DX-0.219
 Fathers-0.213
 resolves-0.211
 DX-0.210
 cow-0.205
Token 00
Token ID3571
Feature activation+7.01e-01

Pos logit contributions
�醒+0.760
olit+0.681
ult+0.678
sted+0.675
adr+0.653
Neg logit contributions
DX-0.405
 DX-0.398
 Fathers-0.397
 resolves-0.393
 cow-0.385
Token:
Token ID25
Feature activation+1.68e+00

Pos logit contributions
�醒+0.599
olit+0.542
ult+0.542
sted+0.538
adr+0.517
Neg logit contributions
DX-0.394
 Fathers-0.385
 resolves-0.384
 DX-0.382
 cow-0.375
Token47
Token ID2857
Feature activation+8.05e-02

Pos logit contributions
�醒+1.127
olit+0.991
ult+0.991
sted+0.982
adr+0.931
Neg logit contributions
DX-1.249
 Fathers-1.228
 resolves-1.223
 DX-1.218
 cow-1.202
Token:
Token ID25
Feature activation+1.11e+00

Pos logit contributions
�醒+0.068
ult+0.062
olit+0.062
sted+0.062
adr+0.059
Neg logit contributions
DX-0.046
 Fathers-0.045
 resolves-0.044
 DX-0.044
 cow-0.043
Token03
Token ID3070
Feature activation+1.06e-01

Pos logit contributions
�醒+0.849
olit+0.750
ult+0.746
sted+0.741
adr+0.707
Neg logit contributions
DX-0.741
 Fathers-0.724
 resolves-0.720
 DX-0.718
 cow-0.704
Token,
Token ID11
Feature activation-2.93e-02

Pos logit contributions
�醒+0.099
ult+0.091
olit+0.091
sted+0.090
adr+0.087
Neg logit contributions
DX-0.051
 Fathers-0.050
 resolves-0.050
 DX-0.049
 cow-0.048
Token78
Token ID3695
Feature activation+1.91e-01

Pos logit contributions
DX+0.020
 Fathers+0.020
 DX+0.019
 resolves+0.019
 cow+0.019
Neg logit contributions
�醒-0.022
olit-0.019
ult-0.019
sted-0.019
adr-0.018
Token be
Token ID307
Feature activation+3.67e-01

Pos logit contributions
�醒+0.432
sted+0.385
ult+0.383
olit+0.381
adr+0.368
Neg logit contributions
DX-0.334
 resolves-0.332
 Fathers-0.330
 cow-0.330
 DX-0.325
Token taken
Token ID2077
Feature activation+1.76e-01

Pos logit contributions
�醒+0.341
ult+0.308
olit+0.308
sted+0.307
adr+0.294
Neg logit contributions
DX-0.179
 Fathers-0.179
 resolves-0.177
 DX-0.177
 cow-0.177
Token and
Token ID290
Feature activation+1.74e-01

Pos logit contributions
�醒+0.163
ult+0.146
sted+0.146
olit+0.146
adr+0.140
Neg logit contributions
DX-0.087
 Fathers-0.087
 resolves-0.087
 DX-0.086
 cow-0.086
Token that
Token ID326
Feature activation+5.38e-01

Pos logit contributions
�醒+0.160
ult+0.143
olit+0.143
sted+0.142
adr+0.137
Neg logit contributions
 resolves-0.088
DX-0.088
 Fathers-0.088
 DX-0.087
 cow-0.086
Token such
Token ID884
Feature activation+6.12e-01

Pos logit contributions
�醒+0.467
olit+0.416
ult+0.414
sted+0.411
adr+0.399
Neg logit contributions
DX-0.302
 Fathers-0.302
 resolves-0.300
 DX-0.296
 cow-0.296
Token adjud
Token ID33719
Feature activation+2.39e-01

Pos logit contributions
�醒+0.546
olit+0.489
ult+0.486
sted+0.484
adr+0.467
Neg logit contributions
 Fathers-0.330
DX-0.329
 resolves-0.328
 DX-0.324
 cow-0.323
Tokenication
Token ID3299
Feature activation-2.06e-01

Pos logit contributions
�醒+0.240
olit+0.218
ult+0.217
sted+0.216
adr+0.209
Neg logit contributions
DX-0.100
 resolves-0.098
 Fathers-0.097
 DX-0.095
 cow-0.094
Token can
Token ID460
Feature activation+6.77e-01

Pos logit contributions
 resolves+0.129
 Fathers+0.128
DX+0.127
 DX+0.125
 cow+0.125
Neg logit contributions
�醒-0.168
sted-0.147
ult-0.146
olit-0.144
adr-0.139
Token be
Token ID307
Feature activation+4.77e-01

Pos logit contributions
�醒+0.548
sted+0.488
ult+0.485
olit+0.484
adr+0.468
Neg logit contributions
DX-0.411
 resolves-0.407
 Fathers-0.405
 cow-0.404
 DX-0.400
Token acceptable
Token ID10909
Feature activation+6.18e-01

Pos logit contributions
�醒+0.454
ult+0.412
olit+0.410
sted+0.409
adr+0.395
Neg logit contributions
DX-0.223
 Fathers-0.222
 resolves-0.220
 DX-0.219
 cow-0.218
Token in
Token ID287
Feature activation-2.56e-01

Pos logit contributions
�醒+0.527
sted+0.468
olit+0.468
ult+0.467
adr+0.449
Neg logit contributions
DX-0.353
 Fathers-0.346
 resolves-0.346
 DX-0.346
 cow-0.345
Token the
Token ID262
Feature activation-4.40e-01

Pos logit contributions
�醒+0.021
olit+0.019
ult+0.019
sted+0.019
adr+0.018
Neg logit contributions
DX-0.014
 DX-0.013
 Fathers-0.013
 resolves-0.013
 cow-0.013
Token past
Token ID1613
Feature activation+2.42e-02

Pos logit contributions
DX+0.230
 Fathers+0.229
 DX+0.229
 resolves+0.225
 cow+0.225
Neg logit contributions
�醒-0.399
olit-0.358
ult-0.356
sted-0.355
adr-0.343
Token four
Token ID1440
Feature activation-4.66e-02

Pos logit contributions
�醒+0.021
olit+0.019
ult+0.019
sted+0.019
adr+0.018
Neg logit contributions
DX-0.013
 Fathers-0.013
 DX-0.013
 resolves-0.013
 cow-0.013
Token decades
Token ID4647
Feature activation+3.14e-01

Pos logit contributions
DX+0.030
 resolves+0.029
 Fathers+0.029
 DX+0.029
 cow+0.029
Neg logit contributions
�醒-0.037
olit-0.033
ult-0.033
sted-0.033
adr-0.031
Token to
Token ID284
Feature activation-7.36e-02

Pos logit contributions
�醒+0.306
olit+0.277
ult+0.275
sted+0.275
adr+0.266
Neg logit contributions
DX-0.141
 Fathers-0.138
 resolves-0.138
 DX-0.137
 cow-0.136
Token estimate
Token ID8636
Feature activation-2.07e-01

Pos logit contributions
DX+0.042
 resolves+0.041
 Fathers+0.041
 DX+0.041
 cow+0.041
Neg logit contributions
�醒-0.064
olit-0.057
ult-0.056
sted-0.056
adr-0.054
Token the
Token ID262
Feature activation+4.13e-02

Pos logit contributions
DX+0.108
 resolves+0.105
 DX+0.105
 Fathers+0.104
 cow+0.103
Neg logit contributions
�醒-0.188
olit-0.171
ult-0.169
sted-0.169
adr-0.163
Token lake
Token ID13546
Feature activation-5.31e-01

Pos logit contributions
�醒+0.036
ult+0.032
olit+0.032
sted+0.032
adr+0.031
Neg logit contributions
DX-0.023
 Fathers-0.023
 resolves-0.023
 DX-0.023
 cow-0.023
Token
Token ID447
Feature activation+2.05e-01

Pos logit contributions
DX+0.236
 resolves+0.230
 Fathers+0.228
 DX+0.228
 cow+0.225
Neg logit contributions
�醒-0.524
ult-0.475
olit-0.473
sted-0.471
adr-0.461
Token
Token ID247
Feature activation+1.10e-01

Pos logit contributions
�醒+0.142
olit+0.127
ult+0.127
sted+0.127
adr+0.119
Neg logit contributions
DX-0.147
 Fathers-0.144
 DX-0.144
 resolves-0.143
 cow-0.142
Tokens
Token ID82
Feature activation-1.89e-01

Pos logit contributions
�醒+0.084
olit+0.074
ult+0.073
sted+0.073
adr+0.070
Neg logit contributions
DX-0.072
 resolves-0.070
 Fathers-0.070
 DX-0.070
 cow-0.069
Token old
Token ID1468
Feature activation+3.08e-01

Pos logit contributions
DX+0.252
 Fathers+0.247
 resolves+0.246
 DX+0.245
 cow+0.242
Neg logit contributions
�醒-0.254
ult-0.226
olit-0.226
sted-0.224
adr-0.213
Token.
Token ID13
Feature activation-1.61e-01

Pos logit contributions
�醒+0.302
ult+0.275
olit+0.275
sted+0.274
adr+0.265
Neg logit contributions
DX-0.135
 Fathers-0.133
 resolves-0.131
 DX-0.131
 cow-0.129
Token
Token ID198
Feature activation+1.40e-01

Pos logit contributions
 Fathers+0.104
DX+0.103
 DX+0.102
 resolves+0.100
 cow+0.099
Neg logit contributions
�醒-0.127
olit-0.113
ult-0.112
sted-0.111
adr-0.107
Token
Token ID198
Feature activation-7.16e-02

Pos logit contributions
�醒+0.107
olit+0.095
ult+0.094
sted+0.093
adr+0.090
Neg logit contributions
DX-0.092
 Fathers-0.091
 resolves-0.090
 DX-0.090
 cow-0.088
TokenMore
Token ID5167
Feature activation-7.19e-01

Pos logit contributions
DX+0.047
 Fathers+0.046
 DX+0.045
 resolves+0.044
 cow+0.044
Neg logit contributions
�醒-0.056
olit-0.050
sted-0.049
ult-0.049
adr-0.047
Token about
Token ID546
Feature activation+4.96e-01

Pos logit contributions
 Fathers+0.368
DX+0.366
 DX+0.362
 cow+0.360
 resolves+0.360
Neg logit contributions
�醒-0.659
olit-0.591
ult-0.587
sted-0.585
adr-0.573
Token this
Token ID428
Feature activation+3.89e-01

Pos logit contributions
�醒+0.431
olit+0.389
ult+0.388
sted+0.385
adr+0.372
Neg logit contributions
DX-0.273
 Fathers-0.271
 DX-0.267
 resolves-0.267
 cow-0.264
Token story
Token ID1621
Feature activation+1.01e-01

Pos logit contributions
�醒+0.332
olit+0.298
ult+0.298
sted+0.296
adr+0.285
Neg logit contributions
DX-0.221
 Fathers-0.219
 DX-0.217
 resolves-0.216
 cow-0.215
Token
Token ID198
Feature activation+2.80e-01

Pos logit contributions
�醒+0.088
olit+0.079
ult+0.079
sted+0.078
adr+0.076
Neg logit contributions
 Fathers-0.056
DX-0.055
 DX-0.055
 resolves-0.054
 cow-0.054
Token
Token ID198
Feature activation-2.30e-01

Pos logit contributions
�醒+0.209
olit+0.186
ult+0.186
sted+0.185
adr+0.176
Neg logit contributions
DX-0.188
 Fathers-0.185
 resolves-0.184
 DX-0.183
 cow-0.180
TokenAfter
Token ID3260
Feature activation-4.65e-01

Pos logit contributions
DX+0.149
 Fathers+0.144
 DX+0.140
 resolves+0.139
 cow+0.138
Neg logit contributions
�醒-0.183
olit-0.162
sted-0.159
ult-0.159
adr-0.152
Token around
Token ID1088
Feature activation-3.28e-01

Pos logit contributions
DX+0.314
 Fathers+0.311
 resolves+0.310
 DX+0.308
 cow+0.307
Neg logit contributions
�醒-0.588
ult-0.530
olit-0.525
sted-0.521
adr-0.507
Token arbitrarily
Token ID40647
Feature activation-3.66e-01

Pos logit contributions
DX+0.163
 resolves+0.161
 Fathers+0.160
 DX+0.160
 cow+0.158
Neg logit contributions
�醒-0.305
olit-0.275
ult-0.275
sted-0.272
adr-0.262
Token;
Token ID26
Feature activation-2.79e-01

Pos logit contributions
 resolves+0.166
DX+0.165
 Fathers+0.163
 changing+0.162
 DX+0.162
Neg logit contributions
�醒-0.360
ult-0.323
olit-0.322
sted-0.318
adr-0.309
Token the
Token ID262
Feature activation+1.26e-01

Pos logit contributions
DX+0.139
 Fathers+0.139
 resolves+0.138
 DX+0.138
 cow+0.138
Neg logit contributions
�醒-0.258
olit-0.233
ult-0.232
sted-0.231
adr-0.222
Token separation
Token ID14139
Feature activation+2.88e-02

Pos logit contributions
�醒+0.116
ult+0.105
olit+0.104
sted+0.104
adr+0.100
Neg logit contributions
 Fathers-0.065
DX-0.064
 DX-0.063
 cow-0.063
 resolves-0.063
Token wall
Token ID3355
Feature activation-4.57e-02

Pos logit contributions
�醒+0.025
sted+0.023
ult+0.022
olit+0.022
adr+0.021
Neg logit contributions
 resolves-0.016
 Fathers-0.016
DX-0.016
 cow-0.016
 DX-0.016
Token cuts
Token ID6630
Feature activation+1.04e-01

Pos logit contributions
 resolves+0.026
 Fathers+0.026
DX+0.026
 cow+0.025
 DX+0.025
Neg logit contributions
�醒-0.040
sted-0.035
ult-0.035
olit-0.035
adr-0.033
Token people
Token ID661
Feature activation+6.98e-01

Pos logit contributions
�醒+0.093
ult+0.083
olit+0.083
sted+0.083
adr+0.080
Neg logit contributions
DX-0.056
 Fathers-0.055
 resolves-0.055
 DX-0.055
 cow-0.055
Token off
Token ID572
Feature activation+9.84e-01

Pos logit contributions
�醒+0.623
ult+0.559
olit+0.558
sted+0.554
adr+0.534
Neg logit contributions
DX-0.369
 Fathers-0.367
 resolves-0.365
 cow-0.361
 DX-0.361
Token,
Token ID11
Feature activation-1.67e-01

Pos logit contributions
�醒+0.999
ult+0.910
olit+0.910
sted+0.906
adr+0.877
Neg logit contributions
DX-0.403
 Fathers-0.395
 resolves-0.395
 DX-0.391
 cow-0.386
Token and
Token ID290
Feature activation-3.26e-01

Pos logit contributions
 Fathers+0.088
 resolves+0.088
DX+0.088
 cow+0.087
 DX+0.087
Neg logit contributions
�醒-0.149
ult-0.133
olit-0.133
sted-0.133
adr-0.128
Token understands
Token ID14759
Feature activation+7.07e-01

Pos logit contributions
 resolves+0.310
DX+0.309
 Fathers+0.306
 cow+0.302
 DX+0.302
Neg logit contributions
�醒-0.443
ult-0.390
olit-0.389
sted-0.387
adr-0.372
Token our
Token ID674
Feature activation+1.66e-01

Pos logit contributions
�醒+0.618
ult+0.558
olit+0.557
sted+0.553
adr+0.532
Neg logit contributions
DX-0.388
 Fathers-0.382
 resolves-0.379
 DX-0.379
 cow-0.373
Token unique
Token ID3748
Feature activation-4.43e-01

Pos logit contributions
�醒+0.149
ult+0.134
olit+0.134
sted+0.133
adr+0.128
Neg logit contributions
DX-0.089
 Fathers-0.088
 resolves-0.087
 DX-0.086
 cow-0.085
Token campus
Token ID7611
Feature activation+3.75e-01

Pos logit contributions
DX+0.242
 Fathers+0.239
 DX+0.237
 resolves+0.236
 cow+0.235
Neg logit contributions
�醒-0.393
ult-0.350
olit-0.349
sted-0.346
adr-0.337
Token culture
Token ID3968
Feature activation-1.34e-01

Pos logit contributions
�醒+0.357
ult+0.324
sted+0.321
olit+0.321
adr+0.312
Neg logit contributions
DX-0.179
 Fathers-0.175
 resolves-0.174
 DX-0.173
 cow-0.171
Token as
Token ID355
Feature activation+1.72e-01

Pos logit contributions
DX+0.063
 Fathers+0.061
 resolves+0.061
 DX+0.061
 cow+0.060
Neg logit contributions
�醒-0.128
ult-0.116
olit-0.116
sted-0.116
adr-0.112
Token opposed
Token ID6886
Feature activation+9.23e-02

Pos logit contributions
�醒+0.151
olit+0.136
ult+0.136
sted+0.135
adr+0.131
Neg logit contributions
DX-0.094
 Fathers-0.092
 resolves-0.092
 DX-0.092
 cow-0.091
Token to
Token ID284
Feature activation-1.90e-01

Pos logit contributions
�醒+0.090
olit+0.081
ult+0.081
sted+0.081
adr+0.078
Neg logit contributions
DX-0.042
 Fathers-0.041
 resolves-0.041
 DX-0.041
 cow-0.040
Token a
Token ID257
Feature activation-1.61e-01

Pos logit contributions
DX+0.105
 Fathers+0.104
 DX+0.104
 resolves+0.104
 cow+0.103
Neg logit contributions
�醒-0.166
olit-0.149
ult-0.148
sted-0.148
adr-0.142
Token national
Token ID2260
Feature activation-2.40e-01

Pos logit contributions
DX+0.084
 DX+0.082
 Fathers+0.082
 cow+0.082
 resolves+0.081
Neg logit contributions
�醒-0.146
ult-0.132
olit-0.131
sted-0.131
adr-0.126
Token [
Token ID685
Feature activation-5.08e-01

Pos logit contributions
DX+0.136
 DX+0.134
 cow+0.133
 Fathers+0.133
 resolves+0.132
Neg logit contributions
�醒-0.206
ult-0.185
olit-0.184
sted-0.182
adr-0.176
Token and
Token ID290
Feature activation+1.11e-01

Pos logit contributions
DX+0.297
 Fathers+0.291
 resolves+0.289
 DX+0.287
 cow+0.284
Neg logit contributions
�醒-0.558
olit-0.508
ult-0.507
sted-0.505
adr-0.490
Token Inner
Token ID24877
Feature activation-2.03e-01

Pos logit contributions
�醒+0.104
olit+0.094
ult+0.094
sted+0.093
adr+0.090
Neg logit contributions
DX-0.055
 Fathers-0.054
 resolves-0.054
 DX-0.054
 cow-0.053
Token Mongolia
Token ID44364
Feature activation-4.77e-01

Pos logit contributions
 Fathers+0.058
DX+0.058
 DX+0.057
 resolves+0.055
 cow+0.053
Neg logit contributions
�醒-0.233
ult-0.213
olit-0.212
sted-0.211
adr-0.208
Token,
Token ID11
Feature activation+2.16e-01

Pos logit contributions
DX+0.236
 Fathers+0.233
 resolves+0.231
 DX+0.229
 cow+0.227
Neg logit contributions
�醒-0.441
olit-0.401
ult-0.400
sted-0.398
adr-0.386
Token the
Token ID262
Feature activation+2.45e-02

Pos logit contributions
�醒+0.194
olit+0.177
ult+0.176
sted+0.175
adr+0.169
Neg logit contributions
DX-0.111
 Fathers-0.110
 resolves-0.109
 DX-0.108
 cow-0.107
Token Mong
Token ID18428
Feature activation-9.83e-01

Pos logit contributions
�醒+0.022
olit+0.020
ult+0.020
sted+0.020
adr+0.019
Neg logit contributions
 Fathers-0.013
DX-0.013
 resolves-0.013
 cow-0.013
 DX-0.012
Tokenols
Token ID10220
Feature activation+1.17e-01

Pos logit contributions
 Fathers+0.393
DX+0.392
 resolves+0.379
 DX+0.372
 cow+0.370
Neg logit contributions
�醒-1.022
sted-0.898
ult-0.887
olit-0.879
adr-0.873
Token also
Token ID635
Feature activation+2.57e-01

Pos logit contributions
�醒+0.099
olit+0.089
ult+0.089
sted+0.088
adr+0.085
Neg logit contributions
DX-0.067
 Fathers-0.066
 resolves-0.066
 DX-0.065
 cow-0.065
Token use
Token ID779
Feature activation-2.10e-01

Pos logit contributions
�醒+0.218
olit+0.196
ult+0.196
sted+0.195
adr+0.187
Neg logit contributions
DX-0.147
 Fathers-0.145
 resolves-0.144
 DX-0.143
 cow-0.142
Token clan
Token ID19065
Feature activation-3.38e-01

Pos logit contributions
DX+0.113
 Fathers+0.112
 resolves+0.111
 DX+0.110
 cow+0.110
Neg logit contributions
�醒-0.185
olit-0.167
ult-0.167
sted-0.166
adr-0.160
Token names
Token ID3891
Feature activation-6.75e-01

Pos logit contributions
DX+0.192
 Fathers+0.190
 resolves+0.190
 DX+0.188
 cow+0.186
Neg logit contributions
�醒-0.289
olit-0.259
ult-0.258
sted-0.256
adr-0.247
Token their
Token ID511
Feature activation-2.35e-01

Pos logit contributions
 Fathers+0.025
 resolves+0.025
DX+0.025
 DX+0.025
 cow+0.025
Neg logit contributions
�醒-0.036
olit-0.033
ult-0.032
sted-0.032
adr-0.031
Token client
Token ID5456
Feature activation-6.70e-01

Pos logit contributions
DX+0.158
 Fathers+0.158
 resolves+0.158
 DX+0.157
 cow+0.157
Neg logit contributions
�醒-0.174
olit-0.155
ult-0.153
sted-0.152
adr-0.144
Token.
Token ID13
Feature activation+4.19e-02

Pos logit contributions
 Fathers+0.345
DX+0.344
 resolves+0.340
 cow+0.339
 DX+0.338
Neg logit contributions
�醒-0.599
olit-0.543
sted-0.537
ult-0.535
adr-0.517
Token
Token ID198
Feature activation+2.18e-01

Pos logit contributions
�醒+0.032
olit+0.029
ult+0.029
sted+0.029
adr+0.027
Neg logit contributions
 Fathers-0.027
DX-0.027
 DX-0.026
 resolves-0.026
 cow-0.026
Token
Token ID198
Feature activation-7.49e-02

Pos logit contributions
�醒+0.167
olit+0.148
ult+0.147
sted+0.146
adr+0.140
Neg logit contributions
DX-0.144
 Fathers-0.141
 resolves-0.140
 DX-0.140
 cow-0.138
TokenAsked
Token ID18932
Feature activation-1.04e+00

Pos logit contributions
DX+0.049
 Fathers+0.047
 resolves+0.046
 DX+0.046
 cow+0.045
Neg logit contributions
�醒-0.059
olit-0.052
sted-0.051
ult-0.050
adr-0.048
Token why
Token ID1521
Feature activation-8.48e-01

Pos logit contributions
DX+0.549
 Fathers+0.548
 DX+0.541
 resolves+0.540
 cow+0.539
Neg logit contributions
�醒-0.936
olit-0.839
ult-0.833
sted-0.833
adr-0.809
Token she
Token ID673
Feature activation-3.24e-01

Pos logit contributions
 Fathers+0.466
 resolves+0.461
 cow+0.460
DX+0.457
 DX+0.457
Neg logit contributions
�醒-0.738
sted-0.658
olit-0.658
ult-0.657
adr-0.636
Token thought
Token ID1807
Feature activation-3.75e-01

Pos logit contributions
 resolves+0.200
 Fathers+0.196
 cow+0.195
DX+0.195
 DX+0.191
Neg logit contributions
�醒-0.265
olit-0.233
ult-0.233
sted-0.232
adr-0.222
Token the
Token ID262
Feature activation-1.80e-01

Pos logit contributions
 Fathers+0.197
 resolves+0.194
DX+0.194
 cow+0.194
 DX+0.193
Neg logit contributions
�醒-0.335
olit-0.302
sted-0.300
ult-0.300
adr-0.292
Token prosecutors
Token ID11947
Feature activation-2.66e-01

Pos logit contributions
 Fathers+0.103
 cow+0.100
 resolves+0.100
DX+0.099
 DX+0.099
Neg logit contributions
�醒-0.154
olit-0.139
ult-0.138
sted-0.137
adr-0.131
Token Engineering
Token ID14044
Feature activation+2.24e-01

Pos logit contributions
�醒+0.121
olit+0.106
ult+0.106
sted+0.104
adr+0.102
Neg logit contributions
 Fathers-0.099
DX-0.098
 DX-0.098
 resolves-0.098
 cow-0.096
Token office
Token ID2607
Feature activation-9.17e-01

Pos logit contributions
�醒+0.216
olit+0.197
ult+0.196
sted+0.194
adr+0.190
Neg logit contributions
DX-0.102
 Fathers-0.100
 DX-0.099
 resolves-0.099
 cow-0.097
Token.
Token ID13
Feature activation-3.02e-01

Pos logit contributions
DX+0.391
 DX+0.383
 resolves+0.379
 Fathers+0.378
 cow+0.376
Neg logit contributions
�醒-0.913
olit-0.834
ult-0.828
sted-0.818
adr-0.805
Token
Token ID198
Feature activation-2.23e-01

Pos logit contributions
 Fathers+0.196
DX+0.196
 DX+0.194
 resolves+0.191
 cow+0.187
Neg logit contributions
�醒-0.235
olit-0.210
ult-0.208
sted-0.205
adr-0.197
Token
Token ID198
Feature activation-4.38e-01

Pos logit contributions
DX+0.145
 Fathers+0.142
 resolves+0.141
 DX+0.141
 cow+0.138
Neg logit contributions
�醒-0.176
olit-0.154
ult-0.153
sted-0.152
adr-0.146
TokenIf
Token ID1532
Feature activation-9.43e-01

Pos logit contributions
DX+0.293
 Fathers+0.279
 resolves+0.276
 DX+0.275
 cow+0.270
Neg logit contributions
�醒-0.337
olit-0.298
ult-0.292
sted-0.291
adr-0.278
Token a
Token ID257
Feature activation+2.02e-01

Pos logit contributions
 resolves+0.514
DX+0.512
 Fathers+0.511
 DX+0.506
 cow+0.500
Neg logit contributions
�醒-0.822
olit-0.745
ult-0.744
sted-0.733
adr-0.711
Token homeowner
Token ID40130
Feature activation-8.60e-02

Pos logit contributions
�醒+0.175
ult+0.160
olit+0.160
sted+0.157
adr+0.152
Neg logit contributions
DX-0.110
 Fathers-0.109
 resolves-0.109
 DX-0.108
 cow-0.108
Token
Token ID447
Feature activation-1.88e-01

Pos logit contributions
 resolves+0.048
DX+0.048
 Fathers+0.048
 DX+0.047
 cow+0.047
Neg logit contributions
�醒-0.074
olit-0.067
ult-0.066
sted-0.066
adr-0.063
Token
Token ID247
Feature activation-2.02e-01

Pos logit contributions
DX+0.152
 Fathers+0.149
 DX+0.148
 resolves+0.147
 cow+0.147
Neg logit contributions
�醒-0.114
olit-0.100
ult-0.100
sted-0.099
adr-0.092
Tokens
Token ID82
Feature activation+2.43e-01

Pos logit contributions
 resolves+0.130
DX+0.128
 Fathers+0.127
 cow+0.125
 DX+0.125
Neg logit contributions
�醒-0.158
olit-0.139
ult-0.136
sted-0.136
adr-0.132
Token Kernel
Token ID32169
Feature activation+2.53e-01

Pos logit contributions
�醒+0.126
olit+0.113
sted+0.113
ult+0.113
adr+0.108
Neg logit contributions
DX-0.082
 resolves-0.081
 DX-0.081
 Fathers-0.080
 cow-0.080
Token cannot
Token ID2314
Feature activation+4.22e-01

Pos logit contributions
�醒+0.212
olit+0.190
ult+0.189
sted+0.189
adr+0.182
Neg logit contributions
DX-0.150
 resolves-0.150
 Fathers-0.147
 DX-0.147
 cow-0.144
Token correctly
Token ID9380
Feature activation-2.25e-01

Pos logit contributions
�醒+0.342
sted+0.304
ult+0.304
olit+0.304
adr+0.291
Neg logit contributions
DX-0.261
 resolves-0.258
 DX-0.255
 Fathers-0.254
 cow-0.252
Token mount
Token ID3817
Feature activation-2.19e-01

Pos logit contributions
DX+0.123
 resolves+0.122
 DX+0.120
 Fathers+0.119
 cow+0.119
Neg logit contributions
�醒-0.200
sted-0.178
ult-0.178
olit-0.178
adr-0.172
Token it
Token ID340
Feature activation-2.06e-01

Pos logit contributions
DX+0.113
 resolves+0.111
 DX+0.110
 Fathers+0.110
 cow+0.108
Neg logit contributions
�醒-0.200
olit-0.180
ult-0.180
sted-0.180
adr-0.172
Token,
Token ID11
Feature activation-9.36e-01

Pos logit contributions
DX+0.097
 resolves+0.096
 DX+0.094
 Fathers+0.094
 cow+0.092
Neg logit contributions
�醒-0.199
olit-0.180
sted-0.179
ult-0.179
adr-0.172
Token it
Token ID340
Feature activation-1.61e-01

Pos logit contributions
DX+0.476
 resolves+0.468
 DX+0.466
 Fathers+0.463
 cow+0.456
Neg logit contributions
�醒-0.866
olit-0.780
sted-0.777
ult-0.773
adr-0.749
Token will
Token ID481
Feature activation+1.90e-01

Pos logit contributions
 resolves+0.097
DX+0.096
 Fathers+0.095
 DX+0.094
 cow+0.094
Neg logit contributions
�醒-0.133
olit-0.118
sted-0.118
ult-0.117
adr-0.113
Token panic
Token ID13619
Feature activation+5.07e-01

Pos logit contributions
�醒+0.167
olit+0.150
sted+0.150
ult+0.149
adr+0.145
Neg logit contributions
DX-0.103
 resolves-0.102
 Fathers-0.101
 DX-0.101
 cow-0.100
Token and
Token ID290
Feature activation+2.30e-02

Pos logit contributions
�醒+0.486
olit+0.444
ult+0.441
sted+0.439
adr+0.427
Neg logit contributions
DX-0.236
 resolves-0.230
 Fathers-0.229
 DX-0.229
 cow-0.224
Token reboot
Token ID20149
Feature activation+5.52e-01

Pos logit contributions
�醒+0.021
olit+0.019
sted+0.019
ult+0.019
adr+0.018
Neg logit contributions
DX-0.012
 resolves-0.012
 Fathers-0.012
 DX-0.012
 cow-0.012
Token
Token ID198
Feature activation-2.68e-01

Pos logit contributions
DX+0.089
 Fathers+0.087
 resolves+0.086
 DX+0.086
 cow+0.085
Neg logit contributions
�醒-0.102
olit-0.091
ult-0.090
sted-0.089
adr-0.086
TokenL
Token ID43
Feature activation-1.53e-01

Pos logit contributions
DX+0.166
 resolves+0.160
 Fathers+0.158
 DX+0.158
 cow+0.154
Neg logit contributions
�醒-0.218
olit-0.195
ult-0.192
sted-0.192
adr-0.184
Tokenanda
Token ID5282
Feature activation-1.43e-01

Pos logit contributions
DX+0.110
 resolves+0.108
 DX+0.106
 Fathers+0.106
 cow+0.105
Neg logit contributions
�醒-0.110
sted-0.092
ult-0.092
olit-0.090
adr-0.087
Token says
Token ID1139
Feature activation-5.59e-01

Pos logit contributions
 resolves+0.082
DX+0.081
 Fathers+0.080
 DX+0.080
 cow+0.079
Neg logit contributions
�醒-0.122
olit-0.109
ult-0.107
sted-0.107
adr-0.104
Token,
Token ID11
Feature activation-2.48e-01

Pos logit contributions
DX+0.257
 resolves+0.256
 Fathers+0.254
 DX+0.252
 cow+0.250
Neg logit contributions
�醒-0.533
olit-0.485
ult-0.483
sted-0.481
adr-0.468
Token '
Token ID705
Feature activation-9.20e-01

Pos logit contributions
DX+0.152
 Fathers+0.150
 resolves+0.149
 DX+0.148
 cow+0.147
Neg logit contributions
�醒-0.198
olit-0.179
ult-0.178
sted-0.177
adr-0.170
Token We
Token ID775
Feature activation-2.67e-01

Pos logit contributions
DX+0.594
 Fathers+0.587
 resolves+0.586
 DX+0.580
 cow+0.569
Neg logit contributions
�醒-0.720
olit-0.634
ult-0.629
sted-0.628
adr-0.606
Token don
Token ID836
Feature activation-6.30e-01

Pos logit contributions
 Fathers+0.173
DX+0.173
 resolves+0.173
 cow+0.171
 DX+0.170
Neg logit contributions
�醒-0.210
olit-0.181
ult-0.180
sted-0.178
adr-0.173
Token't
Token ID470
Feature activation-1.85e-01

Pos logit contributions
DX+0.405
 Fathers+0.397
 resolves+0.395
 DX+0.393
 cow+0.387
Neg logit contributions
�醒-0.493
olit-0.437
ult-0.436
sted-0.433
adr-0.414
Token have
Token ID423
Feature activation+5.49e-01

Pos logit contributions
 cow+0.138
 resolves+0.138
 Fathers+0.138
DX+0.138
 DX+0.137
Neg logit contributions
�醒-0.127
olit-0.107
ult-0.106
sted-0.106
adr-0.102
Token any
Token ID597
Feature activation-4.00e-01

Pos logit contributions
�醒+0.497
ult+0.448
olit+0.448
sted+0.442
adr+0.430
Neg logit contributions
DX-0.285
 Fathers-0.283
 resolves-0.282
 DX-0.280
 cow-0.276