TOP ACTIVATIONS
MAX = 1.312

since the time of the Canaan ites . Israel
bike , made of a bonded aluminum frame with an od
2012 United States 3 240 Posts # 10 Happy it worked
drama parody sk it " Veter in arian 's Hospital ",
2002 United States 3 472 Posts # 11 On September 20
, an impoverished and sterile amalg am of social democracy and
p a day for extra exclus ives , events and e
cub , Faith and I bonded when she was in the
, Soviet People 's Comm iss ar of Defense S emy
- Brit ney - G ambling - Super bowl Advertising -
their tank farm in C ushing , Oklahoma , March 24
ive of Peoples ' Comm iss ariat of Defence No .
2010 United States 10 53 Posts # 15 honestly if we
, I returned for another press visit devoted to two other
for the comic . Ex ceptions to this include " The
iff Tra x Reviewer : V the Happy L
2012 United States 5 667 Posts # 12 I 'm glad
­ ce ives from his fel ­ low Demo ­ cr
s Cors airs are the guardians of values and spirit of
2011 United States 228 65 Posts # 13 On September 20

MIN ACTIVATIONS
MIN = -1.238

upgrades . Select ive cataly tic reduction systems were installed to
explained in that fact - check , one part of AIR
it is thought to be generated in part by a spin
A Bottle Neck To Your Business Growth ?
com spoke with fact - check ers behind the fall TV
though .) Hon orable M ention :
set in a proced urally generated city . This series of
according to the University of Hawaii study cited previously rely
those harsh conditions while still generating electricity " at relatively high
ranking member of the House Oversight Committee , asked the Trump
: Like Loading ... <|endoftext|> Google logo is displayed outside of
providing steam for turbines which generated electricity to deliver 34 MW
. <|endoftext|> Using Google s new domain
END () This generates a function very similar to
Story continues below advertisement Story continues below
according to the University of Hawai i , there
the magazine carriers on his belt was open and the loaded
's ear with a hat chet at the same Fred Meyer
said they are also considering former Force India driver Vit anton
all find it below the IPCC s estimates .

INTERVAL 0.674 - 1.312
CONTAINS 0.196%

doorway of a Bronx apartment building . The killing prompted large
functionality , and some products embrace characteristics of both .
to face , seeing the real world projected onto their screen
ality , which rule the realm of the everyday . By
. As soon as I add the comparison code like in

INTERVAL 0.037 - 0.674
CONTAINS 40.101%

allowing state - funded private adoption agencies to turn away prospective
destroyed digital evidence that would have been crucial to prove V
- year contract with publisher Activision . B ung
, were world - ren ouncing . Values created out of
1 per year , with only half of that sum going

INTERVAL -0.600 - 0.037
CONTAINS 59.316%

other hand , exits epoch management by marking the thread inactive
very first sentence of the essay he writes that the EU
while research on Asians and Latinos appears scant . We were
2 . 5 per cent increase in the first year and
. But how we approach those problems and the resources that

INTERVAL -1.238 - -0.600
CONTAINS 0.388%

( at least among the public at large ), they aren
cars his tyre was half flat .
, 2 , 4 ) Mystery fellow MR
, computer or laptop , cooler or AC and refrigerator .
. However , this prudent check on uncontrolled prescriptions need not
Token since
Token ID1201
Feature activation-3.71e-02

Pos logit contributions
unity+0.612
 Yo+0.590
 Sergey+0.582
 VP+0.555
 travelled+0.546
Neg logit contributions
affle-0.843
rimination-0.786
 offender-0.774
icut-0.761
bourne-0.752
Token the
Token ID262
Feature activation-1.26e-01

Pos logit contributions
unity+0.065
 Yo+0.062
 Sergey+0.061
 VP+0.059
ulum+0.058
Neg logit contributions
affle-0.097
rimination-0.091
 offender-0.090
icut-0.088
bourne-0.087
Token time
Token ID640
Feature activation-4.91e-02

Pos logit contributions
unity+0.235
 Yo+0.231
 Sergey+0.226
 VP+0.216
 UP+0.213
Neg logit contributions
affle-0.317
rimination-0.294
 offender-0.288
icut-0.286
bourne-0.282
Token of
Token ID286
Feature activation-1.43e-01

Pos logit contributions
unity+0.105
 Yo+0.100
 Sergey+0.099
 VP+0.097
 Juno+0.096
Neg logit contributions
affle-0.109
rimination-0.101
 offender-0.100
icut-0.096
bourne-0.096
Token the
Token ID262
Feature activation+1.67e-02

Pos logit contributions
unity+0.256
 Yo+0.243
 Sergey+0.241
 VP+0.230
ulum+0.228
Neg logit contributions
affle-0.367
rimination-0.344
 offender-0.340
icut-0.333
aba-0.329
Token Canaan
Token ID47047
Feature activation+1.31e+00

Pos logit contributions
affle+0.041
rimination+0.038
 offender+0.037
icut+0.037
bourne+0.036
Neg logit contributions
unity-0.032
 Yo-0.032
 Sergey-0.031
 VP-0.030
 UP-0.029
Tokenites
Token ID2737
Feature activation+5.53e-01

Pos logit contributions
affle+2.003
rimination+1.810
 offender+1.772
icut+1.684
aba+1.681
Neg logit contributions
unity-3.705
 Yo-3.573
 Sergey-3.558
 VP-3.450
ulum-3.424
Token.
Token ID13
Feature activation-1.57e-01

Pos logit contributions
affle+1.318
rimination+1.231
 offender+1.216
icut+1.193
aba+1.181
Neg logit contributions
unity-1.087
 Yo-1.043
 Sergey-1.030
 VP-0.989
 Juno-0.976
Token
Token ID198
Feature activation+3.43e-02

Pos logit contributions
unity+0.309
 Yo+0.299
 Sergey+0.295
 VP+0.282
 Juno+0.277
Neg logit contributions
affle-0.378
rimination-0.351
 offender-0.345
icut-0.339
bourne-0.335
Token
Token ID198
Feature activation+2.84e-02

Pos logit contributions
affle+0.094
rimination+0.089
 offender+0.088
icut+0.087
 pitfalls+0.085
Neg logit contributions
unity-0.057
 Yo-0.055
 Sergey-0.054
 VP-0.051
 UP-0.050
TokenIsrael
Token ID14040
Feature activation+9.98e-02

Pos logit contributions
affle+0.063
rimination+0.058
 offender+0.057
icut+0.056
aba+0.055
Neg logit contributions
unity-0.061
 Yo-0.060
 Sergey-0.059
 VP-0.057
 travelled-0.056
Token bike
Token ID7161
Feature activation+4.07e-02

Pos logit contributions
unity+1.134
 Yo+1.104
 Sergey+1.092
 VP+1.054
 travelled+1.042
Neg logit contributions
affle-0.925
rimination-0.846
 offender-0.827
icut-0.809
bourne-0.796
Token,
Token ID11
Feature activation-1.79e-02

Pos logit contributions
affle+0.096
rimination+0.089
 offender+0.088
icut+0.086
bourne+0.085
Neg logit contributions
unity-0.082
 Yo-0.079
 Sergey-0.078
 VP-0.075
ulum-0.074
Token made
Token ID925
Feature activation-1.07e-02

Pos logit contributions
unity+0.033
 Yo+0.032
 Sergey+0.031
 VP+0.030
ulum+0.029
Neg logit contributions
affle-0.045
rimination-0.042
 offender-0.042
icut-0.041
bourne-0.041
Token of
Token ID286
Feature activation+7.82e-02

Pos logit contributions
unity+0.019
 Yo+0.018
 Sergey+0.018
 VP+0.017
ulum+0.017
Neg logit contributions
affle-0.028
rimination-0.026
 offender-0.025
icut-0.025
bourne-0.025
Token a
Token ID257
Feature activation+1.26e-01

Pos logit contributions
affle+0.187
rimination+0.174
 offender+0.170
icut+0.167
bourne+0.166
Neg logit contributions
unity-0.156
 Yo-0.151
 Sergey-0.149
 VP-0.143
 UP-0.141
Token bonded
Token ID40270
Feature activation+1.20e+00

Pos logit contributions
affle+0.290
rimination+0.269
 offender+0.264
icut+0.259
bourne+0.256
Neg logit contributions
unity-0.262
 Yo-0.254
 Sergey-0.251
 VP-0.241
 Juno-0.237
Token aluminum
Token ID15955
Feature activation+1.19e-01

Pos logit contributions
affle+2.843
 offender+2.632
rimination+2.606
icut+2.563
aba+2.518
Neg logit contributions
unity-2.385
 Yo-2.279
 Sergey-2.271
 VP-2.149
ulum-2.137
Token frame
Token ID5739
Feature activation+2.12e-01

Pos logit contributions
affle+0.282
rimination+0.262
 offender+0.256
icut+0.252
bourne+0.250
Neg logit contributions
unity-0.240
 Yo-0.234
 Sergey-0.229
 VP-0.222
 travelled-0.218
Token with
Token ID351
Feature activation-2.72e-01

Pos logit contributions
affle+0.499
rimination+0.462
 offender+0.455
icut+0.447
bourne+0.441
Neg logit contributions
unity-0.430
 Yo-0.416
 Sergey-0.411
 VP-0.393
 Juno-0.387
Token an
Token ID281
Feature activation-9.69e-02

Pos logit contributions
unity+0.516
 Yo+0.503
 Sergey+0.496
 VP+0.475
 UP+0.467
Neg logit contributions
affle-0.672
rimination-0.627
 offender-0.612
icut-0.604
bourne-0.598
Tokenod
Token ID375
Feature activation-4.65e-02

Pos logit contributions
unity+0.188
 Yo+0.182
 Sergey+0.180
 VP+0.172
 Juno+0.169
Neg logit contributions
affle-0.236
rimination-0.220
 offender-0.216
icut-0.212
bourne-0.210
Token 2012
Token ID2321
Feature activation+2.34e-01

Pos logit contributions
affle+0.083
rimination+0.078
 offender+0.077
icut+0.075
bourne+0.074
Neg logit contributions
unity-0.064
 Yo-0.062
 Sergey-0.061
 VP-0.058
 Juno-0.057
Token United
Token ID1578
Feature activation+1.70e-01

Pos logit contributions
affle+0.622
rimination+0.580
 offender+0.573
icut+0.564
bourne+0.558
Neg logit contributions
unity-0.403
 Yo-0.382
 Sergey-0.378
 VP-0.358
ulum-0.356
Token States
Token ID1829
Feature activation+8.24e-02

Pos logit contributions
affle+0.446
rimination+0.415
 offender+0.409
icut+0.405
bourne+0.399
Neg logit contributions
unity-0.302
 Yo-0.286
 Sergey-0.283
 VP-0.267
ulum-0.267
Token 3
Token ID513
Feature activation+7.38e-02

Pos logit contributions
affle+0.204
rimination+0.190
 offender+0.187
icut+0.184
bourne+0.182
Neg logit contributions
unity-0.157
 Yo-0.151
 Sergey-0.149
 VP-0.142
ulum-0.141
Token240
Token ID16102
Feature activation+4.13e-01

Pos logit contributions
affle+0.161
rimination+0.148
 offender+0.145
icut+0.142
bourne+0.141
Neg logit contributions
unity-0.163
 Yo-0.157
 Sergey-0.156
 VP-0.149
ulum-0.148
Token Posts
Token ID12043
Feature activation+1.19e+00

Pos logit contributions
affle+0.934
rimination+0.862
 offender+0.847
icut+0.829
bourne+0.821
Neg logit contributions
unity-0.879
 Yo-0.849
 Sergey-0.841
 VP-0.805
ulum-0.796
Token #
Token ID1303
Feature activation+3.95e-01

Pos logit contributions
affle+3.219
rimination+2.941
 offender+2.937
bourne+2.885
 pitfalls+2.852
Neg logit contributions
unity-1.953
 Sergey-1.824
ulum-1.752
 Yo-1.733
WAYS-1.701
Token10
Token ID940
Feature activation+2.28e-01

Pos logit contributions
affle+0.840
rimination+0.766
 offender+0.750
icut+0.736
aba+0.730
Neg logit contributions
unity-0.889
 Yo-0.863
 Sergey-0.854
 VP-0.821
 travelled-0.817
Token Happy
Token ID14628
Feature activation+4.36e-01

Pos logit contributions
affle+0.558
rimination+0.517
 offender+0.511
icut+0.499
bourne+0.496
Neg logit contributions
unity-0.441
 Yo-0.422
 Sergey-0.419
 VP-0.399
ulum-0.397
Token it
Token ID340
Feature activation+2.64e-01

Pos logit contributions
affle+1.094
rimination+1.014
 offender+1.007
icut+0.984
bourne+0.980
Neg logit contributions
unity-0.814
 Yo-0.777
 Sergey-0.773
 VP-0.732
ulum-0.732
Token worked
Token ID3111
Feature activation+4.16e-01

Pos logit contributions
affle+0.658
rimination+0.611
 offender+0.603
icut+0.594
bourne+0.588
Neg logit contributions
unity-0.493
 Yo-0.477
 Sergey-0.474
 VP-0.453
 Juno-0.446
Token drama
Token ID10512
Feature activation-9.16e-02

Pos logit contributions
affle+0.331
rimination+0.307
 offender+0.303
icut+0.297
bourne+0.293
Neg logit contributions
unity-0.276
 Yo-0.266
 Sergey-0.263
 VP-0.251
 Juno-0.248
Token parody
Token ID29695
Feature activation+1.74e-01

Pos logit contributions
unity+0.179
 Yo+0.173
 Sergey+0.170
 VP+0.163
 Juno+0.160
Neg logit contributions
affle-0.223
rimination-0.207
 offender-0.204
icut-0.200
bourne-0.198
Token sk
Token ID1341
Feature activation+1.13e-01

Pos logit contributions
affle+0.418
rimination+0.389
 offender+0.384
icut+0.375
bourne+0.371
Neg logit contributions
unity-0.342
 Yo-0.329
 Sergey-0.325
 VP-0.311
ulum-0.307
Tokenit
Token ID270
Feature activation+3.87e-01

Pos logit contributions
affle+0.273
rimination+0.254
 offender+0.252
icut+0.245
bourne+0.242
Neg logit contributions
unity-0.222
 Yo-0.216
 Sergey-0.212
 VP-0.203
ulum-0.200
Token "
Token ID366
Feature activation-9.55e-02

Pos logit contributions
affle+0.955
rimination+0.888
 offender+0.877
icut+0.859
bourne+0.850
Neg logit contributions
unity-0.738
 Yo-0.708
 Sergey-0.702
 VP-0.670
ulum-0.661
TokenVeter
Token ID45182
Feature activation+1.19e+00

Pos logit contributions
unity+0.202
 Yo+0.196
 Sergey+0.194
 VP+0.186
 travelled+0.184
Neg logit contributions
affle-0.216
rimination-0.199
 offender-0.196
icut-0.192
bourne-0.190
Tokenin
Token ID259
Feature activation+5.08e-01

Pos logit contributions
affle+2.573
rimination+2.407
icut+2.321
 offender+2.309
aba+2.284
Neg logit contributions
unity-2.584
 Yo-2.518
 Sergey-2.495
 VP-2.414
 UP-2.385
Tokenarian
Token ID3699
Feature activation+2.22e-01

Pos logit contributions
affle+0.912
rimination+0.825
 offender+0.808
icut+0.787
bourne+0.775
Neg logit contributions
unity-1.312
 Yo-1.278
 Sergey-1.266
 VP-1.224
 travelled-1.211
Token's
Token ID338
Feature activation+2.40e-01

Pos logit contributions
affle+0.516
rimination+0.479
 offender+0.471
icut+0.463
bourne+0.456
Neg logit contributions
unity-0.454
 Yo-0.436
 Sergey-0.432
 VP-0.413
ulum-0.410
Token Hospital
Token ID9256
Feature activation+3.64e-01

Pos logit contributions
affle+0.578
rimination+0.538
 offender+0.529
icut+0.519
bourne+0.513
Neg logit contributions
unity-0.472
 Yo-0.455
 Sergey-0.450
 VP-0.430
 travelled-0.424
Token",
Token ID1600
Feature activation-9.66e-02

Pos logit contributions
affle+0.817
rimination+0.757
 offender+0.740
icut+0.731
bourne+0.719
Neg logit contributions
unity-0.776
 Yo-0.746
 Sergey-0.740
 VP-0.708
 travelled-0.701
Token 2002
Token ID6244
Feature activation+3.16e-01

Pos logit contributions
affle+0.590
rimination+0.551
 offender+0.543
icut+0.533
bourne+0.523
Neg logit contributions
unity-0.456
 Yo-0.443
 Sergey-0.437
 VP-0.418
 Juno-0.411
Token United
Token ID1578
Feature activation+1.44e-01

Pos logit contributions
affle+0.827
rimination+0.769
 offender+0.759
icut+0.748
bourne+0.740
Neg logit contributions
unity-0.561
 Yo-0.530
 Sergey-0.524
 VP-0.497
ulum-0.495
Token States
Token ID1829
Feature activation+1.12e-01

Pos logit contributions
affle+0.374
rimination+0.348
 offender+0.343
icut+0.341
bourne+0.335
Neg logit contributions
unity-0.258
 Yo-0.244
 Sergey-0.242
ulum-0.228
 VP-0.228
Token 3
Token ID513
Feature activation+9.68e-02

Pos logit contributions
affle+0.276
rimination+0.256
 offender+0.253
icut+0.248
bourne+0.246
Neg logit contributions
unity-0.215
 Yo-0.207
 Sergey-0.204
 VP-0.195
ulum-0.193
Token472
Token ID37856
Feature activation+4.51e-01

Pos logit contributions
affle+0.205
rimination+0.188
 offender+0.185
icut+0.181
bourne+0.179
Neg logit contributions
unity-0.219
 Yo-0.212
 Sergey-0.210
 VP-0.202
 travelled-0.200
Token Posts
Token ID12043
Feature activation+1.16e+00

Pos logit contributions
affle+1.049
rimination+0.975
 offender+0.958
icut+0.943
bourne+0.923
Neg logit contributions
unity-0.926
 Yo-0.907
 Sergey-0.893
 VP-0.859
 Juno-0.846
Token #
Token ID1303
Feature activation+3.81e-01

Pos logit contributions
affle+3.133
 offender+2.876
rimination+2.861
bourne+2.794
 pitfalls+2.782
Neg logit contributions
unity-1.908
 Sergey-1.781
ulum-1.687
 Yo-1.686
WAYS-1.643
Token11
Token ID1157
Feature activation+2.38e-01

Pos logit contributions
affle+0.753
rimination+0.699
 offender+0.686
icut+0.670
bourne+0.655
Neg logit contributions
unity-0.917
 Yo-0.894
 Sergey-0.879
 VP-0.847
 @@-0.836
Token On
Token ID1550
Feature activation+3.35e-01

Pos logit contributions
affle+0.580
rimination+0.537
 offender+0.532
icut+0.519
bourne+0.515
Neg logit contributions
unity-0.459
 Yo-0.438
 Sergey-0.435
 VP-0.414
ulum-0.414
Token September
Token ID2693
Feature activation+1.46e-01

Pos logit contributions
affle+0.914
 offender+0.851
rimination+0.848
bourne+0.823
icut+0.821
Neg logit contributions
unity-0.555
 Yo-0.515
 Sergey-0.512
 VP-0.491
ulum-0.487
Token 20
Token ID1160
Feature activation+1.63e-01

Pos logit contributions
affle+0.356
rimination+0.331
 offender+0.326
icut+0.320
bourne+0.316
Neg logit contributions
unity-0.282
 Yo-0.273
 Sergey-0.269
 VP-0.257
 travelled-0.253
Token,
Token ID11
Feature activation+7.37e-02

Pos logit contributions
affle+0.059
rimination+0.055
 offender+0.054
icut+0.053
bourne+0.052
Neg logit contributions
unity-0.046
 Yo-0.044
 Sergey-0.044
 VP-0.042
 Juno-0.041
Token an
Token ID281
Feature activation+1.66e-02

Pos logit contributions
affle+0.181
rimination+0.168
 offender+0.166
icut+0.163
bourne+0.161
Neg logit contributions
unity-0.141
 Yo-0.136
 Sergey-0.134
 VP-0.128
ulum-0.127
Token impoverished
Token ID35014
Feature activation+1.34e-01

Pos logit contributions
affle+0.038
rimination+0.035
 offender+0.034
icut+0.034
bourne+0.033
Neg logit contributions
unity-0.035
 Yo-0.034
 Sergey-0.034
 VP-0.032
 Juno-0.032
Token and
Token ID290
Feature activation-4.82e-02

Pos logit contributions
affle+0.311
rimination+0.287
 offender+0.285
icut+0.278
bourne+0.274
Neg logit contributions
unity-0.278
 Yo-0.268
 Sergey-0.265
 VP-0.254
 Juno-0.251
Token sterile
Token ID38697
Feature activation+4.01e-01

Pos logit contributions
unity+0.104
 Yo+0.101
 Sergey+0.100
 VP+0.096
 travelled+0.094
Neg logit contributions
affle-0.107
rimination-0.099
 offender-0.097
icut-0.095
bourne-0.094
Token amalg
Token ID45541
Feature activation+1.16e+00

Pos logit contributions
affle+0.932
rimination+0.863
 offender+0.860
icut+0.836
bourne+0.825
Neg logit contributions
unity-0.819
 Yo-0.788
 Sergey-0.780
 VP-0.747
 Juno-0.737
Tokenam
Token ID321
Feature activation+8.92e-02

Pos logit contributions
affle+2.524
rimination+2.366
aba+2.242
icut+2.239
 offender+2.225
Neg logit contributions
 Yo-2.474
unity-2.449
 Sergey-2.428
 VP-2.345
WAYS-2.332
Token of
Token ID286
Feature activation-1.33e-01

Pos logit contributions
affle+0.205
rimination+0.191
 offender+0.187
icut+0.183
bourne+0.181
Neg logit contributions
unity-0.184
 Yo-0.179
 Sergey-0.177
 VP-0.170
 Juno-0.168
Token social
Token ID1919
Feature activation-4.60e-01

Pos logit contributions
unity+0.270
 Yo+0.262
 Sergey+0.258
 VP+0.247
 travelled+0.244
Neg logit contributions
affle-0.314
rimination-0.292
 offender-0.286
icut-0.282
bourne-0.278
Token democracy
Token ID7996
Feature activation+4.22e-02

Pos logit contributions
unity+0.929
 Yo+0.902
 Sergey+0.888
 VP+0.853
 travelled+0.839
Neg logit contributions
affle-1.082
rimination-1.006
 offender-0.981
icut-0.968
bourne-0.957
Token and
Token ID290
Feature activation+3.61e-02

Pos logit contributions
affle+0.099
rimination+0.092
 offender+0.091
icut+0.089
bourne+0.088
Neg logit contributions
unity-0.086
 Yo-0.083
 Sergey-0.082
 VP-0.078
 Juno-0.077
Tokenp
Token ID79
Feature activation+1.20e-01

Pos logit contributions
unity+0.187
 Yo+0.181
 Sergey+0.178
 VP+0.172
 UP+0.169
Neg logit contributions
affle-0.207
rimination-0.192
 offender-0.189
icut-0.186
bourne-0.183
Token a
Token ID257
Feature activation+1.42e-01

Pos logit contributions
affle+0.299
rimination+0.277
 offender+0.274
icut+0.270
bourne+0.266
Neg logit contributions
unity-0.226
 Yo-0.218
 Sergey-0.216
 VP-0.206
 Juno-0.203
Token day
Token ID1110
Feature activation-7.40e-02

Pos logit contributions
affle+0.390
rimination+0.364
 offender+0.363
icut+0.355
bourne+0.352
Neg logit contributions
unity-0.233
 Yo-0.220
 Sergey-0.219
 VP-0.205
ulum-0.203
Token for
Token ID329
Feature activation-8.47e-03

Pos logit contributions
unity+0.136
 Yo+0.131
 Sergey+0.130
 VP+0.124
 Juno+0.121
Neg logit contributions
affle-0.188
rimination-0.175
 offender-0.173
icut-0.170
bourne-0.168
Token extra
Token ID3131
Feature activation-5.02e-02

Pos logit contributions
unity+0.016
 Yo+0.016
 Sergey+0.015
 VP+0.015
 Juno+0.015
Neg logit contributions
affle-0.021
rimination-0.019
 offender-0.019
icut-0.019
bourne-0.019
Token exclus
Token ID10293
Feature activation+1.15e+00

Pos logit contributions
unity+0.103
 Yo+0.100
 Sergey+0.099
 VP+0.095
 travelled+0.094
Neg logit contributions
affle-0.116
rimination-0.108
 offender-0.106
icut-0.104
bourne-0.103
Tokenives
Token ID1083
Feature activation+6.66e-02

Pos logit contributions
affle+2.778
rimination+2.571
icut+2.506
 offender+2.481
aba+2.461
Neg logit contributions
unity-2.208
 Yo-2.146
 Sergey-2.143
 VP-2.046
 UP-2.011
Token,
Token ID11
Feature activation+1.05e-01

Pos logit contributions
affle+0.163
rimination+0.151
 offender+0.149
icut+0.146
bourne+0.144
Neg logit contributions
unity-0.129
 Yo-0.125
 Sergey-0.123
 VP-0.118
 Juno-0.116
Token events
Token ID2995
Feature activation+2.30e-01

Pos logit contributions
affle+0.250
rimination+0.232
 offender+0.229
icut+0.224
bourne+0.221
Neg logit contributions
unity-0.211
 Yo-0.204
 Sergey-0.202
 VP-0.193
 Juno-0.190
Token and
Token ID290
Feature activation+6.64e-03

Pos logit contributions
affle+0.549
rimination+0.510
 offender+0.502
icut+0.493
bourne+0.486
Neg logit contributions
unity-0.457
 Yo-0.442
 Sergey-0.437
 VP-0.418
 Juno-0.411
Token e
Token ID304
Feature activation-1.83e-01

Pos logit contributions
affle+0.015
rimination+0.014
 offender+0.014
icut+0.014
bourne+0.014
Neg logit contributions
unity-0.014
 Yo-0.013
 Sergey-0.013
 VP-0.013
 travelled-0.012
Token cub
Token ID13617
Feature activation+9.00e-02

Pos logit contributions
affle+0.209
rimination+0.194
 offender+0.191
icut+0.187
bourne+0.185
Neg logit contributions
unity-0.174
 Yo-0.168
 Sergey-0.166
 VP-0.159
 Juno-0.157
Token,
Token ID11
Feature activation-2.97e-01

Pos logit contributions
affle+0.217
rimination+0.202
 offender+0.199
icut+0.195
bourne+0.193
Neg logit contributions
unity-0.177
 Yo-0.171
 Sergey-0.169
 VP-0.162
 UP-0.159
Token Faith
Token ID16463
Feature activation+3.80e-01

Pos logit contributions
unity+0.579
 Yo+0.559
 Sergey+0.552
 VP+0.528
ulum+0.519
Neg logit contributions
affle-0.724
rimination-0.673
 offender-0.664
icut-0.651
bourne-0.643
Token and
Token ID290
Feature activation-4.30e-01

Pos logit contributions
affle+0.914
rimination+0.846
 offender+0.837
icut+0.821
bourne+0.814
Neg logit contributions
unity-0.748
 Yo-0.721
 Sergey-0.713
 VP-0.681
ulum-0.672
Token I
Token ID314
Feature activation-1.05e-01

Pos logit contributions
unity+0.778
 Yo+0.754
 Sergey+0.743
 VP+0.707
 Juno+0.697
Neg logit contributions
affle-1.104
rimination-1.031
 offender-1.013
icut-0.999
bourne-0.986
Token bonded
Token ID40270
Feature activation+1.11e+00

Pos logit contributions
unity+0.193
 Yo+0.186
 Sergey+0.183
 VP+0.175
 Juno+0.172
Neg logit contributions
affle-0.267
rimination-0.249
 offender-0.246
icut-0.242
bourne-0.239
Token when
Token ID618
Feature activation-2.00e-01

Pos logit contributions
affle+2.633
 offender+2.444
rimination+2.423
icut+2.407
bourne+2.373
Neg logit contributions
unity-2.151
 Yo-2.046
 Sergey-2.040
ulum-1.956
 VP-1.956
Token she
Token ID673
Feature activation+4.02e-01

Pos logit contributions
unity+0.415
 Yo+0.401
 Sergey+0.396
 VP+0.380
ulum+0.375
Neg logit contributions
affle-0.461
rimination-0.427
 offender-0.421
icut-0.412
bourne-0.408
Token was
Token ID373
Feature activation+3.92e-02

Pos logit contributions
affle+1.028
rimination+0.956
 offender+0.953
icut+0.935
bourne+0.930
Neg logit contributions
unity-0.729
 Yo-0.692
 Sergey-0.686
 VP-0.652
ulum-0.646
Token in
Token ID287
Feature activation-7.47e-02

Pos logit contributions
affle+0.096
rimination+0.089
 offender+0.089
icut+0.087
bourne+0.086
Neg logit contributions
unity-0.076
 Yo-0.072
 Sergey-0.072
 VP-0.068
ulum-0.068
Token the
Token ID262
Feature activation-1.62e-03

Pos logit contributions
unity+0.143
 Yo+0.139
 Sergey+0.137
 VP+0.131
 UP+0.129
Neg logit contributions
affle-0.184
rimination-0.171
 offender-0.168
icut-0.165
bourne-0.163
Token,
Token ID11
Feature activation+3.90e-02

Pos logit contributions
unity+0.748
 Yo+0.715
 Sergey+0.706
 VP+0.673
ulum+0.666
Neg logit contributions
affle-1.060
rimination-0.988
 offender-0.975
icut-0.958
bourne-0.950
Token Soviet
Token ID7570
Feature activation-3.57e-01

Pos logit contributions
affle+0.105
rimination+0.098
 offender+0.097
icut+0.095
bourne+0.095
Neg logit contributions
unity-0.066
 Yo-0.062
 Sergey-0.061
ulum-0.058
 VP-0.058
Token People
Token ID4380
Feature activation+1.44e-01

Pos logit contributions
unity+0.743
 Yo+0.722
 Sergey+0.714
 VP+0.686
 UP+0.674
Neg logit contributions
affle-0.819
rimination-0.759
 offender-0.744
icut-0.733
bourne-0.722
Token's
Token ID338
Feature activation-1.20e-01

Pos logit contributions
affle+0.359
rimination+0.333
 offender+0.329
icut+0.321
bourne+0.320
Neg logit contributions
unity-0.270
 Yo-0.261
 Sergey-0.255
 VP-0.244
 Juno-0.243
Token Comm
Token ID1520
Feature activation-1.45e-01

Pos logit contributions
unity+0.241
 Yo+0.233
 Sergey+0.231
 VP+0.221
 UP+0.218
Neg logit contributions
affle-0.283
rimination-0.262
 offender-0.258
icut-0.254
bourne-0.250
Tokeniss
Token ID747
Feature activation+1.11e+00

Pos logit contributions
unity+0.418
 Yo+0.407
 Sergey+0.403
 VP+0.392
 Juno+0.386
Neg logit contributions
affle-0.219
rimination-0.194
 offender-0.191
icut-0.183
bourne-0.179
Tokenar
Token ID283
Feature activation+2.78e-01

Pos logit contributions
affle+1.940
rimination+1.743
 offender+1.697
icut+1.676
bourne+1.640
Neg logit contributions
unity-2.889
 Yo-2.830
 Sergey-2.805
 VP-2.718
 UP-2.700
Token of
Token ID286
Feature activation+8.41e-02

Pos logit contributions
affle+0.726
rimination+0.678
 offender+0.669
icut+0.656
bourne+0.652
Neg logit contributions
unity-0.490
 Yo-0.463
 Sergey-0.450
 VP-0.434
ulum-0.432
Token Defense
Token ID5947
Feature activation-7.94e-02

Pos logit contributions
affle+0.205
rimination+0.191
 offender+0.188
icut+0.185
bourne+0.182
Neg logit contributions
unity-0.163
 Yo-0.157
 Sergey-0.155
 VP-0.148
 travelled-0.146
Token S
Token ID311
Feature activation+1.03e-01

Pos logit contributions
unity+0.141
 Yo+0.135
 Sergey+0.133
 VP+0.127
ulum+0.125
Neg logit contributions
affle-0.207
rimination-0.193
 offender-0.191
icut-0.187
bourne-0.185
Tokenemy
Token ID3065
Feature activation-1.97e-01

Pos logit contributions
affle+0.232
rimination+0.215
 offender+0.209
icut+0.207
aba+0.205
Neg logit contributions
unity-0.219
 Yo-0.210
 Sergey-0.207
 VP-0.200
 Juno-0.198
Token-
Token ID12
Feature activation+3.16e-02

Pos logit contributions
unity+0.241
 Yo+0.239
 Sergey+0.233
 VP+0.227
 UP+0.224
Neg logit contributions
affle-0.224
rimination-0.210
 offender-0.205
icut-0.200
 pitfalls-0.195
TokenBrit
Token ID17959
Feature activation+3.56e-02

Pos logit contributions
affle+0.071
rimination+0.066
 offender+0.065
icut+0.064
bourne+0.063
Neg logit contributions
unity-0.067
 Yo-0.065
 Sergey-0.064
 VP-0.062
 travelled-0.061
Tokenney
Token ID1681
Feature activation+2.32e-01

Pos logit contributions
affle+0.082
rimination+0.075
 offender+0.074
icut+0.073
bourne+0.072
Neg logit contributions
unity-0.074
 Yo-0.071
 Sergey-0.071
 VP-0.068
 travelled-0.067
Token-
Token ID12
Feature activation+1.73e-01

Pos logit contributions
affle+0.374
rimination+0.333
 offender+0.327
icut+0.316
bourne+0.314
Neg logit contributions
unity-0.643
 Yo-0.622
 Sergey-0.619
 VP-0.599
ulum-0.597
TokenG
Token ID38
Feature activation-9.98e-02

Pos logit contributions
affle+0.401
rimination+0.370
 offender+0.363
icut+0.357
bourne+0.353
Neg logit contributions
unity-0.358
 Yo-0.347
 Sergey-0.343
 VP-0.329
 travelled-0.327
Tokenambling
Token ID15366
Feature activation+1.09e+00

Pos logit contributions
unity+0.236
 Yo+0.230
 Sergey+0.227
 VP+0.219
 Juno+0.216
Neg logit contributions
affle-0.201
rimination-0.184
 offender-0.181
icut-0.176
bourne-0.174
Token-
Token ID12
Feature activation+6.39e-02

Pos logit contributions
affle+2.444
rimination+2.256
 offender+2.229
icut+2.213
bourne+2.189
Neg logit contributions
unity-2.285
 Yo-2.168
 Sergey-2.165
 travelled-2.098
ulum-2.076
TokenSuper
Token ID12442
Feature activation+3.05e-02

Pos logit contributions
affle+0.147
rimination+0.136
 offender+0.134
icut+0.132
bourne+0.130
Neg logit contributions
unity-0.132
 Yo-0.128
 Sergey-0.127
 VP-0.122
 travelled-0.121
Tokenbowl
Token ID36859
Feature activation+1.94e-01

Pos logit contributions
affle+0.064
rimination+0.059
 offender+0.058
icut+0.057
bourne+0.056
Neg logit contributions
unity-0.069
 Yo-0.067
 Sergey-0.066
 VP-0.063
ulum-0.063
Token Advertising
Token ID40113
Feature activation-1.87e-01

Pos logit contributions
affle+0.473
rimination+0.438
 offender+0.432
icut+0.425
bourne+0.419
Neg logit contributions
unity-0.379
 Yo-0.364
 Sergey-0.361
 travelled-0.342
 VP-0.342
Token-
Token ID12
Feature activation+2.14e-01

Pos logit contributions
unity+0.429
 Yo+0.416
 Sergey+0.412
 VP+0.395
 travelled+0.393
Neg logit contributions
affle-0.393
rimination-0.359
 offender-0.354
icut-0.347
bourne-0.342
Token their
Token ID511
Feature activation+2.83e-02

Pos logit contributions
unity+0.196
 Yo+0.189
 Sergey+0.186
 VP+0.177
 travelled+0.174
Neg logit contributions
affle-0.278
rimination-0.260
 offender-0.256
icut-0.252
bourne-0.249
Token tank
Token ID6873
Feature activation+1.83e-01

Pos logit contributions
affle+0.069
rimination+0.064
 offender+0.063
icut+0.062
bourne+0.061
Neg logit contributions
unity-0.055
 Yo-0.053
 Sergey-0.052
 VP-0.050
 Juno-0.049
Token farm
Token ID5318
Feature activation+8.07e-02

Pos logit contributions
affle+0.426
rimination+0.394
 offender+0.389
icut+0.382
bourne+0.377
Neg logit contributions
unity-0.374
 Yo-0.361
 Sergey-0.357
 VP-0.342
 Juno-0.337
Token in
Token ID287
Feature activation-1.55e-01

Pos logit contributions
affle+0.202
rimination+0.188
 offender+0.186
icut+0.183
bourne+0.180
Neg logit contributions
unity-0.151
 Yo-0.146
 Sergey-0.144
 VP-0.137
ulum-0.135
Token C
Token ID327
Feature activation+2.20e-01

Pos logit contributions
unity+0.293
 Yo+0.285
 Sergey+0.281
 VP+0.268
 Juno+0.265
Neg logit contributions
affle-0.387
rimination-0.361
 offender-0.355
icut-0.349
bourne-0.344
Tokenushing
Token ID8023
Feature activation+1.09e+00

Pos logit contributions
affle+0.477
rimination+0.437
 offender+0.426
icut+0.424
aba+0.420
Neg logit contributions
unity-0.484
 Yo-0.472
 Sergey-0.469
 VP-0.451
 Juno-0.444
Token,
Token ID11
Feature activation-1.07e-01

Pos logit contributions
affle+2.384
rimination+2.208
 offender+2.190
icut+2.145
bourne+2.144
Neg logit contributions
unity-2.338
 Yo-2.258
 Sergey-2.240
 VP-2.139
ulum-2.114
Token Oklahoma
Token ID10433
Feature activation+7.41e-02

Pos logit contributions
unity+0.181
 Yo+0.175
 Sergey+0.171
 VP+0.163
 UP+0.161
Neg logit contributions
affle-0.288
rimination-0.270
 offender-0.265
icut-0.261
bourne-0.258
Token,
Token ID11
Feature activation-8.87e-02

Pos logit contributions
affle+0.185
rimination+0.173
 offender+0.171
icut+0.169
bourne+0.167
Neg logit contributions
unity-0.139
 Yo-0.132
 Sergey-0.130
 VP-0.125
ulum-0.123
Token March
Token ID2805
Feature activation-2.53e-01

Pos logit contributions
unity+0.147
 Yo+0.141
 Sergey+0.139
 VP+0.132
 Juno+0.130
Neg logit contributions
affle-0.241
rimination-0.226
 offender-0.223
icut-0.220
bourne-0.217
Token 24
Token ID1987
Feature activation-2.89e-01

Pos logit contributions
unity+0.452
 Yo+0.441
 Sergey+0.435
 VP+0.415
 UP+0.407
Neg logit contributions
affle-0.656
rimination-0.616
 offender-0.605
icut-0.595
bourne-0.586
Tokenive
Token ID425
Feature activation-1.23e-01

Pos logit contributions
unity+0.093
 Yo+0.090
 Sergey+0.089
 VP+0.085
 Juno+0.084
Neg logit contributions
affle-0.109
rimination-0.101
 offender-0.099
icut-0.097
bourne-0.096
Token of
Token ID286
Feature activation+1.00e-01

Pos logit contributions
unity+0.237
 Yo+0.230
 Sergey+0.227
 VP+0.217
 UP+0.213
Neg logit contributions
affle-0.301
rimination-0.280
 offender-0.275
icut-0.270
bourne-0.266
Token Peoples
Token ID41770
Feature activation+3.17e-01

Pos logit contributions
affle+0.264
rimination+0.247
 offender+0.243
icut+0.239
bourne+0.236
Neg logit contributions
unity-0.175
 Yo-0.169
 Sergey-0.166
 VP-0.158
 travelled-0.155
Token'
Token ID6
Feature activation+4.09e-01

Pos logit contributions
affle+0.699
rimination+0.644
 offender+0.633
icut+0.621
bourne+0.611
Neg logit contributions
unity-0.691
 Yo-0.671
 Sergey-0.663
 VP-0.637
 UP-0.628
Token Comm
Token ID1520
Feature activation-1.66e-02

Pos logit contributions
affle+1.012
rimination+0.943
 offender+0.928
icut+0.911
bourne+0.900
Neg logit contributions
unity-0.781
 Yo-0.754
 Sergey-0.744
 VP-0.710
 travelled-0.699
Tokeniss
Token ID747
Feature activation+1.09e+00

Pos logit contributions
unity+0.048
 Yo+0.047
 Sergey+0.046
 VP+0.045
 Juno+0.045
Neg logit contributions
affle-0.025
rimination-0.022
 offender-0.021
icut-0.021
bourne-0.020
Tokenariat
Token ID21621
Feature activation+1.69e-01

Pos logit contributions
affle+2.087
rimination+1.902
 offender+1.841
icut+1.833
bourne+1.795
Neg logit contributions
unity-2.651
 Yo-2.603
 Sergey-2.578
 VP-2.497
 Juno-2.470
Token of
Token ID286
Feature activation+2.05e-01

Pos logit contributions
affle+0.400
rimination+0.372
 offender+0.365
icut+0.359
bourne+0.355
Neg logit contributions
unity-0.340
 Yo-0.328
 Sergey-0.323
 VP-0.310
 Juno-0.307
Token Defence
Token ID16721
Feature activation-5.78e-02

Pos logit contributions
affle+0.497
rimination+0.462
 offender+0.454
icut+0.446
bourne+0.441
Neg logit contributions
unity-0.400
 Yo-0.386
 Sergey-0.380
 VP-0.364
 travelled-0.359
Token No
Token ID1400
Feature activation+1.40e-01

Pos logit contributions
unity+0.116
 Yo+0.113
 Sergey+0.111
 VP+0.107
 travelled+0.105
Neg logit contributions
affle-0.137
rimination-0.127
 offender-0.125
icut-0.123
bourne-0.121
Token.
Token ID13
Feature activation-5.22e-02

Pos logit contributions
affle+0.353
rimination+0.330
 offender+0.324
icut+0.320
aba+0.317
Neg logit contributions
unity-0.260
 Yo-0.249
 Sergey-0.246
 VP-0.235
 travelled-0.232
Token 2010
Token ID3050
Feature activation+2.89e-01

Pos logit contributions
unity+0.061
 Yo+0.059
 Sergey+0.058
 VP+0.055
 travelled+0.055
Neg logit contributions
affle-0.077
rimination-0.071
 offender-0.070
icut-0.069
bourne-0.068
Token United
Token ID1578
Feature activation+1.77e-01

Pos logit contributions
affle+0.772
rimination+0.720
 offender+0.710
icut+0.701
bourne+0.693
Neg logit contributions
unity-0.497
 Yo-0.471
 Sergey-0.465
 VP-0.441
ulum-0.438
Token States
Token ID1829
Feature activation+1.76e-02

Pos logit contributions
affle+0.458
rimination+0.426
 offender+0.419
icut+0.417
bourne+0.410
Neg logit contributions
unity-0.320
 Yo-0.303
 Sergey-0.299
ulum-0.283
 VP-0.283
Token 10
Token ID838
Feature activation+9.43e-02

Pos logit contributions
affle+0.044
rimination+0.041
 offender+0.040
icut+0.039
bourne+0.039
Neg logit contributions
unity-0.034
 Yo-0.032
 Sergey-0.032
 VP-0.030
 travelled-0.030
Token53
Token ID4310
Feature activation+2.49e-01

Pos logit contributions
affle+0.188
rimination+0.171
 offender+0.167
icut+0.163
bourne+0.162
Neg logit contributions
unity-0.226
 Yo-0.219
 Sergey-0.217
 VP-0.209
ulum-0.207
Token Posts
Token ID12043
Feature activation+1.09e+00

Pos logit contributions
affle+0.582
rimination+0.543
 offender+0.533
icut+0.526
bourne+0.513
Neg logit contributions
unity-0.505
 Yo-0.497
 Sergey-0.489
 VP-0.470
 Juno-0.463
Token #
Token ID1303
Feature activation+3.82e-01

Pos logit contributions
affle+2.929
 offender+2.680
rimination+2.678
icut+2.607
bourne+2.600
Neg logit contributions
unity-1.782
 Sergey-1.661
 Yo-1.586
ulum-1.571
WAYS-1.547
Token15
Token ID1314
Feature activation+4.09e-04

Pos logit contributions
affle+0.832
rimination+0.778
 offender+0.759
icut+0.745
bourne+0.726
Neg logit contributions
unity-0.849
 Yo-0.821
 Sergey-0.809
 VP-0.777
 UP-0.765
Token honestly
Token ID12698
Feature activation-2.42e-02

Pos logit contributions
affle+0.001
rimination+0.001
 offender+0.001
icut+0.001
bourne+0.001
Neg logit contributions
unity-0.001
 Yo-0.001
 Sergey-0.001
 VP-0.001
ulum-0.001
Token if
Token ID611
Feature activation+3.83e-02

Pos logit contributions
unity+0.048
 Yo+0.046
 Sergey+0.045
 VP+0.043
ulum+0.043
Neg logit contributions
affle-0.058
rimination-0.054
 offender-0.053
icut-0.052
bourne-0.052
Token we
Token ID356
Feature activation-4.82e-02

Pos logit contributions
affle+0.093
rimination+0.087
 offender+0.086
icut+0.084
bourne+0.083
Neg logit contributions
unity-0.074
 Yo-0.072
 Sergey-0.071
 VP-0.067
 travelled-0.067
Token,
Token ID11
Feature activation-1.40e-01

Pos logit contributions
unity+0.487
 Yo+0.476
 Sergey+0.468
 VP+0.451
 travelled+0.446
Neg logit contributions
affle-0.614
rimination-0.571
icut-0.554
 offender-0.553
bourne-0.545
Token I
Token ID314
Feature activation-8.91e-02

Pos logit contributions
unity+0.282
 Yo+0.272
 Sergey+0.269
 VP+0.257
ulum+0.254
Neg logit contributions
affle-0.333
rimination-0.309
 offender-0.304
icut-0.298
bourne-0.295
Token returned
Token ID4504
Feature activation-2.31e-01

Pos logit contributions
unity+0.153
 Yo+0.147
 Sergey+0.144
 VP+0.137
ulum+0.135
Neg logit contributions
affle-0.238
rimination-0.223
 offender-0.220
icut-0.216
bourne-0.214
Token for
Token ID329
Feature activation+2.92e-01

Pos logit contributions
unity+0.396
 Yo+0.381
 Sergey+0.375
 VP+0.356
 travelled+0.350
Neg logit contributions
affle-0.617
rimination-0.578
 offender-0.570
icut-0.560
bourne-0.554
Token another
Token ID1194
Feature activation+4.88e-02

Pos logit contributions
affle+0.798
rimination+0.744
 offender+0.737
icut+0.722
bourne+0.716
Neg logit contributions
unity-0.484
 Yo-0.460
 Sergey-0.456
 VP-0.430
 travelled-0.425
Token press
Token ID1803
Feature activation+1.08e+00

Pos logit contributions
affle+0.125
rimination+0.116
 offender+0.114
icut+0.113
bourne+0.111
Neg logit contributions
unity-0.089
 Yo-0.086
 Sergey-0.085
 VP-0.081
 Juno-0.080
Token visit
Token ID3187
Feature activation+6.82e-02

Pos logit contributions
affle+2.532
 offender+2.308
rimination+2.282
icut+2.245
bourne+2.203
Neg logit contributions
unity-2.196
 Yo-2.108
 Sergey-2.092
ulum-1.995
 VP-1.985
Token devoted
Token ID13378
Feature activation-8.58e-02

Pos logit contributions
affle+0.175
rimination+0.164
 offender+0.161
icut+0.159
bourne+0.157
Neg logit contributions
unity-0.123
 Yo-0.119
 Sergey-0.117
 VP-0.112
 Juno-0.110
Token to
Token ID284
Feature activation+2.38e-01

Pos logit contributions
unity+0.158
 Yo+0.153
 Sergey+0.151
 VP+0.143
ulum+0.141
Neg logit contributions
affle-0.217
rimination-0.202
 offender-0.200
icut-0.197
bourne-0.194
Token two
Token ID734
Feature activation+1.53e-01

Pos logit contributions
affle+0.591
rimination+0.549
 offender+0.543
icut+0.532
bourne+0.526
Neg logit contributions
unity-0.450
 Yo-0.433
 Sergey-0.428
 VP-0.408
ulum-0.403
Token other
Token ID584
Feature activation+1.39e-01

Pos logit contributions
affle+0.346
rimination+0.320
 offender+0.316
icut+0.308
bourne+0.304
Neg logit contributions
unity-0.323
 Yo-0.312
 Sergey-0.309
 VP-0.296
ulum-0.293
Token for
Token ID329
Feature activation-1.78e-01

Pos logit contributions
affle+0.762
rimination+0.708
 offender+0.702
icut+0.689
bourne+0.681
Neg logit contributions
unity-0.570
 Yo-0.546
 Sergey-0.543
 VP-0.514
ulum-0.511
Token the
Token ID262
Feature activation-9.55e-02

Pos logit contributions
unity+0.305
 Yo+0.294
 Sergey+0.289
 VP+0.275
 Juno+0.270
Neg logit contributions
affle-0.476
rimination-0.445
 offender-0.439
icut-0.432
bourne-0.427
Token comic
Token ID9048
Feature activation-1.98e-01

Pos logit contributions
unity+0.203
 Yo+0.197
 Sergey+0.194
 VP+0.187
 UP+0.184
Neg logit contributions
affle-0.216
rimination-0.199
 offender-0.196
icut-0.192
bourne-0.190
Token.
Token ID13
Feature activation-3.61e-02

Pos logit contributions
unity+0.376
 Yo+0.363
 Sergey+0.359
 VP+0.342
 travelled+0.337
Neg logit contributions
affle-0.491
rimination-0.457
 offender-0.451
icut-0.443
bourne-0.437
Token Ex
Token ID1475
Feature activation-1.17e-02

Pos logit contributions
unity+0.072
 Yo+0.070
 Sergey+0.069
 VP+0.066
 travelled+0.065
Neg logit contributions
affle-0.086
rimination-0.080
 offender-0.079
icut-0.077
bourne-0.076
Tokenceptions
Token ID11755
Feature activation+1.07e+00

Pos logit contributions
unity+0.024
 Yo+0.023
 Sergey+0.023
 VP+0.022
 travelled+0.022
Neg logit contributions
affle-0.027
rimination-0.025
 offender-0.025
icut-0.025
aba-0.024
Token to
Token ID284
Feature activation+3.31e-03

Pos logit contributions
affle+2.590
rimination+2.394
 offender+2.392
icut+2.340
aba+2.296
Neg logit contributions
unity-2.055
 Yo-1.975
 Sergey-1.969
 VP-1.871
ulum-1.861
Token this
Token ID428
Feature activation+4.03e-02

Pos logit contributions
affle+0.008
rimination+0.008
 offender+0.007
icut+0.007
bourne+0.007
Neg logit contributions
unity-0.006
 Yo-0.006
 Sergey-0.006
 VP-0.006
 travelled-0.006
Token include
Token ID2291
Feature activation+4.31e-01

Pos logit contributions
affle+0.094
rimination+0.087
 offender+0.086
icut+0.084
bourne+0.083
Neg logit contributions
unity-0.083
 Yo-0.080
 Sergey-0.079
 VP-0.076
 Juno-0.075
Token "
Token ID366
Feature activation-5.37e-02

Pos logit contributions
affle+1.065
rimination+0.985
 offender+0.980
icut+0.955
aba+0.944
Neg logit contributions
unity-0.825
 Yo-0.785
 Sergey-0.782
ulum-0.741
 VP-0.741
TokenThe
Token ID464
Feature activation+2.08e-01

Pos logit contributions
unity+0.116
 Yo+0.113
 Sergey+0.112
 VP+0.107
 travelled+0.106
Neg logit contributions
affle-0.119
rimination-0.110
 offender-0.108
icut-0.106
bourne-0.104
Tokeniff
Token ID733
Feature activation-5.27e-01

Pos logit contributions
unity+0.116
 Yo+0.114
 Sergey+0.111
ulum+0.110
 @@+0.108
Neg logit contributions
affle-0.048
 offender-0.045
rimination-0.044
 pitfalls-0.042
uyomi-0.042
TokenTra
Token ID15721
Feature activation+1.46e-01

Pos logit contributions
unity+1.303
 Yo+1.278
 Sergey+1.245
 VP+1.208
ulum+1.204
Neg logit contributions
affle-0.987
rimination-0.919
 offender-0.894
icut-0.883
aba-0.857
Tokenx
Token ID87
Feature activation+3.28e-01

Pos logit contributions
affle+0.379
rimination+0.357
 offender+0.353
icut+0.345
 pitfalls+0.338
Neg logit contributions
unity-0.262
 Yo-0.251
 Sergey-0.244
 VP-0.234
ulum-0.230
Token
Token ID198
Feature activation+1.62e-01

Pos logit contributions
affle+0.807
rimination+0.751
 offender+0.745
icut+0.732
bourne+0.719
Neg logit contributions
unity-0.634
 Yo-0.599
 Sergey-0.594
 VP-0.564
 travelled-0.561
Token
Token ID198
Feature activation+1.83e-01

Pos logit contributions
affle+0.443
rimination+0.420
 offender+0.413
icut+0.407
 pitfalls+0.398
Neg logit contributions
unity-0.267
 Yo-0.261
 Sergey-0.255
 VP-0.243
 UP-0.238
TokenReviewer
Token ID35407
Feature activation+1.06e+00

Pos logit contributions
affle+0.211
rimination+0.180
 offender+0.173
icut+0.166
bourne+0.161
Neg logit contributions
unity-0.591
 Yo-0.579
 Sergey-0.575
 VP-0.560
 travelled-0.555
Token:
Token ID25
Feature activation+5.29e-01

Pos logit contributions
affle+2.616
rimination+2.438
 offender+2.401
icut+2.358
bourne+2.327
Neg logit contributions
unity-2.026
 Yo-1.958
 Sergey-1.932
 VP-1.845
 Juno-1.815
Token V
Token ID569
Feature activation-4.12e-02

Pos logit contributions
affle+1.308
rimination+1.211
 offender+1.208
icut+1.177
bourne+1.166
Neg logit contributions
unity-1.009
 Yo-0.953
 Sergey-0.943
 VP-0.899
ulum-0.898
Tokenthe
Token ID1169
Feature activation-2.49e-02

Pos logit contributions
unity+0.091
 Yo+0.089
 Sergey+0.087
 VP+0.084
 Juno+0.083
Neg logit contributions
affle-0.089
rimination-0.082
 offender-0.081
icut-0.079
bourne-0.078
TokenHappy
Token ID25082
Feature activation+4.57e-01

Pos logit contributions
unity+0.054
 Yo+0.052
 Sergey+0.052
 VP+0.049
 Juno+0.049
Neg logit contributions
affle-0.056
rimination-0.051
 offender-0.050
icut-0.049
bourne-0.049
TokenL
Token ID43
Feature activation-1.03e-01

Pos logit contributions
affle+1.068
rimination+0.987
 offender+0.975
icut+0.955
bourne+0.947
Neg logit contributions
unity-0.932
 Yo-0.901
 Sergey-0.893
 VP-0.852
ulum-0.841
Token 2012
Token ID2321
Feature activation+2.30e-01

Pos logit contributions
affle+0.041
rimination+0.039
 offender+0.038
icut+0.037
bourne+0.037
Neg logit contributions
unity-0.032
 Yo-0.032
 Sergey-0.031
 VP-0.030
 Juno-0.029
Token United
Token ID1578
Feature activation+2.60e-01

Pos logit contributions
affle+0.608
rimination+0.568
 offender+0.560
icut+0.552
bourne+0.546
Neg logit contributions
unity-0.399
 Yo-0.380
 Sergey-0.375
 VP-0.356
ulum-0.352
Token States
Token ID1829
Feature activation+7.13e-02

Pos logit contributions
affle+0.670
rimination+0.622
 offender+0.615
icut+0.612
bourne+0.601
Neg logit contributions
unity-0.473
 Yo-0.446
 Sergey-0.440
ulum-0.418
 VP-0.415
Token 5
Token ID642
Feature activation+1.44e-01

Pos logit contributions
affle+0.176
rimination+0.164
 offender+0.161
icut+0.158
bourne+0.157
Neg logit contributions
unity-0.136
 Yo-0.131
 Sergey-0.129
 VP-0.123
ulum-0.122
Token667
Token ID28933
Feature activation+4.97e-01

Pos logit contributions
affle+0.293
rimination+0.267
 offender+0.261
icut+0.256
aba+0.254
Neg logit contributions
unity-0.341
 Yo-0.329
 Sergey-0.326
 VP-0.314
ulum-0.312
Token Posts
Token ID12043
Feature activation+1.05e+00

Pos logit contributions
affle+1.149
rimination+1.069
 offender+1.050
icut+1.032
bourne+1.012
Neg logit contributions
unity-1.025
 Yo-1.002
 Sergey-0.988
 VP-0.949
 Juno-0.935
Token #
Token ID1303
Feature activation+3.58e-01

Pos logit contributions
affle+2.837
 offender+2.592
rimination+2.589
icut+2.523
bourne+2.522
Neg logit contributions
unity-1.737
 Sergey-1.629
 Yo-1.554
ulum-1.537
WAYS-1.511
Token12
Token ID1065
Feature activation+1.02e-01

Pos logit contributions
affle+0.711
rimination+0.663
 offender+0.646
icut+0.631
bourne+0.616
Neg logit contributions
unity-0.862
 Yo-0.837
 Sergey-0.826
 VP-0.795
 Juno-0.784
Token I
Token ID314
Feature activation+1.28e-01

Pos logit contributions
affle+0.252
rimination+0.234
 offender+0.231
icut+0.226
bourne+0.224
Neg logit contributions
unity-0.197
 Yo-0.188
 Sergey-0.187
 VP-0.178
ulum-0.177
Token'm
Token ID1101
Feature activation+8.92e-03

Pos logit contributions
affle+0.317
rimination+0.296
 offender+0.291
icut+0.286
bourne+0.283
Neg logit contributions
unity-0.245
 Yo-0.236
 Sergey-0.234
 VP-0.223
ulum-0.220
Token glad
Token ID9675
Feature activation+2.97e-01

Pos logit contributions
affle+0.021
rimination+0.020
 offender+0.020
icut+0.019
bourne+0.019
Neg logit contributions
unity-0.018
 Yo-0.017
 Sergey-0.017
 VP-0.016
ulum-0.016
Token­
Token ID3907
Feature activation+5.90e-01

Pos logit contributions
unity+0.061
 Yo+0.059
 Sergey+0.059
 VP+0.057
 Juno+0.056
Neg logit contributions
affle-0.060
rimination-0.055
 offender-0.054
icut-0.053
aba-0.052
Tokence
Token ID344
Feature activation-2.34e-01

Pos logit contributions
affle+1.300
rimination+1.194
 offender+1.168
icut+1.162
bourne+1.141
Neg logit contributions
unity-1.274
 Yo-1.247
 Sergey-1.236
 VP-1.186
 UP-1.169
Tokenives
Token ID1083
Feature activation+2.27e-01

Pos logit contributions
unity+0.508
 Yo+0.491
 Sergey+0.487
 VP+0.467
ulum+0.460
Neg logit contributions
affle-0.520
rimination-0.479
 offender-0.468
icut-0.465
bourne-0.456
Token from
Token ID422
Feature activation+3.78e-01

Pos logit contributions
affle+0.565
rimination+0.525
 offender+0.520
icut+0.510
aba+0.502
Neg logit contributions
unity-0.430
 Yo-0.413
 Sergey-0.408
 VP-0.389
ulum-0.385
Token his
Token ID465
Feature activation+1.35e-01

Pos logit contributions
affle+0.953
rimination+0.885
 offender+0.880
icut+0.861
aba+0.851
Neg logit contributions
unity-0.699
 Yo-0.662
 Sergey-0.657
 VP-0.624
ulum-0.621
Token fel
Token ID10756
Feature activation+1.05e+00

Pos logit contributions
affle+0.325
rimination+0.302
 offender+0.299
icut+0.293
bourne+0.289
Neg logit contributions
unity-0.264
 Yo-0.254
 Sergey-0.252
 VP-0.240
ulum-0.237
Token­
Token ID3907
Feature activation+6.16e-01

Pos logit contributions
affle+2.183
 offender+1.986
rimination+1.976
icut+1.958
aba+1.936
Neg logit contributions
unity-2.380
 Sergey-2.301
 Yo-2.300
ulum-2.213
 VP-2.206
Tokenlow
Token ID9319
Feature activation+4.35e-01

Pos logit contributions
affle+0.992
rimination+0.886
 offender+0.862
icut+0.842
bourne+0.825
Neg logit contributions
unity-1.707
 Yo-1.669
 Sergey-1.655
 VP-1.607
 travelled-1.590
Token Demo
Token ID34588
Feature activation+1.59e-01

Pos logit contributions
affle+1.006
rimination+0.930
 offender+0.924
icut+0.908
aba+0.890
Neg logit contributions
unity-0.894
 Yo-0.860
 Sergey-0.851
 VP-0.812
 Juno-0.807
Token­
Token ID3907
Feature activation+8.72e-01

Pos logit contributions
affle+0.354
rimination+0.327
 offender+0.322
icut+0.315
bourne+0.311
Neg logit contributions
unity-0.341
 Yo-0.331
 Sergey-0.327
 VP-0.314
 Juno-0.309
Tokencr
Token ID6098
Feature activation+3.34e-01

Pos logit contributions
affle+1.156
rimination+1.007
 offender+0.977
icut+0.943
bourne+0.918
Neg logit contributions
unity-2.661
 Yo-2.606
 Sergey-2.585
 VP-2.513
 Juno-2.490
Tokens
Token ID82
Feature activation-7.03e-02

Pos logit contributions
affle+0.914
rimination+0.850
 offender+0.845
icut+0.827
bourne+0.815
Neg logit contributions
unity-0.744
 Yo-0.718
 Sergey-0.709
 VP-0.675
ulum-0.671
Token Cors
Token ID26978
Feature activation+5.55e-01

Pos logit contributions
unity+0.139
 Yo+0.134
 Sergey+0.133
 VP+0.127
 Juno+0.125
Neg logit contributions
affle-0.169
rimination-0.157
 offender-0.155
icut-0.152
bourne-0.150
Tokenairs
Token ID3468
Feature activation+8.92e-01

Pos logit contributions
affle+1.557
rimination+1.451
 offender+1.435
icut+1.433
aba+1.414
Neg logit contributions
unity-0.862
 Yo-0.833
 Sergey-0.819
 VP-0.778
 UP-0.765
Token are
Token ID389
Feature activation+4.58e-02

Pos logit contributions
affle+2.128
rimination+1.973
 offender+1.970
icut+1.920
bourne+1.901
Neg logit contributions
unity-1.757
 Yo-1.681
 Sergey-1.657
 VP-1.586
ulum-1.583
Token the
Token ID262
Feature activation+7.85e-02

Pos logit contributions
affle+0.113
rimination+0.105
 offender+0.104
icut+0.102
bourne+0.101
Neg logit contributions
unity-0.087
 Yo-0.084
 Sergey-0.083
 VP-0.079
ulum-0.078
Token guardians
Token ID32769
Feature activation+1.05e+00

Pos logit contributions
affle+0.188
rimination+0.174
 offender+0.171
icut+0.168
bourne+0.166
Neg logit contributions
unity-0.157
 Yo-0.152
 Sergey-0.150
 VP-0.143
 Juno-0.141
Token of
Token ID286
Feature activation-5.23e-02

Pos logit contributions
affle+2.249
 offender+2.069
rimination+2.064
icut+2.031
aba+1.999
Neg logit contributions
unity-2.256
 Yo-2.196
 Sergey-2.187
 VP-2.115
 travelled-2.063
Token values
Token ID3815
Feature activation+1.15e-01

Pos logit contributions
unity+0.090
 Yo+0.086
 Sergey+0.085
 VP+0.081
ulum+0.080
Neg logit contributions
affle-0.138
rimination-0.130
 offender-0.129
icut-0.126
bourne-0.125
Token and
Token ID290
Feature activation-7.17e-02

Pos logit contributions
affle+0.272
rimination+0.253
 offender+0.250
icut+0.245
bourne+0.242
Neg logit contributions
unity-0.230
 Yo-0.222
 Sergey-0.219
 VP-0.210
ulum-0.208
Token spirit
Token ID4437
Feature activation+1.19e-01

Pos logit contributions
unity+0.139
 Yo+0.134
 Sergey+0.132
 VP+0.126
ulum+0.124
Neg logit contributions
affle-0.175
rimination-0.163
 offender-0.161
icut-0.158
bourne-0.156
Token of
Token ID286
Feature activation-1.62e-01

Pos logit contributions
affle+0.282
rimination+0.263
 offender+0.259
icut+0.254
bourne+0.252
Neg logit contributions
unity-0.234
 Yo-0.227
 Sergey-0.224
 VP-0.215
 Juno-0.212
Token 2011
Token ID2813
Feature activation+2.47e-01

Pos logit contributions
affle+0.089
rimination+0.083
 offender+0.082
icut+0.080
bourne+0.079
Neg logit contributions
unity-0.070
 Yo-0.068
 Sergey-0.067
 VP-0.064
 Juno-0.063
Token United
Token ID1578
Feature activation+1.62e-01

Pos logit contributions
affle+0.661
rimination+0.616
 offender+0.609
icut+0.600
bourne+0.593
Neg logit contributions
unity-0.421
 Yo-0.400
 Sergey-0.395
 VP-0.374
ulum-0.371
Token States
Token ID1829
Feature activation+3.37e-02

Pos logit contributions
affle+0.420
rimination+0.390
 offender+0.385
icut+0.383
bourne+0.376
Neg logit contributions
unity-0.292
 Yo-0.276
 Sergey-0.272
ulum-0.258
 travelled-0.257
Token 228
Token ID29041
Feature activation-8.35e-02

Pos logit contributions
affle+0.083
rimination+0.077
 offender+0.076
icut+0.075
bourne+0.074
Neg logit contributions
unity-0.064
 Yo-0.062
 Sergey-0.061
 VP-0.058
 travelled-0.057
Token65
Token ID2996
Feature activation+4.07e-01

Pos logit contributions
unity+0.191
 Yo+0.186
 Sergey+0.184
 VP+0.177
 Juno+0.175
Neg logit contributions
affle-0.174
rimination-0.160
 offender-0.157
icut-0.154
bourne-0.152
Token Posts
Token ID12043
Feature activation+1.05e+00

Pos logit contributions
affle+0.947
rimination+0.881
 offender+0.866
icut+0.852
bourne+0.833
Neg logit contributions
unity-0.831
 Yo-0.815
 Sergey-0.804
 VP-0.772
 Juno-0.760
Token #
Token ID1303
Feature activation+3.70e-01

Pos logit contributions
affle+2.836
 offender+2.599
rimination+2.593
icut+2.524
bourne+2.522
Neg logit contributions
unity-1.728
 Sergey-1.616
 Yo-1.539
ulum-1.523
WAYS-1.494
Token13
Token ID1485
Feature activation+1.77e-01

Pos logit contributions
affle+0.824
rimination+0.774
 offender+0.757
icut+0.743
bourne+0.727
Neg logit contributions
unity-0.795
 Yo-0.770
 Sergey-0.761
 VP-0.727
 UP-0.720
Token On
Token ID1550
Feature activation+2.52e-01

Pos logit contributions
affle+0.432
rimination+0.401
 offender+0.397
icut+0.388
bourne+0.384
Neg logit contributions
unity-0.342
 Yo-0.327
 Sergey-0.324
 VP-0.309
ulum-0.307
Token September
Token ID2693
Feature activation+9.59e-02

Pos logit contributions
affle+0.727
rimination+0.684
 offender+0.675
icut+0.665
bourne+0.658
Neg logit contributions
unity-0.377
 Yo-0.360
 Sergey-0.354
 VP-0.334
 travelled-0.326
Token 20
Token ID1160
Feature activation+1.42e-01

Pos logit contributions
affle+0.210
rimination+0.192
 offender+0.189
icut+0.185
bourne+0.184
Neg logit contributions
unity-0.210
 Yo-0.203
 Sergey-0.201
 VP-0.193
ulum-0.193
Token upgrades
Token ID16608
Feature activation+1.74e-01

Pos logit contributions
unity+0.673
 Yo+0.654
 Sergey+0.644
 VP+0.618
 UP+0.608
Neg logit contributions
affle-0.829
rimination-0.772
 offender-0.756
icut-0.744
bourne-0.734
Token.
Token ID13
Feature activation-4.92e-03

Pos logit contributions
affle+0.429
rimination+0.398
 offender+0.394
icut+0.385
bourne+0.382
Neg logit contributions
unity-0.333
 Yo-0.320
 Sergey-0.316
 VP-0.302
ulum-0.298
Token Select
Token ID9683
Feature activation+4.99e-01

Pos logit contributions
unity+0.010
 Yo+0.009
 Sergey+0.009
 travelled+0.009
 VP+0.009
Neg logit contributions
affle-0.012
rimination-0.011
 offender-0.011
icut-0.011
aba-0.011
Tokenive
Token ID425
Feature activation+1.24e-01

Pos logit contributions
affle+1.063
rimination+0.973
 offender+0.962
icut+0.959
aba+0.932
Neg logit contributions
unity-1.113
 Yo-1.082
 Sergey-1.071
 travelled-1.026
 VP-1.022
Token cataly
Token ID36745
Feature activation-1.77e-01

Pos logit contributions
affle+0.289
rimination+0.267
 offender+0.265
icut+0.259
bourne+0.256
Neg logit contributions
unity-0.254
 Yo-0.244
 Sergey-0.242
 VP-0.231
 travelled-0.230
Tokentic
Token ID13370
Feature activation-1.24e+00

Pos logit contributions
unity+0.394
 Yo+0.382
 Sergey+0.377
 VP+0.362
 Juno+0.358
Neg logit contributions
affle-0.384
rimination-0.353
 offender-0.348
icut-0.340
bourne-0.335
Token reduction
Token ID7741
Feature activation-1.86e-01

Pos logit contributions
unity+2.676
 Yo+2.616
 Sergey+2.570
 VP+2.529
 UP+2.459
Neg logit contributions
affle-2.719
rimination-2.524
 offender-2.425
icut-2.408
aba-2.360
Token systems
Token ID3341
Feature activation-2.18e-01

Pos logit contributions
unity+0.368
 Yo+0.356
 Sergey+0.352
 VP+0.336
 Juno+0.331
Neg logit contributions
affle-0.448
rimination-0.416
 offender-0.410
icut-0.402
bourne-0.397
Token were
Token ID547
Feature activation-9.38e-02

Pos logit contributions
unity+0.423
 Yo+0.409
 Sergey+0.404
 VP+0.386
 travelled+0.380
Neg logit contributions
affle-0.533
rimination-0.497
 offender-0.488
icut-0.480
bourne-0.473
Token installed
Token ID6589
Feature activation-2.19e-01

Pos logit contributions
unity+0.178
 Yo+0.171
 Sergey+0.168
 VP+0.160
ulum+0.159
Neg logit contributions
affle-0.233
rimination-0.217
 offender-0.215
icut-0.211
bourne-0.208
Token to
Token ID284
Feature activation-1.55e-01

Pos logit contributions
unity+0.393
 Yo+0.379
 Sergey+0.373
 VP+0.355
 Juno+0.349
Neg logit contributions
affle-0.568
rimination-0.531
 offender-0.523
icut-0.514
bourne-0.508
Token explained
Token ID4893
Feature activation+6.19e-02

Pos logit contributions
affle+0.199
rimination+0.185
 offender+0.183
icut+0.179
bourne+0.177
Neg logit contributions
unity-0.160
 Yo-0.155
 Sergey-0.153
 VP-0.146
 Juno-0.144
Token in
Token ID287
Feature activation-1.13e-01

Pos logit contributions
affle+0.160
rimination+0.150
 offender+0.148
icut+0.146
bourne+0.144
Neg logit contributions
unity-0.110
 Yo-0.106
 Sergey-0.105
 VP-0.099
ulum-0.098
Token that
Token ID326
Feature activation+5.25e-02

Pos logit contributions
unity+0.188
 Yo+0.180
 Sergey+0.177
 VP+0.168
 travelled+0.166
Neg logit contributions
affle-0.306
rimination-0.286
 offender-0.283
icut-0.277
bourne-0.275
Token fact
Token ID1109
Feature activation+2.00e-01

Pos logit contributions
affle+0.129
rimination+0.120
 offender+0.118
icut+0.116
bourne+0.114
Neg logit contributions
unity-0.101
 Yo-0.097
 Sergey-0.096
 VP-0.092
 travelled-0.091
Token-
Token ID12
Feature activation-2.98e-01

Pos logit contributions
affle+0.464
rimination+0.430
 offender+0.423
icut+0.415
bourne+0.410
Neg logit contributions
unity-0.411
 Yo-0.397
 Sergey-0.392
 VP-0.377
ulum-0.371
Tokencheck
Token ID9122
Feature activation-1.20e+00

Pos logit contributions
unity+0.632
 Yo+0.602
 Sergey+0.596
 VP+0.576
ulum+0.565
Neg logit contributions
affle-0.678
rimination-0.628
 offender-0.619
icut-0.606
bourne-0.595
Token,
Token ID11
Feature activation+2.38e-02

Pos logit contributions
unity+2.283
 Yo+2.236
 Sergey+2.175
 VP+2.102
 UP+2.072
Neg logit contributions
affle-2.922
rimination-2.746
 offender-2.630
icut-2.609
bourne-2.566
Token one
Token ID530
Feature activation+6.69e-02

Pos logit contributions
affle+0.059
rimination+0.055
 offender+0.054
icut+0.053
bourne+0.052
Neg logit contributions
unity-0.046
 Yo-0.044
 Sergey-0.043
 VP-0.041
 travelled-0.041
Token part
Token ID636
Feature activation+2.19e-01

Pos logit contributions
affle+0.156
rimination+0.145
 offender+0.143
icut+0.139
bourne+0.138
Neg logit contributions
unity-0.137
 Yo-0.132
 Sergey-0.130
 VP-0.125
 travelled-0.123
Token of
Token ID286
Feature activation+3.72e-02

Pos logit contributions
affle+0.500
rimination+0.463
 offender+0.457
icut+0.446
bourne+0.442
Neg logit contributions
unity-0.457
 Yo-0.442
 Sergey-0.436
 VP-0.418
 travelled-0.412
Token AIR
Token ID31600
Feature activation-2.91e-01

Pos logit contributions
affle+0.097
rimination+0.090
 offender+0.089
icut+0.087
bourne+0.086
Neg logit contributions
unity-0.066
 Yo-0.064
 Sergey-0.063
 VP-0.059
 travelled-0.059
Token it
Token ID340
Feature activation-1.97e-01

Pos logit contributions
affle+0.123
rimination+0.114
 offender+0.113
icut+0.110
bourne+0.109
Neg logit contributions
unity-0.097
 Yo-0.093
 Sergey-0.092
 VP-0.088
ulum-0.086
Token is
Token ID318
Feature activation-5.45e-02

Pos logit contributions
unity+0.378
 Yo+0.365
 Sergey+0.360
 VP+0.344
 Juno+0.338
Neg logit contributions
affle-0.484
rimination-0.450
 offender-0.444
icut-0.436
bourne-0.430
Token thought
Token ID1807
Feature activation-2.37e-01

Pos logit contributions
unity+0.107
 Yo+0.103
 Sergey+0.102
 VP+0.097
ulum+0.096
Neg logit contributions
affle-0.132
rimination-0.122
 offender-0.121
icut-0.118
bourne-0.117
Token to
Token ID284
Feature activation-2.45e-01

Pos logit contributions
unity+0.437
 Yo+0.419
 Sergey+0.415
 VP+0.394
 @@+0.388
Neg logit contributions
affle-0.598
rimination-0.552
 offender-0.551
icut-0.538
bourne-0.533
Token be
Token ID307
Feature activation-1.90e-01

Pos logit contributions
unity+0.473
 Yo+0.457
 Sergey+0.451
 VP+0.431
 Juno+0.424
Neg logit contributions
affle-0.599
rimination-0.556
 offender-0.549
icut-0.538
bourne-0.532
Token generated
Token ID7560
Feature activation-1.18e+00

Pos logit contributions
unity+0.379
 Yo+0.366
 Sergey+0.362
 VP+0.346
ulum+0.341
Neg logit contributions
affle-0.452
rimination-0.419
 offender-0.414
icut-0.406
bourne-0.400
Token in
Token ID287
Feature activation-2.11e-01

Pos logit contributions
unity+1.732
 Yo+1.676
 Sergey+1.629
 VP+1.547
 UP+1.521
Neg logit contributions
affle-3.428
rimination-3.231
 offender-3.162
icut-3.126
bourne-3.092
Token part
Token ID636
Feature activation+1.09e-01

Pos logit contributions
unity+0.372
 Yo+0.359
 Sergey+0.353
 VP+0.336
 Juno+0.331
Neg logit contributions
affle-0.550
rimination-0.515
 offender-0.507
icut-0.499
bourne-0.493
Token by
Token ID416
Feature activation-4.22e-02

Pos logit contributions
affle+0.325
rimination+0.305
 offender+0.303
icut+0.299
bourne+0.296
Neg logit contributions
unity-0.152
 Yo-0.144
 Sergey-0.143
 VP-0.134
ulum-0.131
Token a
Token ID257
Feature activation-9.00e-02

Pos logit contributions
unity+0.075
 Yo+0.071
 Sergey+0.070
 VP+0.067
ulum+0.066
Neg logit contributions
affle-0.110
rimination-0.103
 offender-0.102
icut-0.100
bourne-0.099
Token spin
Token ID7906
Feature activation-3.26e-01

Pos logit contributions
unity+0.180
 Yo+0.173
 Sergey+0.171
 VP+0.164
 travelled+0.161
Neg logit contributions
affle-0.214
rimination-0.199
 offender-0.196
icut-0.192
bourne-0.190
Token A
Token ID317
Feature activation-2.85e-01

Pos logit contributions
unity+0.436
 Yo+0.417
 Sergey+0.413
 VP+0.394
ulum+0.391
Neg logit contributions
affle-0.549
rimination-0.508
 offender-0.502
icut-0.493
bourne-0.488
Token Bottle
Token ID33608
Feature activation-1.30e-01

Pos logit contributions
unity+0.539
 Yo+0.522
 Sergey+0.513
 VP+0.492
 Juno+0.483
Neg logit contributions
affle-0.708
rimination-0.661
 offender-0.650
icut-0.639
bourne-0.631
Token Neck
Token ID34726
Feature activation-1.83e-01

Pos logit contributions
unity+0.271
 Yo+0.262
 Sergey+0.260
 VP+0.248
ulum+0.245
Neg logit contributions
affle-0.297
rimination-0.274
 offender-0.270
icut-0.265
bourne-0.261
Token To
Token ID1675
Feature activation-8.72e-02

Pos logit contributions
unity+0.430
 Yo+0.417
 Sergey+0.413
 VP+0.398
 Juno+0.394
Neg logit contributions
affle-0.371
rimination-0.339
 offender-0.333
icut-0.325
bourne-0.321
Token Your
Token ID3406
Feature activation-2.33e-01

Pos logit contributions
unity+0.172
 Yo+0.165
 Sergey+0.163
 VP+0.156
 travelled+0.154
Neg logit contributions
affle-0.211
rimination-0.195
 offender-0.193
icut-0.189
bourne-0.187
Token Business
Token ID7320
Feature activation-1.17e+00

Pos logit contributions
unity+0.466
 Yo+0.448
 Sergey+0.444
 VP+0.424
 travelled+0.419
Neg logit contributions
affle-0.556
rimination-0.516
 offender-0.508
icut-0.498
bourne-0.493
Token
Token ID447
Feature activation-8.95e-02

Pos logit contributions
unity+2.123
 Yo+2.052
 Sergey+2.021
 VP+1.930
 Juno+1.892
Neg logit contributions
affle-2.981
rimination-2.789
 offender-2.745
icut-2.697
bourne-2.666
Token
Token ID247
Feature activation-6.24e-02

Pos logit contributions
unity+0.155
 Yo+0.149
 Sergey+0.147
 VP+0.140
 Juno+0.138
Neg logit contributions
affle-0.237
rimination-0.221
 offender-0.218
icut-0.214
bourne-0.212
Token Growth
Token ID19045
Feature activation-6.67e-02

Pos logit contributions
unity+0.118
 Yo+0.113
 Sergey+0.113
 VP+0.107
 travelled+0.106
Neg logit contributions
affle-0.155
rimination-0.144
 offender-0.142
icut-0.140
bourne-0.138
Token?
Token ID30
Feature activation+2.51e-01

Pos logit contributions
unity+0.126
 Yo+0.121
 Sergey+0.120
 VP+0.114
 travelled+0.113
Neg logit contributions
affle-0.166
rimination-0.154
 offender-0.152
icut-0.149
bourne-0.148
Token
Token ID198
Feature activation-1.74e-01

Pos logit contributions
affle+0.617
rimination+0.573
 offender+0.566
icut+0.554
bourne+0.549
Neg logit contributions
unity-0.482
 Yo-0.457
 Sergey-0.455
 VP-0.433
 travelled-0.433
Tokencom
Token ID785
Feature activation-2.66e-01

Pos logit contributions
unity+0.117
 Yo+0.114
 Sergey+0.113
 VP+0.109
 travelled+0.109
Neg logit contributions
affle-0.084
rimination-0.076
 offender-0.075
icut-0.074
bourne-0.073
Token spoke
Token ID5158
Feature activation-2.67e-01

Pos logit contributions
unity+0.528
 Yo+0.512
 Sergey+0.506
 VP+0.486
 travelled+0.480
Neg logit contributions
affle-0.637
rimination-0.593
 offender-0.581
icut-0.572
bourne-0.563
Token with
Token ID351
Feature activation+9.78e-03

Pos logit contributions
unity+0.503
 Yo+0.480
 Sergey+0.474
ulum+0.453
 VP+0.450
Neg logit contributions
affle-0.668
rimination-0.617
 offender-0.614
icut-0.605
bourne-0.595
Token fact
Token ID1109
Feature activation+4.00e-01

Pos logit contributions
affle+0.026
rimination+0.024
 offender+0.024
icut+0.023
bourne+0.023
Neg logit contributions
unity-0.017
 Yo-0.016
 Sergey-0.016
 VP-0.015
 travelled-0.015
Token-
Token ID12
Feature activation-3.06e-01

Pos logit contributions
affle+0.817
rimination+0.748
 offender+0.737
icut+0.718
bourne+0.709
Neg logit contributions
unity-0.934
 Yo-0.909
 Sergey-0.900
 VP-0.863
 Juno-0.856
Tokencheck
Token ID9122
Feature activation-1.15e+00

Pos logit contributions
unity+0.674
 Yo+0.650
 Sergey+0.642
 VP+0.621
 travelled+0.610
Neg logit contributions
affle-0.668
rimination-0.616
 offender-0.605
icut-0.593
bourne-0.583
Tokeners
Token ID364
Feature activation-2.56e-03

Pos logit contributions
unity+2.327
 Yo+2.268
 Sergey+2.225
 VP+2.173
 UP+2.110
Neg logit contributions
affle-2.698
rimination-2.543
 offender-2.421
icut-2.410
bourne-2.386
Token behind
Token ID2157
Feature activation-1.89e-01

Pos logit contributions
unity+0.005
 Yo+0.005
 Sergey+0.005
 VP+0.004
ulum+0.004
Neg logit contributions
affle-0.006
rimination-0.006
 offender-0.006
icut-0.006
bourne-0.006
Token the
Token ID262
Feature activation-3.47e-02

Pos logit contributions
unity+0.337
 Yo+0.323
 Sergey+0.319
 VP+0.303
 travelled+0.300
Neg logit contributions
affle-0.493
rimination-0.458
 offender-0.454
icut-0.446
bourne-0.440
Token fall
Token ID2121
Feature activation+1.82e-01

Pos logit contributions
unity+0.071
 Yo+0.069
 Sergey+0.068
 VP+0.065
 travelled+0.065
Neg logit contributions
affle-0.080
rimination-0.074
 offender-0.073
icut-0.072
bourne-0.071
Token TV
Token ID3195
Feature activation+8.34e-03

Pos logit contributions
affle+0.436
rimination+0.402
 offender+0.400
icut+0.390
bourne+0.387
Neg logit contributions
unity-0.362
 Yo-0.351
 Sergey-0.345
 VP-0.329
 travelled-0.327
Token though
Token ID996
Feature activation+1.07e-01

Pos logit contributions
unity+0.117
 Yo+0.112
 Sergey+0.111
 VP+0.106
ulum+0.104
Neg logit contributions
affle-0.154
rimination-0.143
 offender-0.141
icut-0.138
bourne-0.137
Token.)
Token ID2014
Feature activation-5.97e-02

Pos logit contributions
affle+0.301
rimination+0.282
 offender+0.281
icut+0.273
bourne+0.272
Neg logit contributions
unity-0.169
 Yo-0.160
 Sergey-0.158
 VP-0.149
ulum-0.147
Token
Token ID198
Feature activation+6.58e-02

Pos logit contributions
unity+0.113
 Yo+0.108
 Sergey+0.107
 VP+0.102
ulum+0.101
Neg logit contributions
affle-0.149
rimination-0.138
 offender-0.137
icut-0.134
bourne-0.132
Token
Token ID198
Feature activation+2.99e-02

Pos logit contributions
affle+0.179
rimination+0.170
 offender+0.166
icut+0.164
 pitfalls+0.160
Neg logit contributions
unity-0.110
 Yo-0.107
 Sergey-0.105
 VP-0.100
 UP-0.098
TokenHon
Token ID29478
Feature activation-1.54e-01

Pos logit contributions
affle+0.063
rimination+0.057
 offender+0.056
icut+0.055
bourne+0.054
Neg logit contributions
unity-0.069
 Yo-0.067
 Sergey-0.066
 VP-0.063
 travelled-0.063
Tokenorable
Token ID10475
Feature activation-1.12e+00

Pos logit contributions
unity+0.304
 Yo+0.294
 Sergey+0.291
 VP+0.278
 Juno+0.274
Neg logit contributions
affle-0.368
rimination-0.342
 offender-0.337
icut-0.331
bourne-0.327
Token M
Token ID337
Feature activation+1.81e-01

Pos logit contributions
unity+2.239
 Yo+2.207
 Sergey+2.177
 VP+2.083
 Juno+2.057
Neg logit contributions
affle-2.602
rimination-2.436
icut-2.363
 offender-2.363
aba-2.323
Tokenention
Token ID1463
Feature activation-2.95e-01

Pos logit contributions
affle+0.373
rimination+0.342
 offender+0.333
icut+0.326
bourne+0.322
Neg logit contributions
unity-0.419
 Yo-0.409
 Sergey-0.405
 VP-0.391
 Juno-0.387
Token:
Token ID25
Feature activation+6.74e-02

Pos logit contributions
unity+0.563
 Yo+0.541
 Sergey+0.534
 VP+0.510
 travelled+0.504
Neg logit contributions
affle-0.730
rimination-0.678
 offender-0.672
icut-0.657
bourne-0.649
Token
Token ID198
Feature activation+3.00e-02

Pos logit contributions
affle+0.165
rimination+0.153
 offender+0.151
icut+0.148
bourne+0.146
Neg logit contributions
unity-0.131
 Yo-0.125
 Sergey-0.124
 VP-0.118
 travelled-0.118
Token
Token ID198
Feature activation+7.19e-02

Pos logit contributions
affle+0.083
rimination+0.079
 offender+0.077
icut+0.077
 pitfalls+0.075
Neg logit contributions
unity-0.049
 Yo-0.048
 Sergey-0.047
 VP-0.044
 UP-0.044
Token set
Token ID900
Feature activation-2.38e-01

Pos logit contributions
unity+0.371
 Yo+0.361
 Sergey+0.354
 VP+0.339
 travelled+0.335
Neg logit contributions
affle-0.461
rimination-0.429
 offender-0.420
icut-0.415
bourne-0.409
Token in
Token ID287
Feature activation-2.58e-01

Pos logit contributions
unity+0.422
 Yo+0.406
 Sergey+0.400
 VP+0.381
 Juno+0.374
Neg logit contributions
affle-0.623
rimination-0.582
 offender-0.574
icut-0.564
bourne-0.558
Token a
Token ID257
Feature activation-9.34e-02

Pos logit contributions
unity+0.463
 Yo+0.448
 Sergey+0.440
 VP+0.419
 Juno+0.413
Neg logit contributions
affle-0.668
rimination-0.624
 offender-0.614
icut-0.604
bourne-0.596
Token proced
Token ID5131
Feature activation-4.85e-01

Pos logit contributions
unity+0.183
 Yo+0.178
 Sergey+0.175
 VP+0.168
 Juno+0.165
Neg logit contributions
affle-0.227
rimination-0.211
 offender-0.207
icut-0.203
bourne-0.201
Tokenurally
Token ID20221
Feature activation-2.68e-01

Pos logit contributions
unity+0.836
 Yo+0.813
 Sergey+0.785
 VP+0.741
ulum+0.739
Neg logit contributions
affle-1.283
rimination-1.204
 offender-1.201
bourne-1.158
icut-1.156
Token generated
Token ID7560
Feature activation-1.10e+00

Pos logit contributions
unity+0.480
 Yo+0.463
 Sergey+0.456
 VP+0.434
 travelled+0.427
Neg logit contributions
affle-0.695
rimination-0.650
 offender-0.640
icut-0.629
bourne-0.622
Token city
Token ID1748
Feature activation+2.35e-01

Pos logit contributions
 Yo+1.907
unity+1.906
 Sergey+1.849
 VP+1.758
 UP+1.741
Neg logit contributions
affle-2.876
rimination-2.695
 offender-2.594
icut-2.579
bourne-2.550
Token.
Token ID13
Feature activation-4.05e-02

Pos logit contributions
affle+0.574
rimination+0.533
 offender+0.528
icut+0.517
bourne+0.511
Neg logit contributions
unity-0.453
 Yo-0.436
 Sergey-0.430
 VP-0.412
ulum-0.406
Token This
Token ID770
Feature activation-4.07e-02

Pos logit contributions
unity+0.083
 Yo+0.080
 Sergey+0.079
 VP+0.076
ulum+0.075
Neg logit contributions
affle-0.094
rimination-0.087
 offender-0.086
icut-0.084
bourne-0.083
Token series
Token ID2168
Feature activation-1.68e-01

Pos logit contributions
unity+0.089
 Yo+0.087
 Sergey+0.085
 VP+0.082
 travelled+0.081
Neg logit contributions
affle-0.090
rimination-0.083
 offender-0.081
icut-0.080
bourne-0.078
Token of
Token ID286
Feature activation-1.93e-01

Pos logit contributions
unity+0.349
 Yo+0.339
 Sergey+0.335
 VP+0.321
 travelled+0.318
Neg logit contributions
affle-0.387
rimination-0.359
 offender-0.351
icut-0.347
bourne-0.341
Token according
Token ID1864
Feature activation-1.04e-01

Pos logit contributions
unity+0.265
 Yo+0.257
 Sergey+0.253
 VP+0.242
 travelled+0.238
Neg logit contributions
affle-0.331
rimination-0.308
 offender-0.303
icut-0.298
bourne-0.294
Token to
Token ID284
Feature activation-2.23e-01

Pos logit contributions
unity+0.163
 Yo+0.158
 Sergey+0.155
 VP+0.147
 UP+0.144
Neg logit contributions
affle-0.292
rimination-0.276
 offender-0.271
icut-0.266
bourne-0.263
Token the
Token ID262
Feature activation-1.71e-01

Pos logit contributions
unity+0.383
 Yo+0.367
 Sergey+0.362
 VP+0.344
 travelled+0.338
Neg logit contributions
affle-0.593
rimination-0.555
 offender-0.548
icut-0.539
bourne-0.532
Token University
Token ID2059
Feature activation-3.05e-02

Pos logit contributions
unity+0.290
 Yo+0.281
 Sergey+0.275
 VP+0.263
 UP+0.258
Neg logit contributions
affle-0.458
rimination-0.429
 offender-0.422
icut-0.416
bourne-0.411
Token of
Token ID286
Feature activation-3.35e-01

Pos logit contributions
unity+0.063
 Yo+0.061
 Sergey+0.060
 VP+0.057
ulum+0.057
Neg logit contributions
affle-0.071
rimination-0.065
 offender-0.065
icut-0.063
aba-0.063
Token Hawaii
Token ID13708
Feature activation-1.08e+00

Pos logit contributions
unity+0.668
 Yo+0.651
 Sergey+0.640
 VP+0.614
 UP+0.606
Neg logit contributions
affle-0.796
rimination-0.741
 offender-0.727
icut-0.712
bourne-0.704
Token study
Token ID2050
Feature activation-1.10e-01

Pos logit contributions
unity+2.038
 Yo+1.986
 Sergey+1.950
 VP+1.878
 UP+1.846
Neg logit contributions
affle-2.678
rimination-2.490
 offender-2.444
icut-2.400
bourne-2.387
Token cited
Token ID9181
Feature activation-3.43e-01

Pos logit contributions
unity+0.201
 Yo+0.194
 Sergey+0.191
 VP+0.183
 travelled+0.180
Neg logit contributions
affle-0.279
rimination-0.260
 offender-0.256
icut-0.252
bourne-0.249
Token previously
Token ID4271
Feature activation-8.25e-02

Pos logit contributions
unity+0.572
 Yo+0.549
 Sergey+0.541
 VP+0.513
 Juno+0.504
Neg logit contributions
affle-0.930
rimination-0.872
 offender-0.861
icut-0.847
bourne-0.836
Token
Token ID784
Feature activation-1.97e-01

Pos logit contributions
unity+0.149
 Yo+0.144
 Sergey+0.142
 VP+0.135
 Juno+0.133
Neg logit contributions
affle-0.212
rimination-0.198
 offender-0.195
icut-0.192
bourne-0.190
Token rely
Token ID8814
Feature activation+4.57e-02

Pos logit contributions
unity+0.395
 Yo+0.384
 Sergey+0.378
 VP+0.362
 travelled+0.358
Neg logit contributions
affle-0.467
rimination-0.434
 offender-0.427
icut-0.419
bourne-0.413
Token those
Token ID883
Feature activation-2.66e-01

Pos logit contributions
unity+0.464
 Yo+0.450
 Sergey+0.443
 VP+0.423
 Juno+0.416
Neg logit contributions
affle-0.642
rimination-0.599
 offender-0.589
icut-0.579
bourne-0.573
Token harsh
Token ID11859
Feature activation-9.71e-02

Pos logit contributions
unity+0.417
 Yo+0.406
 Sergey+0.399
 VP+0.378
 Juno+0.371
Neg logit contributions
affle-0.745
rimination-0.701
 offender-0.686
icut-0.678
bourne-0.672
Token conditions
Token ID3403
Feature activation+2.23e-01

Pos logit contributions
unity+0.147
 Yo+0.140
 Sergey+0.138
 VP+0.130
 Juno+0.127
Neg logit contributions
affle-0.279
rimination-0.262
 offender-0.259
icut-0.255
bourne-0.252
Token while
Token ID981
Feature activation-3.18e-01

Pos logit contributions
affle+0.557
rimination+0.520
 offender+0.514
icut+0.505
bourne+0.498
Neg logit contributions
unity-0.417
 Yo-0.399
 Sergey-0.395
 VP-0.376
ulum-0.371
Token still
Token ID991
Feature activation-1.71e-01

Pos logit contributions
unity+0.621
 Yo+0.600
 Sergey+0.593
 VP+0.567
 Juno+0.558
Neg logit contributions
affle-0.774
rimination-0.720
 offender-0.709
icut-0.696
bourne-0.687
Token generating
Token ID15453
Feature activation-1.07e+00

Pos logit contributions
unity+0.345
 Yo+0.332
 Sergey+0.328
 VP+0.314
ulum+0.310
Neg logit contributions
affle-0.402
rimination-0.374
 offender-0.369
icut-0.361
bourne-0.356
Token electricity
Token ID8744
Feature activation-2.32e-01

Pos logit contributions
unity+2.041
 Yo+2.021
 Sergey+1.982
 VP+1.910
 UP+1.884
Neg logit contributions
affle-2.637
rimination-2.464
 offender-2.389
icut-2.369
bourne-2.339
Token "
Token ID366
Feature activation-1.71e-01

Pos logit contributions
unity+0.436
 Yo+0.420
 Sergey+0.414
 VP+0.395
 Juno+0.389
Neg logit contributions
affle-0.579
rimination-0.539
 offender-0.531
icut-0.522
bourne-0.516
Tokenat
Token ID265
Feature activation+4.61e-02

Pos logit contributions
unity+0.396
 Yo+0.386
 Sergey+0.382
 VP+0.368
 travelled+0.363
Neg logit contributions
affle-0.352
rimination-0.322
 offender-0.316
icut-0.310
bourne-0.305
Token relatively
Token ID5365
Feature activation+2.38e-02

Pos logit contributions
affle+0.111
rimination+0.103
 offender+0.102
icut+0.100
bourne+0.098
Neg logit contributions
unity-0.091
 Yo-0.088
 Sergey-0.087
 VP-0.083
 travelled-0.082
Token high
Token ID1029
Feature activation+4.66e-01

Pos logit contributions
affle+0.040
rimination+0.036
 offender+0.035
icut+0.034
bourne+0.033
Neg logit contributions
unity-0.065
 Yo-0.063
 Sergey-0.063
 VP-0.061
 UP-0.060
Token ranking
Token ID12759
Feature activation-4.63e-02

Pos logit contributions
unity+0.036
 Yo+0.035
 Sergey+0.035
 VP+0.033
 Juno+0.032
Neg logit contributions
affle-0.048
rimination-0.045
 offender-0.044
icut-0.043
bourne-0.043
Token member
Token ID2888
Feature activation-5.29e-01

Pos logit contributions
unity+0.088
 Yo+0.085
 Sergey+0.084
 VP+0.080
 Juno+0.079
Neg logit contributions
affle-0.114
rimination-0.107
 offender-0.105
icut-0.103
bourne-0.102
Token of
Token ID286
Feature activation-2.07e-02

Pos logit contributions
unity+1.065
 Yo+1.031
 Sergey+1.017
 VP+0.974
 Juno+0.960
Neg logit contributions
affle-1.252
rimination-1.162
 offender-1.145
icut-1.123
bourne-1.108
Token the
Token ID262
Feature activation+1.11e-01

Pos logit contributions
unity+0.035
 Yo+0.034
 Sergey+0.033
 VP+0.031
 Juno+0.031
Neg logit contributions
affle-0.055
rimination-0.052
 offender-0.051
icut-0.050
bourne-0.050
Token House
Token ID2097
Feature activation-4.91e-02

Pos logit contributions
affle+0.244
rimination+0.224
 offender+0.220
icut+0.216
bourne+0.213
Neg logit contributions
unity-0.241
 Yo-0.234
 Sergey-0.232
 VP-0.223
 UP-0.219
Token Oversight
Token ID35968
Feature activation-1.06e+00

Pos logit contributions
unity+0.103
 Yo+0.100
 Sergey+0.099
 VP+0.095
 travelled+0.093
Neg logit contributions
affle-0.112
rimination-0.104
 offender-0.102
icut-0.100
bourne-0.099
Token Committee
Token ID4606
Feature activation+1.11e-01

Pos logit contributions
unity+2.065
 Yo+1.994
 Sergey+1.976
 VP+1.889
 UP+1.859
Neg logit contributions
affle-2.553
rimination-2.370
 offender-2.338
icut-2.313
bourne-2.281
Token,
Token ID11
Feature activation+8.56e-02

Pos logit contributions
affle+0.256
rimination+0.237
 offender+0.233
icut+0.229
bourne+0.226
Neg logit contributions
unity-0.230
 Yo-0.222
 Sergey-0.220
 VP-0.211
 Juno-0.208
Token asked
Token ID1965
Feature activation+2.04e-01

Pos logit contributions
affle+0.205
rimination+0.190
 offender+0.187
icut+0.184
bourne+0.181
Neg logit contributions
unity-0.170
 Yo-0.164
 Sergey-0.162
 VP-0.155
 Juno-0.153
Token the
Token ID262
Feature activation+4.08e-02

Pos logit contributions
affle+0.568
rimination+0.533
 offender+0.527
icut+0.518
aba+0.511
Neg logit contributions
unity-0.325
 Yo-0.309
 Sergey-0.301
 VP-0.286
 travelled-0.285
Token Trump
Token ID1301
Feature activation-1.18e-01

Pos logit contributions
affle+0.106
rimination+0.099
 offender+0.098
icut+0.096
bourne+0.095
Neg logit contributions
unity-0.072
 Yo-0.070
 Sergey-0.069
 VP-0.066
 Juno-0.064
Token:
Token ID25
Feature activation-1.25e-01

Pos logit contributions
unity+0.275
 Yo+0.270
 Sergey+0.265
 VP+0.252
 UP+0.250
Neg logit contributions
affle-0.404
rimination-0.382
 offender-0.371
icut-0.370
aba-0.364
Token Like
Token ID4525
Feature activation-2.11e-01

Pos logit contributions
unity+0.311
 Yo+0.306
 Sergey+0.301
 VP+0.289
 Juno+0.287
Neg logit contributions
affle-0.234
rimination-0.215
 offender-0.210
icut-0.206
bourne-0.202
Token Loading
Token ID12320
Feature activation-3.34e-01

Pos logit contributions
unity+0.318
 Yo+0.308
 Sergey+0.302
 VP+0.285
 UP+0.279
Neg logit contributions
affle-0.604
rimination-0.571
 offender-0.561
icut-0.554
bourne-0.547
Token...
Token ID986
Feature activation-6.25e-01

Pos logit contributions
unity+0.524
 Yo+0.511
 Sergey+0.497
 VP+0.477
 UP+0.468
Neg logit contributions
affle-0.934
rimination-0.885
 offender-0.866
icut-0.854
aba-0.842
Token<|endoftext|>
Token ID50256
Feature activation-9.93e-02

Pos logit contributions
unity+1.200
 Yo+1.157
 Sergey+1.143
 VP+1.091
 travelled+1.075
Neg logit contributions
affle-1.539
rimination-1.429
 offender-1.408
icut-1.383
bourne-1.368
TokenGoogle
Token ID11708
Feature activation-1.03e+00

Pos logit contributions
unity+0.204
 Yo+0.198
 Sergey+0.196
 VP+0.188
 travelled+0.185
Neg logit contributions
affle-0.230
rimination-0.213
 offender-0.209
icut-0.206
bourne-0.203
Token logo
Token ID11112
Feature activation-1.11e-01

Pos logit contributions
unity+1.943
 Yo+1.898
 Sergey+1.873
 VP+1.802
 UP+1.758
Neg logit contributions
affle-2.552
rimination-2.377
 offender-2.341
icut-2.303
bourne-2.274
Token is
Token ID318
Feature activation-1.36e-01

Pos logit contributions
unity+0.210
 Yo+0.203
 Sergey+0.200
 VP+0.191
 Juno+0.188
Neg logit contributions
affle-0.277
rimination-0.258
 offender-0.254
icut-0.249
bourne-0.246
Token displayed
Token ID9066
Feature activation-2.20e-01

Pos logit contributions
unity+0.260
 Yo+0.251
 Sergey+0.248
 VP+0.237
 travelled+0.233
Neg logit contributions
affle-0.336
rimination-0.313
 offender-0.308
icut-0.303
bourne-0.299
Token outside
Token ID2354
Feature activation-5.35e-02

Pos logit contributions
unity+0.399
 Yo+0.385
 Sergey+0.379
 VP+0.362
 Juno+0.355
Neg logit contributions
affle-0.566
rimination-0.528
 offender-0.521
icut-0.512
bourne-0.506
Token of
Token ID286
Feature activation-2.00e-03

Pos logit contributions
unity+0.094
 Yo+0.090
 Sergey+0.089
 VP+0.084
 travelled+0.083
Neg logit contributions
affle-0.141
rimination-0.131
 offender-0.130
icut-0.127
bourne-0.126
Token providing
Token ID4955
Feature activation-5.84e-01

Pos logit contributions
unity+0.159
 Yo+0.154
 Sergey+0.152
 VP+0.145
ulum+0.143
Neg logit contributions
affle-0.196
rimination-0.182
 offender-0.180
icut-0.177
bourne-0.175
Token steam
Token ID13324
Feature activation+8.54e-02

Pos logit contributions
unity+1.127
 Yo+1.101
 Sergey+1.088
 VP+1.043
 UP+1.028
Neg logit contributions
affle-1.429
rimination-1.338
 offender-1.301
icut-1.278
bourne-1.267
Token for
Token ID329
Feature activation-2.55e-01

Pos logit contributions
affle+0.214
rimination+0.200
 offender+0.197
icut+0.194
bourne+0.192
Neg logit contributions
unity-0.159
 Yo-0.153
 Sergey-0.151
 VP-0.144
 Juno-0.142
Token turbines
Token ID35658
Feature activation-1.32e-01

Pos logit contributions
unity+0.483
 Yo+0.464
 Sergey+0.456
 VP+0.436
ulum+0.433
Neg logit contributions
affle-0.635
rimination-0.590
 offender-0.584
icut-0.573
bourne-0.566
Token which
Token ID543
Feature activation-8.20e-02

Pos logit contributions
unity+0.250
 Yo+0.241
 Sergey+0.237
 VP+0.227
ulum+0.224
Neg logit contributions
affle-0.326
rimination-0.303
 offender-0.299
icut-0.294
bourne-0.291
Token generated
Token ID7560
Feature activation-1.02e+00

Pos logit contributions
unity+0.153
 Yo+0.147
 Sergey+0.145
 VP+0.138
ulum+0.137
Neg logit contributions
affle-0.205
rimination-0.191
 offender-0.189
icut-0.185
bourne-0.184
Token electricity
Token ID8744
Feature activation-1.52e-01

Pos logit contributions
unity+1.868
 Yo+1.826
 Sergey+1.797
 VP+1.722
 UP+1.693
Neg logit contributions
affle-2.582
rimination-2.421
 offender-2.362
icut-2.327
bourne-2.299
Token to
Token ID284
Feature activation-2.14e-01

Pos logit contributions
unity+0.285
 Yo+0.272
 Sergey+0.270
 VP+0.256
ulum+0.255
Neg logit contributions
affle-0.380
rimination-0.353
 offender-0.350
icut-0.344
aba-0.340
Token deliver
Token ID5203
Feature activation-6.43e-01

Pos logit contributions
unity+0.376
 Yo+0.361
 Sergey+0.355
 VP+0.338
ulum+0.334
Neg logit contributions
affle-0.564
rimination-0.525
 offender-0.520
icut-0.511
bourne-0.506
Token 34
Token ID4974
Feature activation-3.81e-01

Pos logit contributions
unity+1.167
 Yo+1.133
 Sergey+1.118
 VP+1.066
 travelled+1.047
Neg logit contributions
affle-1.647
rimination-1.542
 offender-1.511
icut-1.487
bourne-1.470
Token MW
Token ID29961
Feature activation+1.32e-01

Pos logit contributions
unity+0.679
 Yo+0.656
 Sergey+0.645
 VP+0.616
 travelled+0.604
Neg logit contributions
affle-0.989
rimination-0.924
 offender-0.910
icut-0.896
bourne-0.884
Token.
Token ID13
Feature activation+6.88e-02

Pos logit contributions
affle+0.696
rimination+0.648
 offender+0.640
icut+0.624
aba+0.619
Neg logit contributions
unity-0.570
 Yo-0.547
 Sergey-0.542
 VP-0.518
 Juno-0.511
Token
Token ID447
Feature activation+1.13e-01

Pos logit contributions
affle+0.167
rimination+0.156
 offender+0.153
icut+0.150
bourne+0.149
Neg logit contributions
unity-0.134
 Yo-0.129
 Sergey-0.127
 VP-0.122
 travelled-0.121
Token
Token ID251
Feature activation-1.40e-01

Pos logit contributions
affle+0.333
rimination+0.313
 offender+0.309
icut+0.304
bourne+0.302
Neg logit contributions
unity-0.163
 Yo-0.156
 Sergey-0.154
 VP-0.144
 travelled-0.142
Token<|endoftext|>
Token ID50256
Feature activation+6.75e-02

Pos logit contributions
unity+0.275
 Yo+0.264
 Sergey+0.261
 VP+0.249
 travelled+0.247
Neg logit contributions
affle-0.341
rimination-0.316
 offender-0.311
icut-0.306
bourne-0.302
TokenUsing
Token ID12814
Feature activation+1.93e-01

Pos logit contributions
affle+0.156
rimination+0.144
 offender+0.142
icut+0.140
bourne+0.138
Neg logit contributions
unity-0.139
 Yo-0.135
 Sergey-0.134
 VP-0.128
 travelled-0.127
Token Google
Token ID3012
Feature activation-1.02e+00

Pos logit contributions
affle+0.492
rimination+0.457
 offender+0.453
icut+0.444
aba+0.437
Neg logit contributions
unity-0.354
 Yo-0.338
 Sergey-0.334
 VP-0.317
ulum-0.316
Token
Token ID447
Feature activation-1.86e-01

Pos logit contributions
unity+1.721
 Yo+1.679
 Sergey+1.647
 VP+1.573
 UP+1.537
Neg logit contributions
affle-2.714
rimination-2.544
 offender-2.503
icut-2.475
bourne-2.443
Token
Token ID247
Feature activation-9.09e-02

Pos logit contributions
unity+0.322
 Yo+0.310
 Sergey+0.306
 VP+0.290
 Juno+0.285
Neg logit contributions
affle-0.493
rimination-0.461
 offender-0.455
icut-0.447
bourne-0.442
Tokens
Token ID82
Feature activation-1.67e-01

Pos logit contributions
unity+0.174
 Yo+0.168
 Sergey+0.165
 VP+0.158
 travelled+0.156
Neg logit contributions
affle-0.225
rimination-0.209
 offender-0.206
icut-0.202
bourne-0.200
Token new
Token ID649
Feature activation-2.08e-01

Pos logit contributions
unity+0.306
 Yo+0.296
 Sergey+0.291
 VP+0.278
 Juno+0.273
Neg logit contributions
affle-0.425
rimination-0.396
 offender-0.390
icut-0.384
bourne-0.379
Token domain
Token ID7386
Feature activation-5.72e-02

Pos logit contributions
unity+0.385
 Yo+0.373
 Sergey+0.367
 VP+0.351
 UP+0.345
Neg logit contributions
affle-0.524
rimination-0.489
 offender-0.481
icut-0.474
bourne-0.468
TokenEND
Token ID10619
Feature activation+5.09e-01

Pos logit contributions
affle+0.342
rimination+0.312
 offender+0.309
icut+0.299
bourne+0.298
Neg logit contributions
unity-0.341
 Yo-0.332
 Sergey-0.330
 VP-0.314
 travelled-0.313
Token()
Token ID3419
Feature activation-1.73e-02

Pos logit contributions
affle+1.124
rimination+1.025
 offender+1.017
icut+0.987
bourne+0.981
Neg logit contributions
unity-1.111
 Yo-1.068
 Sergey-1.053
 VP-1.004
 Juno-0.998
Token
Token ID198
Feature activation-6.66e-03

Pos logit contributions
unity+0.031
 Yo+0.030
 Sergey+0.029
 VP+0.028
 Juno+0.027
Neg logit contributions
affle-0.045
rimination-0.042
 offender-0.041
icut-0.041
bourne-0.040
Token
Token ID198
Feature activation-2.90e-03

Pos logit contributions
unity+0.011
 Yo+0.011
 Sergey+0.010
 VP+0.010
 UP+0.010
Neg logit contributions
affle-0.018
rimination-0.018
 offender-0.017
icut-0.017
bourne-0.017
TokenThis
Token ID1212
Feature activation-2.70e-01

Pos logit contributions
unity+0.006
 Yo+0.006
 Sergey+0.006
 VP+0.006
 Juno+0.006
Neg logit contributions
affle-0.006
rimination-0.006
 offender-0.006
icut-0.006
bourne-0.006
Token generates
Token ID18616
Feature activation-1.01e+00

Pos logit contributions
unity+0.534
 Yo+0.519
 Sergey+0.512
 VP+0.490
 UP+0.483
Neg logit contributions
affle-0.647
rimination-0.602
 offender-0.589
icut-0.582
bourne-0.575
Token a
Token ID257
Feature activation-3.63e-02

Pos logit contributions
unity+1.699
 Yo+1.657
 Sergey+1.630
 VP+1.560
 UP+1.531
Neg logit contributions
affle-2.690
rimination-2.529
 offender-2.478
icut-2.455
bourne-2.432
Token function
Token ID2163
Feature activation+6.10e-02

Pos logit contributions
unity+0.074
 Yo+0.072
 Sergey+0.071
 VP+0.068
 travelled+0.067
Neg logit contributions
affle-0.085
rimination-0.079
 offender-0.077
icut-0.076
bourne-0.075
Token very
Token ID845
Feature activation+1.11e-01

Pos logit contributions
affle+0.153
rimination+0.143
 offender+0.141
icut+0.138
bourne+0.137
Neg logit contributions
unity-0.114
 Yo-0.110
 Sergey-0.109
 VP-0.104
 Juno-0.102
Token similar
Token ID2092
Feature activation+7.62e-02

Pos logit contributions
affle+0.236
rimination+0.217
 offender+0.213
icut+0.209
bourne+0.206
Neg logit contributions
unity-0.252
 Yo-0.246
 Sergey-0.243
 VP-0.234
 Juno-0.231
Token to
Token ID284
Feature activation-1.50e-01

Pos logit contributions
affle+0.207
rimination+0.194
 offender+0.192
icut+0.189
bourne+0.187
Neg logit contributions
unity-0.127
 Yo-0.122
 Sergey-0.120
 VP-0.114
 Juno-0.111
Token
Token ID198
Feature activation-9.23e-02

Pos logit contributions
unity+0.056
 Yo+0.054
 Sergey+0.053
 VP+0.051
 travelled+0.050
Neg logit contributions
affle-0.074
rimination-0.069
 offender-0.068
icut-0.067
bourne-0.066
Token
Token ID198
Feature activation-4.17e-02

Pos logit contributions
unity+0.151
 Yo+0.148
 Sergey+0.144
 VP+0.137
 UP+0.135
Neg logit contributions
affle-0.254
rimination-0.241
 offender-0.237
icut-0.234
 pitfalls-0.228
TokenStory
Token ID11605
Feature activation-6.74e-01

Pos logit contributions
unity+0.091
 Yo+0.088
 Sergey+0.087
 VP+0.084
 travelled+0.083
Neg logit contributions
affle-0.092
rimination-0.085
 offender-0.083
icut-0.082
bourne-0.080
Token continues
Token ID4477
Feature activation-4.68e-01

Pos logit contributions
unity+1.297
 Yo+1.263
 Sergey+1.238
 VP+1.183
 travelled+1.177
Neg logit contributions
affle-1.682
rimination-1.529
 offender-1.520
icut-1.506
aba-1.460
Token below
Token ID2174
Feature activation-2.57e-01

Pos logit contributions
unity+0.917
 Yo+0.907
 Sergey+0.894
 VP+0.851
 UP+0.849
Neg logit contributions
affle-1.142
rimination-1.049
 offender-1.021
icut-1.017
bourne-1.005
Token advertisement
Token ID15422
Feature activation-1.00e+00

Pos logit contributions
unity+0.543
 Yo+0.529
 Sergey+0.523
 VP+0.502
 Juno+0.494
Neg logit contributions
affle-0.583
rimination-0.538
 offender-0.529
icut-0.520
bourne-0.514
Token
Token ID198
Feature activation-3.65e-01

Pos logit contributions
unity+1.481
 Yo+1.479
 Sergey+1.444
 VP+1.354
 UP+1.335
Neg logit contributions
affle-2.919
rimination-2.780
 offender-2.719
icut-2.696
uyomi-2.673
Token
Token ID198
Feature activation-2.96e-01

Pos logit contributions
unity+0.578
 Yo+0.568
 Sergey+0.553
 VP+0.523
 UP+0.515
Neg logit contributions
affle-1.026
rimination-0.974
 offender-0.958
icut-0.949
 pitfalls-0.927
TokenStory
Token ID11605
Feature activation-6.96e-01

Pos logit contributions
unity+0.585
 Yo+0.564
 Sergey+0.557
 VP+0.533
 Juno+0.525
Neg logit contributions
affle-0.711
rimination-0.662
 offender-0.652
icut-0.640
bourne-0.631
Token continues
Token ID4477
Feature activation-5.60e-01

Pos logit contributions
unity+1.280
 Yo+1.223
 Sergey+1.195
 VP+1.164
 travelled+1.154
Neg logit contributions
affle-1.813
rimination-1.661
icut-1.632
 offender-1.632
uyomi-1.575
Token below
Token ID2174
Feature activation-2.43e-01

Pos logit contributions
unity+1.062
 Yo+1.043
 Sergey+1.031
 UP+0.993
 VP+0.980
Neg logit contributions
affle-1.398
rimination-1.304
icut-1.259
 offender-1.253
bourne-1.239
Token according
Token ID1864
Feature activation-3.14e-02

Pos logit contributions
unity+0.019
 Yo+0.018
 Sergey+0.018
 VP+0.017
ulum+0.017
Neg logit contributions
affle-0.025
rimination-0.023
 offender-0.023
icut-0.023
bourne-0.022
Token to
Token ID284
Feature activation-1.62e-01

Pos logit contributions
unity+0.050
 Yo+0.048
 Sergey+0.047
 VP+0.045
 UP+0.044
Neg logit contributions
affle-0.088
rimination-0.083
 offender-0.081
icut-0.080
bourne-0.079
Token the
Token ID262
Feature activation-5.17e-02

Pos logit contributions
unity+0.280
 Yo+0.267
 Sergey+0.264
 VP+0.250
 travelled+0.247
Neg logit contributions
affle-0.431
rimination-0.403
 offender-0.399
icut-0.392
bourne-0.387
Token University
Token ID2059
Feature activation+5.95e-02

Pos logit contributions
unity+0.092
 Yo+0.089
 Sergey+0.087
 VP+0.083
 UP+0.082
Neg logit contributions
affle-0.135
rimination-0.126
 offender-0.124
icut-0.122
bourne-0.120
Token of
Token ID286
Feature activation-2.63e-01

Pos logit contributions
affle+0.137
rimination+0.127
 offender+0.125
icut+0.122
aba+0.121
Neg logit contributions
unity-0.124
 Yo-0.119
 Sergey-0.118
 VP-0.113
ulum-0.111
Token Hawai
Token ID10847
Feature activation-9.94e-01

Pos logit contributions
unity+0.515
 Yo+0.504
 Sergey+0.494
 VP+0.474
 UP+0.469
Neg logit contributions
affle-0.638
rimination-0.595
 offender-0.583
icut-0.572
bourne-0.566
Token
Token ID447
Feature activation-2.46e-02

Pos logit contributions
unity+2.323
 Yo+2.257
 Sergey+2.216
 VP+2.141
ulum+2.133
Neg logit contributions
affle-2.038
rimination-1.843
 offender-1.823
icut-1.785
bourne-1.767
Token
Token ID247
Feature activation+6.23e-02

Pos logit contributions
unity+0.031
 Yo+0.029
 Sergey+0.029
 VP+0.027
 travelled+0.026
Neg logit contributions
affle-0.077
rimination-0.073
 offender-0.072
icut-0.071
bourne-0.070
Tokeni
Token ID72
Feature activation-1.26e-01

Pos logit contributions
affle+0.147
rimination+0.136
 offender+0.134
icut+0.132
bourne+0.130
Neg logit contributions
unity-0.126
 Yo-0.122
 Sergey-0.121
 VP-0.115
 travelled-0.114
Token,
Token ID11
Feature activation-1.13e-01

Pos logit contributions
unity+0.251
 Yo+0.243
 Sergey+0.240
 VP+0.229
 travelled+0.226
Neg logit contributions
affle-0.300
rimination-0.279
 offender-0.274
icut-0.269
bourne-0.266
Token there
Token ID612
Feature activation+5.84e-02

Pos logit contributions
unity+0.212
 Yo+0.204
 Sergey+0.201
 VP+0.192
ulum+0.189
Neg logit contributions
affle-0.284
rimination-0.264
 offender-0.261
icut-0.256
bourne-0.253
Token the
Token ID262
Feature activation-6.16e-03

Pos logit contributions
affle+0.154
rimination+0.143
 offender+0.142
icut+0.139
bourne+0.138
Neg logit contributions
unity-0.102
 Yo-0.098
 Sergey-0.096
 VP-0.092
ulum-0.090
Token magazine
Token ID7093
Feature activation-4.51e-01

Pos logit contributions
unity+0.012
 Yo+0.012
 Sergey+0.012
 VP+0.011
 travelled+0.011
Neg logit contributions
affle-0.015
rimination-0.014
 offender-0.014
icut-0.013
bourne-0.013
Token carriers
Token ID16651
Feature activation-6.45e-02

Pos logit contributions
unity+0.948
 Yo+0.921
 Sergey+0.910
 VP+0.873
 travelled+0.861
Neg logit contributions
affle-1.026
rimination-0.950
 offender-0.932
icut-0.915
bourne-0.902
Token on
Token ID319
Feature activation+8.32e-02

Pos logit contributions
unity+0.122
 Yo+0.118
 Sergey+0.117
 VP+0.111
 travelled+0.110
Neg logit contributions
affle-0.160
rimination-0.149
 offender-0.147
icut-0.144
bourne-0.142
Token his
Token ID465
Feature activation-1.23e-01

Pos logit contributions
affle+0.214
rimination+0.198
 offender+0.197
icut+0.193
bourne+0.190
Neg logit contributions
unity-0.152
 Yo-0.145
 Sergey-0.143
 VP-0.137
ulum-0.135
Token belt
Token ID10999
Feature activation-9.88e-01

Pos logit contributions
unity+0.277
 Yo+0.270
 Sergey+0.267
 VP+0.257
 Juno+0.253
Neg logit contributions
affle-0.262
rimination-0.241
 offender-0.236
icut-0.232
bourne-0.228
Token was
Token ID373
Feature activation-2.05e-02

Pos logit contributions
unity+1.975
 Yo+1.930
 Sergey+1.907
 VP+1.821
 travelled+1.812
Neg logit contributions
affle-2.327
rimination-2.172
 offender-2.111
icut-2.093
bourne-2.047
Token open
Token ID1280
Feature activation-2.30e-01

Pos logit contributions
unity+0.038
 Yo+0.037
 Sergey+0.036
 VP+0.035
ulum+0.034
Neg logit contributions
affle-0.052
rimination-0.048
 offender-0.048
icut-0.047
bourne-0.046
Token and
Token ID290
Feature activation-1.53e-01

Pos logit contributions
unity+0.429
 Yo+0.417
 Sergey+0.410
 VP+0.393
 travelled+0.386
Neg logit contributions
affle-0.577
rimination-0.538
 offender-0.527
icut-0.519
bourne-0.513
Token the
Token ID262
Feature activation-7.62e-02

Pos logit contributions
unity+0.298
 Yo+0.287
 Sergey+0.283
 VP+0.271
 Juno+0.267
Neg logit contributions
affle-0.371
rimination-0.345
 offender-0.340
icut-0.333
bourne-0.329
Token loaded
Token ID9639
Feature activation-2.33e-01

Pos logit contributions
unity+0.152
 Yo+0.147
 Sergey+0.145
 VP+0.139
 Juno+0.137
Neg logit contributions
affle-0.181
rimination-0.168
 offender-0.166
icut-0.163
bourne-0.161
Token's
Token ID338
Feature activation+5.70e-02

Pos logit contributions
unity+0.370
 Yo+0.355
 Sergey+0.351
 VP+0.334
 UP+0.329
Neg logit contributions
affle-0.508
rimination-0.473
 offender-0.468
icut-0.458
bourne-0.454
Token ear
Token ID1027
Feature activation-1.20e-01

Pos logit contributions
affle+0.132
rimination+0.122
 offender+0.120
icut+0.117
bourne+0.116
Neg logit contributions
unity-0.118
 Yo-0.114
 Sergey-0.113
 VP-0.108
ulum-0.106
Token with
Token ID351
Feature activation-5.41e-02

Pos logit contributions
unity+0.288
 Yo+0.279
 Sergey+0.277
 VP+0.266
 Juno+0.264
Neg logit contributions
affle-0.237
rimination-0.216
 offender-0.213
icut-0.206
bourne-0.206
Token a
Token ID257
Feature activation-2.98e-02

Pos logit contributions
unity+0.097
 Yo+0.093
 Sergey+0.092
 VP+0.088
 travelled+0.086
Neg logit contributions
affle-0.140
rimination-0.131
 offender-0.129
icut-0.126
bourne-0.125
Token hat
Token ID6877
Feature activation-4.73e-01

Pos logit contributions
unity+0.069
 Yo+0.067
 Sergey+0.066
 VP+0.064
 Juno+0.063
Neg logit contributions
affle-0.061
rimination-0.056
 offender-0.055
icut-0.054
bourne-0.053
Tokenchet
Token ID20043
Feature activation-9.88e-01

Pos logit contributions
unity+0.872
 Yo+0.843
 Sergey+0.829
 VP+0.791
 travelled+0.780
Neg logit contributions
affle-1.196
rimination-1.120
 offender-1.098
icut-1.084
bourne-1.069
Token at
Token ID379
Feature activation-8.11e-02

Pos logit contributions
unity+1.754
 Yo+1.723
 Sergey+1.688
 VP+1.609
 travelled+1.595
Neg logit contributions
affle-2.541
rimination-2.389
 offender-2.303
icut-2.298
bourne-2.265
Token the
Token ID262
Feature activation+2.47e-02

Pos logit contributions
unity+0.149
 Yo+0.144
 Sergey+0.142
 VP+0.135
 Juno+0.133
Neg logit contributions
affle-0.206
rimination-0.193
 offender-0.190
icut-0.187
bourne-0.184
Token same
Token ID976
Feature activation-2.35e-01

Pos logit contributions
affle+0.060
rimination+0.056
 offender+0.055
icut+0.054
bourne+0.053
Neg logit contributions
unity-0.048
 Yo-0.047
 Sergey-0.046
 VP-0.044
 Juno-0.043
Token Fred
Token ID8559
Feature activation+8.30e-03

Pos logit contributions
unity+0.421
 Yo+0.410
 Sergey+0.400
 VP+0.383
 Juno+0.378
Neg logit contributions
affle-0.605
rimination-0.569
 offender-0.554
icut-0.550
bourne-0.542
Token Meyer
Token ID23975
Feature activation-5.14e-03

Pos logit contributions
affle+0.026
rimination+0.025
 offender+0.025
icut+0.024
aba+0.024
Neg logit contributions
unity-0.010
 Yo-0.010
 Sergey-0.009
 VP-0.009
 Juno-0.008
Token said
Token ID531
Feature activation-1.53e-02

Pos logit contributions
affle+0.100
rimination+0.093
 offender+0.092
icut+0.090
bourne+0.089
Neg logit contributions
unity-0.076
 Yo-0.073
 Sergey-0.072
 VP-0.068
ulum-0.068
Token they
Token ID484
Feature activation+1.37e-01

Pos logit contributions
unity+0.029
 Yo+0.028
 Sergey+0.027
 VP+0.026
ulum+0.026
Neg logit contributions
affle-0.039
rimination-0.036
 offender-0.035
icut-0.035
bourne-0.034
Token are
Token ID389
Feature activation+8.79e-02

Pos logit contributions
affle+0.326
rimination+0.303
 offender+0.298
icut+0.292
bourne+0.289
Neg logit contributions
unity-0.272
 Yo-0.263
 Sergey-0.259
 VP-0.248
ulum-0.245
Token also
Token ID635
Feature activation-1.94e-01

Pos logit contributions
affle+0.211
rimination+0.195
 offender+0.194
icut+0.190
bourne+0.188
Neg logit contributions
unity-0.174
 Yo-0.167
 Sergey-0.165
 VP-0.158
ulum-0.156
Token considering
Token ID6402
Feature activation+2.41e-01

Pos logit contributions
unity+0.392
 Yo+0.379
 Sergey+0.375
 VP+0.359
 Juno+0.353
Neg logit contributions
affle-0.456
rimination-0.423
 offender-0.416
icut-0.408
bourne-0.403
Token former
Token ID1966
Feature activation-9.84e-01

Pos logit contributions
affle+0.594
rimination+0.550
 offender+0.546
icut+0.533
aba+0.528
Neg logit contributions
unity-0.462
 Yo-0.444
 Sergey-0.437
 VP-0.419
ulum-0.416
Token Force
Token ID5221
Feature activation-4.79e-01

Pos logit contributions
unity+1.717
 Yo+1.695
 Sergey+1.683
 VP+1.592
 Juno+1.555
Neg logit contributions
affle-2.581
rimination-2.422
 offender-2.334
icut-2.333
aba-2.285
Token India
Token ID3794
Feature activation-1.83e-01

Pos logit contributions
unity+0.710
 Yo+0.683
 Sergey+0.673
 VP+0.633
 Juno+0.617
Neg logit contributions
affle-1.389
rimination-1.317
 offender-1.289
icut-1.280
bourne-1.253
Token driver
Token ID4639
Feature activation-7.96e-01

Pos logit contributions
unity+0.360
 Yo+0.349
 Sergey+0.345
 VP+0.330
 Juno+0.324
Neg logit contributions
affle-0.441
rimination-0.410
 offender-0.403
icut-0.396
bourne-0.391
Token Vit
Token ID18271
Feature activation+4.58e-02

Pos logit contributions
unity+1.368
 Yo+1.345
 Sergey+1.333
 VP+1.249
 Juno+1.225
Neg logit contributions
affle-2.114
rimination-1.985
 offender-1.940
icut-1.918
bourne-1.884
Tokenanton
Token ID23026
Feature activation+3.80e-01

Pos logit contributions
affle+0.095
rimination+0.087
 offender+0.085
icut+0.083
bourne+0.082
Neg logit contributions
unity-0.106
 Yo-0.103
 Sergey-0.101
 VP-0.098
 Juno-0.097
Token all
Token ID477
Feature activation+4.95e-02

Pos logit contributions
affle+0.076
rimination+0.071
 offender+0.070
icut+0.069
bourne+0.068
Neg logit contributions
unity-0.057
 Yo-0.055
 Sergey-0.055
 VP-0.052
 travelled-0.051
Token find
Token ID1064
Feature activation-2.51e-01

Pos logit contributions
affle+0.120
rimination+0.112
 offender+0.110
icut+0.108
bourne+0.107
Neg logit contributions
unity-0.097
 Yo-0.094
 Sergey-0.092
 VP-0.088
 Juno-0.087
Token it
Token ID340
Feature activation+1.49e-01

Pos logit contributions
unity+0.542
 Yo+0.528
 Sergey+0.522
 VP+0.503
 UP+0.495
Neg logit contributions
affle-0.557
rimination-0.513
 offender-0.502
icut-0.494
bourne-0.488
Token below
Token ID2174
Feature activation+1.56e-01

Pos logit contributions
affle+0.322
rimination+0.297
 offender+0.294
icut+0.288
bourne+0.284
Neg logit contributions
unity-0.328
 Yo-0.316
 Sergey-0.312
 VP-0.299
ulum-0.297
Token the
Token ID262
Feature activation-2.87e-02

Pos logit contributions
affle+0.402
rimination+0.375
 offender+0.372
icut+0.364
bourne+0.360
Neg logit contributions
unity-0.282
 Yo-0.269
 Sergey-0.266
 VP-0.253
ulum-0.251
Token IPCC
Token ID35814
Feature activation-9.83e-01

Pos logit contributions
unity+0.056
 Yo+0.054
 Sergey+0.053
 VP+0.051
 travelled+0.050
Neg logit contributions
affle-0.070
rimination-0.065
 offender-0.064
icut-0.063
bourne-0.062
Token
Token ID447
Feature activation+9.90e-02

Pos logit contributions
unity+1.863
 Yo+1.812
 Sergey+1.787
 VP+1.725
 UP+1.692
Neg logit contributions
affle-2.432
rimination-2.255
 offender-2.214
icut-2.186
bourne-2.155
Token
Token ID247
Feature activation+1.08e-01

Pos logit contributions
affle+0.250
rimination+0.233
 offender+0.230
icut+0.225
bourne+0.223
Neg logit contributions
unity-0.182
 Yo-0.177
 Sergey-0.174
 VP-0.166
 Juno-0.164
Tokens
Token ID82
Feature activation+7.93e-03

Pos logit contributions
affle+0.242
rimination+0.224
 offender+0.220
icut+0.216
bourne+0.213
Neg logit contributions
unity-0.229
 Yo-0.222
 Sergey-0.219
 VP-0.210
 travelled-0.208
Token estimates
Token ID7746
Feature activation+1.56e-03

Pos logit contributions
affle+0.019
rimination+0.017
 offender+0.017
icut+0.017
bourne+0.016
Neg logit contributions
unity-0.016
 Yo-0.016
 Sergey-0.015
 VP-0.015
 Juno-0.015
Token.
Token ID13
Feature activation+1.99e-02

Pos logit contributions
affle+0.004
rimination+0.004
 offender+0.004
icut+0.004
bourne+0.003
Neg logit contributions
unity-0.003
 Yo-0.003
 Sergey-0.003
 VP-0.003
 Juno-0.003
Token doorway
Token ID32439
Feature activation-1.88e-01

Pos logit contributions
affle+0.265
rimination+0.247
 offender+0.242
icut+0.239
bourne+0.236
Neg logit contributions
unity-0.205
 Yo-0.198
 Sergey-0.195
 VP-0.187
 Juno-0.183
Token of
Token ID286
Feature activation-1.19e-02

Pos logit contributions
unity+0.369
 Yo+0.359
 Sergey+0.353
 VP+0.338
 Juno+0.333
Neg logit contributions
affle-0.453
rimination-0.422
 offender-0.414
icut-0.407
bourne-0.402
Token a
Token ID257
Feature activation+7.49e-02

Pos logit contributions
unity+0.023
 Yo+0.022
 Sergey+0.022
 VP+0.021
 travelled+0.021
Neg logit contributions
affle-0.029
rimination-0.027
 offender-0.027
icut-0.026
bourne-0.026
Token Bronx
Token ID32486
Feature activation+2.61e-01

Pos logit contributions
affle+0.175
rimination+0.162
 offender+0.160
icut+0.157
bourne+0.155
Neg logit contributions
unity-0.153
 Yo-0.149
 Sergey-0.146
 VP-0.141
 Juno-0.138
Token apartment
Token ID7962
Feature activation+2.04e-01

Pos logit contributions
affle+0.573
rimination+0.529
 offender+0.520
icut+0.509
bourne+0.502
Neg logit contributions
unity-0.569
 Yo-0.551
 Sergey-0.546
 VP-0.524
 travelled-0.517
Token building
Token ID2615
Feature activation+6.76e-01

Pos logit contributions
affle+0.431
rimination+0.396
 offender+0.390
icut+0.380
bourne+0.375
Neg logit contributions
unity-0.462
 Yo-0.447
 Sergey-0.443
 VP-0.426
ulum-0.423
Token.
Token ID13
Feature activation-1.17e-01

Pos logit contributions
affle+1.663
rimination+1.546
 offender+1.530
icut+1.498
aba+1.479
Neg logit contributions
unity-1.298
 Yo-1.240
 Sergey-1.228
 VP-1.173
ulum-1.166
Token The
Token ID383
Feature activation-1.19e-01

Pos logit contributions
unity+0.239
 Yo+0.230
 Sergey+0.228
 VP+0.218
 travelled+0.216
Neg logit contributions
affle-0.275
rimination-0.255
 offender-0.251
icut-0.247
bourne-0.244
Token killing
Token ID5170
Feature activation-1.88e-01

Pos logit contributions
unity+0.245
 Yo+0.237
 Sergey+0.234
 VP+0.225
 Juno+0.221
Neg logit contributions
affle-0.277
rimination-0.257
 offender-0.252
icut-0.248
bourne-0.245
Token prompted
Token ID12053
Feature activation-3.18e-03

Pos logit contributions
unity+0.366
 Yo+0.354
 Sergey+0.350
 VP+0.334
 travelled+0.329
Neg logit contributions
affle-0.457
rimination-0.425
 offender-0.418
icut-0.411
bourne-0.406
Token large
Token ID1588
Feature activation-2.83e-01

Pos logit contributions
unity+0.006
 Yo+0.006
 Sergey+0.006
 VP+0.005
ulum+0.005
Neg logit contributions
affle-0.008
rimination-0.007
 offender-0.007
icut-0.007
aba-0.007
Token functionality
Token ID11244
Feature activation+1.87e-01

Pos logit contributions
unity+0.066
 Yo+0.063
 Sergey+0.062
 VP+0.059
 travelled+0.058
Neg logit contributions
affle-0.102
rimination-0.096
 offender-0.095
icut-0.093
bourne-0.092
Token,
Token ID11
Feature activation+3.04e-02

Pos logit contributions
affle+0.442
rimination+0.410
 offender+0.405
icut+0.394
aba+0.391
Neg logit contributions
unity-0.377
 Yo-0.363
 Sergey-0.360
 VP-0.344
 Juno-0.341
Token and
Token ID290
Feature activation+8.04e-02

Pos logit contributions
affle+0.071
rimination+0.066
 offender+0.065
icut+0.063
bourne+0.063
Neg logit contributions
unity-0.062
 Yo-0.060
 Sergey-0.060
 VP-0.057
 Juno-0.056
Token some
Token ID617
Feature activation+1.67e-01

Pos logit contributions
affle+0.196
rimination+0.182
 offender+0.179
icut+0.176
bourne+0.174
Neg logit contributions
unity-0.156
 Yo-0.152
 Sergey-0.149
 VP-0.143
 Juno-0.141
Token products
Token ID3186
Feature activation+1.41e-01

Pos logit contributions
affle+0.386
rimination+0.357
 offender+0.352
icut+0.345
bourne+0.340
Neg logit contributions
unity-0.345
 Yo-0.334
 Sergey-0.330
 VP-0.317
 Juno-0.312
Token embrace
Token ID12553
Feature activation+7.25e-01

Pos logit contributions
affle+0.325
rimination+0.301
 offender+0.295
icut+0.291
bourne+0.286
Neg logit contributions
unity-0.293
 Yo-0.285
 Sergey-0.281
 VP-0.270
 travelled-0.266
Token characteristics
Token ID9695
Feature activation+3.79e-01

Pos logit contributions
affle+1.784
 offender+1.647
rimination+1.646
icut+1.597
 pitfalls+1.581
Neg logit contributions
unity-1.393
 Yo-1.325
 Sergey-1.319
 VP-1.249
ulum-1.243
Token of
Token ID286
Feature activation+2.95e-02

Pos logit contributions
affle+0.900
rimination+0.831
 offender+0.823
icut+0.802
bourne+0.795
Neg logit contributions
unity-0.761
 Yo-0.732
 Sergey-0.725
 VP-0.692
ulum-0.685
Token both
Token ID1111
Feature activation-1.78e-01

Pos logit contributions
affle+0.075
rimination+0.070
 offender+0.069
icut+0.068
bourne+0.067
Neg logit contributions
unity-0.054
 Yo-0.052
 Sergey-0.052
 VP-0.049
 Juno-0.049
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
unity+0.346
 Yo+0.336
 Sergey+0.331
 VP+0.317
 UP+0.312
Neg logit contributions
affle-0.433
rimination-0.404
 offender-0.395
icut-0.390
bourne-0.384
Token
Token ID198
Feature activation+1.95e-01

Pos logit contributions
affle+0.262
rimination+0.243
 offender+0.240
icut+0.236
aba+0.233
Neg logit contributions
unity-0.197
 Yo-0.188
 Sergey-0.186
 VP-0.177
 travelled-0.176
Token to
Token ID284
Feature activation-7.25e-02

Pos logit contributions
unity+0.763
 Yo+0.735
 Sergey+0.725
 VP+0.691
 Juno+0.680
Neg logit contributions
affle-1.070
rimination-0.999
 offender-0.985
icut-0.968
bourne-0.956
Token face
Token ID1986
Feature activation+2.36e-01

Pos logit contributions
unity+0.131
 Yo+0.126
 Sergey+0.124
 VP+0.118
 Juno+0.116
Neg logit contributions
affle-0.187
rimination-0.174
 offender-0.173
icut-0.169
bourne-0.167
Token,
Token ID11
Feature activation+8.18e-02

Pos logit contributions
affle+0.578
rimination+0.538
 offender+0.534
icut+0.518
bourne+0.513
Neg logit contributions
unity-0.453
 Yo-0.435
 Sergey-0.430
 VP-0.412
ulum-0.406
Token seeing
Token ID4379
Feature activation-2.77e-01

Pos logit contributions
affle+0.196
rimination+0.182
 offender+0.180
icut+0.176
bourne+0.174
Neg logit contributions
unity-0.162
 Yo-0.156
 Sergey-0.154
 VP-0.147
ulum-0.145
Token the
Token ID262
Feature activation+1.22e-01

Pos logit contributions
unity+0.522
 Yo+0.508
 Sergey+0.500
 VP+0.476
 travelled+0.470
Neg logit contributions
affle-0.691
rimination-0.644
 offender-0.631
icut-0.621
bourne-0.615
Token real
Token ID1103
Feature activation+7.12e-01

Pos logit contributions
affle+0.287
rimination+0.266
 offender+0.262
icut+0.257
bourne+0.253
Neg logit contributions
unity-0.248
 Yo-0.240
 Sergey-0.237
 VP-0.227
 Juno-0.223
Token world
Token ID995
Feature activation+1.37e-01

Pos logit contributions
affle+1.756
rimination+1.637
 offender+1.633
icut+1.586
bourne+1.565
Neg logit contributions
unity-1.352
 Yo-1.289
 Sergey-1.280
 VP-1.230
ulum-1.211
Token projected
Token ID13301
Feature activation+9.07e-02

Pos logit contributions
affle+0.332
rimination+0.309
 offender+0.304
icut+0.298
bourne+0.294
Neg logit contributions
unity-0.268
 Yo-0.260
 Sergey-0.256
 VP-0.245
 travelled-0.241
Token onto
Token ID4291
Feature activation+2.32e-01

Pos logit contributions
affle+0.219
rimination+0.204
 offender+0.201
icut+0.197
bourne+0.194
Neg logit contributions
unity-0.178
 Yo-0.172
 Sergey-0.170
 VP-0.163
 Juno-0.160
Token their
Token ID511
Feature activation-5.62e-02

Pos logit contributions
affle+0.647
rimination+0.607
 offender+0.603
icut+0.591
bourne+0.584
Neg logit contributions
unity-0.366
 Yo-0.348
 Sergey-0.343
 VP-0.326
ulum-0.319
Token screen
Token ID3159
Feature activation+1.05e-01

Pos logit contributions
unity+0.113
 Yo+0.109
 Sergey+0.108
 VP+0.104
 Juno+0.102
Neg logit contributions
affle-0.133
rimination-0.123
 offender-0.122
icut-0.119
bourne-0.118
Tokenality
Token ID1483
Feature activation-9.76e-02

Pos logit contributions
affle+0.267
rimination+0.247
 offender+0.241
icut+0.238
aba+0.235
Neg logit contributions
unity-0.254
 Yo-0.249
 Sergey-0.247
 VP-0.238
 Juno-0.234
Token,
Token ID11
Feature activation+1.08e-01

Pos logit contributions
unity+0.194
 Yo+0.187
 Sergey+0.185
 VP+0.177
 Juno+0.174
Neg logit contributions
affle-0.234
rimination-0.217
 offender-0.214
icut-0.210
bourne-0.207
Token which
Token ID543
Feature activation+2.57e-01

Pos logit contributions
affle+0.263
rimination+0.244
 offender+0.242
icut+0.237
bourne+0.233
Neg logit contributions
unity-0.210
 Yo-0.203
 Sergey-0.201
 VP-0.192
ulum-0.190
Token rule
Token ID3896
Feature activation+4.77e-01

Pos logit contributions
affle+0.596
rimination+0.553
 offender+0.547
icut+0.534
bourne+0.527
Neg logit contributions
unity-0.528
 Yo-0.507
 Sergey-0.501
 VP-0.481
ulum-0.476
Token the
Token ID262
Feature activation+1.43e-01

Pos logit contributions
affle+1.166
 offender+1.075
rimination+1.075
icut+1.047
aba+1.033
Neg logit contributions
unity-0.915
 Yo-0.879
 Sergey-0.877
 VP-0.833
ulum-0.825
Token realm
Token ID13360
Feature activation+8.10e-01

Pos logit contributions
affle+0.360
rimination+0.334
 offender+0.331
icut+0.324
bourne+0.320
Neg logit contributions
unity-0.266
 Yo-0.256
 Sergey-0.253
 VP-0.241
ulum-0.237
Token of
Token ID286
Feature activation-1.32e-01

Pos logit contributions
affle+1.740
 offender+1.589
rimination+1.586
icut+1.525
bourne+1.520
Neg logit contributions
unity-1.784
 Yo-1.706
 Sergey-1.695
 VP-1.643
ulum-1.621
Token the
Token ID262
Feature activation+1.22e-01

Pos logit contributions
unity+0.249
 Yo+0.240
 Sergey+0.237
 VP+0.226
 travelled+0.223
Neg logit contributions
affle-0.331
rimination-0.308
 offender-0.304
icut-0.298
bourne-0.294
Token everyday
Token ID10908
Feature activation+3.37e-01

Pos logit contributions
affle+0.287
rimination+0.266
 offender+0.262
icut+0.257
bourne+0.254
Neg logit contributions
unity-0.248
 Yo-0.240
 Sergey-0.237
 VP-0.227
 Juno-0.224
Token.
Token ID13
Feature activation+4.32e-02

Pos logit contributions
affle+0.830
 offender+0.769
rimination+0.766
icut+0.748
bourne+0.737
Neg logit contributions
unity-0.650
 Yo-0.622
 Sergey-0.614
 VP-0.586
ulum-0.580
Token By
Token ID2750
Feature activation+2.21e-01

Pos logit contributions
affle+0.104
rimination+0.096
 offender+0.095
icut+0.093
bourne+0.092
Neg logit contributions
unity-0.086
 Yo-0.082
 Sergey-0.081
 VP-0.077
ulum-0.077
Token.
Token ID13
Feature activation-9.45e-02

Pos logit contributions
unity+0.138
 Yo+0.132
 Sergey+0.131
 VP+0.125
 Juno+0.123
Neg logit contributions
affle-0.178
rimination-0.166
 offender-0.164
icut-0.160
bourne-0.159
Token As
Token ID1081
Feature activation+1.11e-01

Pos logit contributions
unity+0.191
 Yo+0.184
 Sergey+0.182
 VP+0.174
 travelled+0.172
Neg logit contributions
affle-0.223
rimination-0.207
 offender-0.204
icut-0.200
bourne-0.198
Token soon
Token ID2582
Feature activation+1.35e-01

Pos logit contributions
affle+0.268
rimination+0.248
 offender+0.246
icut+0.241
bourne+0.238
Neg logit contributions
unity-0.221
 Yo-0.211
 Sergey-0.208
 VP-0.199
ulum-0.198
Token as
Token ID355
Feature activation+1.42e-01

Pos logit contributions
affle+0.312
rimination+0.288
 offender+0.287
icut+0.278
aba+0.274
Neg logit contributions
unity-0.282
 Yo-0.270
 Sergey-0.264
 VP-0.254
 Juno-0.253
Token I
Token ID314
Feature activation-4.30e-02

Pos logit contributions
affle+0.338
rimination+0.314
 offender+0.311
icut+0.303
bourne+0.299
Neg logit contributions
unity-0.282
 Yo-0.272
 Sergey-0.266
 VP-0.254
ulum-0.254
Token add
Token ID751
Feature activation+7.75e-01

Pos logit contributions
unity+0.085
 Yo+0.082
 Sergey+0.080
 VP+0.077
 Juno+0.076
Neg logit contributions
affle-0.104
rimination-0.096
 offender-0.095
icut-0.093
bourne-0.092
Token the
Token ID262
Feature activation-2.79e-01

Pos logit contributions
affle+1.926
rimination+1.793
 offender+1.776
icut+1.744
bourne+1.719
Neg logit contributions
unity-1.443
 Yo-1.383
 Sergey-1.373
ulum-1.290
 Juno-1.288
Token comparison
Token ID7208
Feature activation-1.63e-01

Pos logit contributions
unity+0.545
 Yo+0.529
 Sergey+0.522
 VP+0.502
 UP+0.494
Neg logit contributions
affle-0.674
rimination-0.626
 offender-0.615
icut-0.606
bourne-0.597
Token code
Token ID2438
Feature activation-3.38e-01

Pos logit contributions
unity+0.270
 Yo+0.259
 Sergey+0.256
 VP+0.242
 Juno+0.237
Neg logit contributions
affle-0.444
rimination-0.416
 offender-0.411
icut-0.405
bourne-0.400
Token like
Token ID588
Feature activation-1.90e-01

Pos logit contributions
unity+0.613
 Yo+0.591
 Sergey+0.582
 VP+0.555
 UP+0.547
Neg logit contributions
affle-0.867
rimination-0.810
 offender-0.795
icut-0.783
bourne-0.775
Token in
Token ID287
Feature activation-1.83e-01

Pos logit contributions
unity+0.368
 Yo+0.356
 Sergey+0.351
 VP+0.336
 Juno+0.330
Neg logit contributions
affle-0.464
rimination-0.431
 offender-0.424
icut-0.417
bourne-0.412
Token allowing
Token ID5086
Feature activation-3.80e-01

Pos logit contributions
affle+0.400
rimination+0.373
 offender+0.367
icut+0.361
bourne+0.357
Neg logit contributions
unity-0.286
 Yo-0.277
 Sergey-0.273
 VP-0.260
 Juno-0.255
Token state
Token ID1181
Feature activation+3.63e-01

Pos logit contributions
unity+0.753
 Yo+0.743
 Sergey+0.733
 VP+0.705
 UP+0.695
Neg logit contributions
affle-0.899
rimination-0.839
 offender-0.808
bourne-0.803
icut-0.801
Token-
Token ID12
Feature activation+2.51e-02

Pos logit contributions
affle+0.820
rimination+0.758
 offender+0.743
icut+0.731
bourne+0.722
Neg logit contributions
unity-0.770
 Yo-0.747
 Sergey-0.737
 VP-0.708
 UP-0.697
Tokenfunded
Token ID18246
Feature activation-4.42e-01

Pos logit contributions
affle+0.052
rimination+0.048
 offender+0.047
icut+0.046
bourne+0.045
Neg logit contributions
unity-0.059
 Yo-0.057
 Sergey-0.056
 VP-0.054
 travelled-0.053
Token private
Token ID2839
Feature activation-2.86e-01

Pos logit contributions
unity+0.917
 Yo+0.908
 Sergey+0.896
 VP+0.864
 UP+0.851
Neg logit contributions
affle-1.006
rimination-0.937
bourne-0.899
icut-0.897
 offender-0.895
Token adoption
Token ID12695
Feature activation+1.43e-01

Pos logit contributions
unity+0.679
 Yo+0.667
 Sergey+0.659
 VP+0.638
 UP+0.629
Neg logit contributions
affle-0.572
rimination-0.524
 offender-0.502
icut-0.499
bourne-0.498
Token agencies
Token ID5942
Feature activation-1.17e-01

Pos logit contributions
affle+0.357
rimination+0.333
 offender+0.326
icut+0.323
bourne+0.319
Neg logit contributions
unity-0.270
 Yo-0.261
 Sergey-0.258
 VP-0.246
 travelled-0.242
Token to
Token ID284
Feature activation-1.55e-02

Pos logit contributions
unity+0.196
 Yo+0.188
 Sergey+0.185
 VP+0.176
 Juno+0.173
Neg logit contributions
affle-0.315
rimination-0.295
 offender-0.291
icut-0.287
bourne-0.283
Token turn
Token ID1210
Feature activation+2.10e-01

Pos logit contributions
unity+0.033
 Yo+0.032
 Sergey+0.032
 VP+0.031
 UP+0.031
Neg logit contributions
affle-0.034
rimination-0.032
 offender-0.031
icut-0.031
bourne-0.030
Token away
Token ID1497
Feature activation-1.90e-01

Pos logit contributions
affle+0.556
rimination+0.519
 offender+0.515
icut+0.505
bourne+0.497
Neg logit contributions
unity-0.365
 Yo-0.349
 Sergey-0.345
 VP-0.328
 Juno-0.322
Token prospective
Token ID17530
Feature activation-1.07e-01

Pos logit contributions
unity+0.353
 Yo+0.345
 Sergey+0.340
 VP+0.325
 travelled+0.319
Neg logit contributions
affle-0.476
rimination-0.445
 offender-0.435
icut-0.430
bourne-0.425
Token destroyed
Token ID6572
Feature activation+1.85e-02

Pos logit contributions
affle+0.011
rimination+0.010
 offender+0.010
icut+0.010
bourne+0.010
Neg logit contributions
unity-0.007
 Yo-0.007
 Sergey-0.007
 VP-0.007
 Juno-0.007
Token digital
Token ID4875
Feature activation+8.66e-02

Pos logit contributions
affle+0.047
rimination+0.044
 offender+0.043
icut+0.042
aba+0.042
Neg logit contributions
unity-0.034
 Yo-0.033
 Sergey-0.033
 VP-0.031
 travelled-0.031
Token evidence
Token ID2370
Feature activation+7.83e-02

Pos logit contributions
affle+0.209
rimination+0.194
 offender+0.192
icut+0.188
bourne+0.186
Neg logit contributions
unity-0.170
 Yo-0.164
 Sergey-0.162
 VP-0.155
 travelled-0.153
Token that
Token ID326
Feature activation+6.81e-03

Pos logit contributions
affle+0.195
rimination+0.182
 offender+0.179
icut+0.176
bourne+0.174
Neg logit contributions
unity-0.148
 Yo-0.143
 Sergey-0.141
 VP-0.135
 travelled-0.133
Token would
Token ID561
Feature activation+1.88e-01

Pos logit contributions
affle+0.016
rimination+0.015
 offender+0.015
icut+0.015
bourne+0.015
Neg logit contributions
unity-0.013
 Yo-0.013
 Sergey-0.013
 VP-0.012
 Juno-0.012
Token have
Token ID423
Feature activation+6.56e-02

Pos logit contributions
affle+0.464
rimination+0.433
 offender+0.426
icut+0.418
bourne+0.413
Neg logit contributions
unity-0.361
 Yo-0.348
 Sergey-0.344
 VP-0.328
 Juno-0.323
Token been
Token ID587
Feature activation+2.50e-02

Pos logit contributions
affle+0.153
rimination+0.142
 offender+0.139
icut+0.137
bourne+0.135
Neg logit contributions
unity-0.135
 Yo-0.131
 Sergey-0.129
 VP-0.124
 travelled-0.122
Token crucial
Token ID8780
Feature activation-1.40e-01

Pos logit contributions
affle+0.063
rimination+0.058
 offender+0.057
icut+0.057
bourne+0.056
Neg logit contributions
unity-0.047
 Yo-0.045
 Sergey-0.045
 VP-0.043
 travelled-0.042
Token to
Token ID284
Feature activation+5.79e-02

Pos logit contributions
unity+0.247
 Yo+0.237
 Sergey+0.235
 VP+0.222
 travelled+0.219
Neg logit contributions
affle-0.366
rimination-0.342
 offender-0.339
icut-0.333
aba-0.329
Token prove
Token ID5879
Feature activation+3.70e-01

Pos logit contributions
affle+0.146
rimination+0.135
 offender+0.134
icut+0.131
aba+0.130
Neg logit contributions
unity-0.108
 Yo-0.103
 Sergey-0.102
ulum-0.097
 travelled-0.097
Token V
Token ID569
Feature activation-2.43e-01

Pos logit contributions
affle+0.921
rimination+0.855
 offender+0.849
icut+0.829
aba+0.817
Neg logit contributions
unity-0.701
 Yo-0.671
 Sergey-0.664
 VP-0.630
 travelled-0.628
Token-
Token ID12
Feature activation-8.23e-02

Pos logit contributions
unity+0.245
 Yo+0.237
 Sergey+0.234
 VP+0.223
 travelled+0.220
Neg logit contributions
affle-0.297
rimination-0.276
 offender-0.272
icut-0.267
bourne-0.264
Tokenyear
Token ID1941
Feature activation-1.58e-01

Pos logit contributions
unity+0.157
 Yo+0.154
 Sergey+0.152
 VP+0.146
ulum+0.144
Neg logit contributions
affle-0.200
rimination-0.186
 offender-0.184
bourne-0.179
icut-0.179
Token contract
Token ID2775
Feature activation+3.80e-02

Pos logit contributions
unity+0.302
 Yo+0.292
 Sergey+0.288
 VP+0.275
 Juno+0.271
Neg logit contributions
affle-0.392
rimination-0.365
 offender-0.360
icut-0.353
bourne-0.349
Token with
Token ID351
Feature activation-2.25e-01

Pos logit contributions
affle+0.093
rimination+0.086
 offender+0.085
icut+0.083
bourne+0.082
Neg logit contributions
unity-0.074
 Yo-0.071
 Sergey-0.070
 VP-0.067
 travelled-0.066
Token publisher
Token ID9991
Feature activation-1.08e-01

Pos logit contributions
unity+0.401
 Yo+0.385
 Sergey+0.380
 VP+0.361
 travelled+0.357
Neg logit contributions
affle-0.583
rimination-0.544
 offender-0.537
icut-0.527
bourne-0.521
Token Activision
Token ID40723
Feature activation+1.92e-01

Pos logit contributions
unity+0.205
 Yo+0.196
 Sergey+0.194
 travelled+0.185
 VP+0.185
Neg logit contributions
affle-0.267
rimination-0.248
 offender-0.245
icut-0.240
bourne-0.239
Token.
Token ID13
Feature activation-7.52e-02

Pos logit contributions
affle+0.477
rimination+0.446
 offender+0.439
icut+0.432
bourne+0.427
Neg logit contributions
unity-0.364
 Yo-0.348
 Sergey-0.343
ulum-0.327
 travelled-0.326
Token
Token ID198
Feature activation-7.41e-02

Pos logit contributions
unity+0.144
 Yo+0.139
 Sergey+0.137
 VP+0.130
 travelled+0.130
Neg logit contributions
affle-0.185
rimination-0.172
 offender-0.169
icut-0.166
bourne-0.165
Token
Token ID198
Feature activation-4.50e-02

Pos logit contributions
unity+0.121
 Yo+0.118
 Sergey+0.115
 VP+0.109
 UP+0.107
Neg logit contributions
affle-0.205
rimination-0.195
 offender-0.191
icut-0.188
 pitfalls-0.184
TokenB
Token ID33
Feature activation-3.04e-02

Pos logit contributions
unity+0.097
 Yo+0.094
 Sergey+0.093
 VP+0.089
 travelled+0.088
Neg logit contributions
affle-0.100
rimination-0.093
 offender-0.091
icut-0.089
bourne-0.088
Tokenung
Token ID2150
Feature activation+3.50e-01

Pos logit contributions
unity+0.075
 Yo+0.073
 Sergey+0.072
 VP+0.070
 Juno+0.069
Neg logit contributions
affle-0.058
rimination-0.053
 offender-0.052
icut-0.051
bourne-0.050
Token,
Token ID11
Feature activation+2.65e-02

Pos logit contributions
affle+0.072
rimination+0.067
 offender+0.066
icut+0.064
bourne+0.064
Neg logit contributions
unity-0.064
 Yo-0.062
 Sergey-0.061
 VP-0.059
ulum-0.058
Token were
Token ID547
Feature activation-2.43e-02

Pos logit contributions
affle+0.064
rimination+0.059
 offender+0.059
icut+0.057
bourne+0.057
Neg logit contributions
unity-0.052
 Yo-0.050
 Sergey-0.050
 VP-0.048
ulum-0.047
Token world
Token ID995
Feature activation+2.14e-01

Pos logit contributions
unity+0.048
 Yo+0.046
 Sergey+0.046
 VP+0.044
 Juno+0.043
Neg logit contributions
affle-0.058
rimination-0.054
 offender-0.053
icut-0.052
bourne-0.052
Token-
Token ID12
Feature activation-1.29e-01

Pos logit contributions
affle+0.431
rimination+0.394
 offender+0.388
icut+0.379
bourne+0.374
Neg logit contributions
unity-0.507
 Yo-0.493
 Sergey-0.488
 VP-0.470
 Juno-0.465
Tokenren
Token ID918
Feature activation-1.05e-02

Pos logit contributions
unity+0.279
 Yo+0.272
 Sergey+0.269
 VP+0.258
 Juno+0.255
Neg logit contributions
affle-0.286
rimination-0.264
 offender-0.259
icut-0.255
bourne-0.252
Tokenouncing
Token ID18155
Feature activation+1.92e-01

Pos logit contributions
unity+0.017
 Yo+0.016
 Sergey+0.016
 VP+0.015
 travelled+0.015
Neg logit contributions
affle-0.029
rimination-0.027
 offender-0.027
icut-0.026
aba-0.026
Token.
Token ID13
Feature activation+5.57e-02

Pos logit contributions
affle+0.462
 offender+0.428
rimination+0.427
icut+0.415
 pitfalls+0.411
Neg logit contributions
unity-0.377
 Yo-0.362
 Sergey-0.360
 VP-0.343
ulum-0.340
Token Values
Token ID27068
Feature activation-9.88e-03

Pos logit contributions
affle+0.137
rimination+0.127
 offender+0.125
icut+0.123
bourne+0.122
Neg logit contributions
unity-0.107
 Yo-0.102
 Sergey-0.101
 VP-0.097
 travelled-0.096
Token created
Token ID2727
Feature activation-3.00e-02

Pos logit contributions
unity+0.019
 Yo+0.018
 Sergey+0.018
 VP+0.017
ulum+0.017
Neg logit contributions
affle-0.025
rimination-0.023
 offender-0.023
icut-0.022
bourne-0.022
Token out
Token ID503
Feature activation+1.17e-01

Pos logit contributions
unity+0.050
 Yo+0.048
 Sergey+0.047
 VP+0.045
ulum+0.044
Neg logit contributions
affle-0.081
rimination-0.076
 offender-0.075
icut-0.074
bourne-0.073
Token of
Token ID286
Feature activation+6.46e-03

Pos logit contributions
affle+0.262
rimination+0.241
 offender+0.238
icut+0.230
bourne+0.230
Neg logit contributions
unity-0.249
 Yo-0.243
 Sergey-0.242
 VP-0.233
ulum-0.229
Token1
Token ID16
Feature activation-5.05e-02

Pos logit contributions
unity+0.226
 Yo+0.219
 Sergey+0.217
 VP+0.209
 UP+0.206
Neg logit contributions
affle-0.203
rimination-0.187
 offender-0.184
icut-0.180
bourne-0.177
Token per
Token ID583
Feature activation-4.65e-01

Pos logit contributions
unity+0.099
 Yo+0.096
 Sergey+0.094
 VP+0.090
 Juno+0.089
Neg logit contributions
affle-0.122
rimination-0.114
 offender-0.112
icut-0.110
bourne-0.108
Token year
Token ID614
Feature activation+1.03e-01

Pos logit contributions
unity+0.884
 Yo+0.860
 Sergey+0.842
 VP+0.817
 UP+0.799
Neg logit contributions
affle-1.149
rimination-1.079
 offender-1.043
icut-1.037
bourne-1.030
Token,
Token ID11
Feature activation+8.98e-03

Pos logit contributions
affle+0.254
rimination+0.236
 offender+0.233
icut+0.228
bourne+0.225
Neg logit contributions
unity-0.199
 Yo-0.193
 Sergey-0.190
 VP-0.182
 Juno-0.179
Token with
Token ID351
Feature activation+4.83e-02

Pos logit contributions
affle+0.022
rimination+0.020
 offender+0.020
icut+0.020
bourne+0.019
Neg logit contributions
unity-0.017
 Yo-0.017
 Sergey-0.017
 VP-0.016
 Juno-0.016
Token only
Token ID691
Feature activation+1.13e-01

Pos logit contributions
affle+0.121
rimination+0.112
 offender+0.111
icut+0.109
bourne+0.107
Neg logit contributions
unity-0.091
 Yo-0.087
 Sergey-0.086
 VP-0.082
 travelled-0.081
Token half
Token ID2063
Feature activation-4.85e-01

Pos logit contributions
affle+0.283
rimination+0.264
 offender+0.260
icut+0.256
bourne+0.252
Neg logit contributions
unity-0.211
 Yo-0.203
 Sergey-0.200
 VP-0.191
 travelled-0.188
Token of
Token ID286
Feature activation+5.20e-02

Pos logit contributions
unity+0.953
 Yo+0.923
 Sergey+0.911
 VP+0.872
 travelled+0.858
Neg logit contributions
affle-1.167
rimination-1.087
 offender-1.068
icut-1.049
bourne-1.036
Token that
Token ID326
Feature activation+4.79e-02

Pos logit contributions
affle+0.136
rimination+0.127
 offender+0.126
icut+0.124
bourne+0.122
Neg logit contributions
unity-0.092
 Yo-0.088
 Sergey-0.087
 VP-0.082
 travelled-0.081
Token sum
Token ID2160
Feature activation+1.25e-01

Pos logit contributions
affle+0.118
rimination+0.110
 offender+0.108
icut+0.106
bourne+0.105
Neg logit contributions
unity-0.092
 Yo-0.089
 Sergey-0.087
 VP-0.084
 Juno-0.082
Token going
Token ID1016
Feature activation-6.02e-02

Pos logit contributions
affle+0.315
rimination+0.294
 offender+0.289
icut+0.284
bourne+0.281
Neg logit contributions
unity-0.233
 Yo-0.225
 Sergey-0.222
 VP-0.212
 Juno-0.208
Token other
Token ID584
Feature activation-1.31e-01

Pos logit contributions
unity+0.155
 Yo+0.148
 Sergey+0.146
 VP+0.138
 Juno+0.135
Neg logit contributions
affle-0.271
rimination-0.255
 offender-0.252
icut-0.248
bourne-0.245
Token hand
Token ID1021
Feature activation-2.03e-01

Pos logit contributions
unity+0.248
 Yo+0.244
 Sergey+0.242
 VP+0.232
 UP+0.227
Neg logit contributions
affle-0.324
rimination-0.305
icut-0.293
 offender-0.292
aba-0.287
Token,
Token ID11
Feature activation-1.15e-01

Pos logit contributions
unity+0.432
 Yo+0.417
 Sergey+0.411
 VP+0.395
 Juno+0.390
Neg logit contributions
affle-0.456
rimination-0.421
 offender-0.417
icut-0.405
aba-0.402
Token exits
Token ID30151
Feature activation-6.92e-02

Pos logit contributions
unity+0.239
 Yo+0.231
 Sergey+0.228
 VP+0.219
 Juno+0.216
Neg logit contributions
affle-0.265
rimination-0.245
 offender-0.241
icut-0.236
bourne-0.233
Token epoch
Token ID36835
Feature activation-2.02e-01

Pos logit contributions
unity+0.130
 Yo+0.126
 Sergey+0.125
 VP+0.119
 Juno+0.118
Neg logit contributions
affle-0.173
rimination-0.161
 offender-0.158
icut-0.156
bourne-0.154
Token management
Token ID4542
Feature activation-4.28e-02

Pos logit contributions
unity+0.421
 Yo+0.410
 Sergey+0.406
 VP+0.390
 Juno+0.385
Neg logit contributions
affle-0.464
rimination-0.429
 offender-0.419
icut-0.412
bourne-0.407
Token by
Token ID416
Feature activation-1.49e-01

Pos logit contributions
unity+0.081
 Yo+0.078
 Sergey+0.077
 VP+0.074
 Juno+0.072
Neg logit contributions
affle-0.107
rimination-0.100
 offender-0.098
icut-0.096
bourne-0.095
Token marking
Token ID18730
Feature activation+7.23e-03

Pos logit contributions
unity+0.303
 Yo+0.293
 Sergey+0.289
 VP+0.277
 Juno+0.273
Neg logit contributions
affle-0.351
rimination-0.325
 offender-0.320
icut-0.314
bourne-0.310
Token the
Token ID262
Feature activation-9.65e-02

Pos logit contributions
affle+0.018
rimination+0.017
 offender+0.017
icut+0.016
bourne+0.016
Neg logit contributions
unity-0.014
 Yo-0.013
 Sergey-0.013
 VP-0.012
ulum-0.012
Token thread
Token ID4704
Feature activation+2.88e-01

Pos logit contributions
unity+0.192
 Yo+0.185
 Sergey+0.183
 VP+0.175
 Juno+0.173
Neg logit contributions
affle-0.231
rimination-0.215
 offender-0.211
icut-0.207
bourne-0.205
Token inactive
Token ID28621
Feature activation+1.19e-01

Pos logit contributions
affle+0.679
 offender+0.631
rimination+0.625
icut+0.611
bourne+0.605
Neg logit contributions
unity-0.582
 Yo-0.557
 Sergey-0.549
 VP-0.524
ulum-0.519
Token very
Token ID845
Feature activation+2.36e-01

Pos logit contributions
unity+0.026
 Yo+0.025
 Sergey+0.025
 VP+0.024
ulum+0.023
Neg logit contributions
affle-0.033
rimination-0.031
 offender-0.031
icut-0.030
bourne-0.030
Token first
Token ID717
Feature activation+1.00e-01

Pos logit contributions
affle+0.577
rimination+0.535
 offender+0.534
icut+0.518
bourne+0.515
Neg logit contributions
unity-0.457
 Yo-0.436
 Sergey-0.430
 VP-0.411
ulum-0.408
Token sentence
Token ID6827
Feature activation-5.78e-03

Pos logit contributions
affle+0.248
rimination+0.231
 offender+0.228
icut+0.224
bourne+0.221
Neg logit contributions
unity-0.192
 Yo-0.184
 Sergey-0.182
 VP-0.174
 Juno-0.171
Token of
Token ID286
Feature activation+2.26e-01

Pos logit contributions
unity+0.012
 Yo+0.012
 Sergey+0.012
 VP+0.011
 travelled+0.011
Neg logit contributions
affle-0.013
rimination-0.012
 offender-0.012
icut-0.012
bourne-0.012
Token the
Token ID262
Feature activation+1.81e-01

Pos logit contributions
affle+0.563
rimination+0.524
 offender+0.518
icut+0.506
bourne+0.503
Neg logit contributions
unity-0.427
 Yo-0.408
 Sergey-0.401
 VP-0.383
ulum-0.380
Token essay
Token ID14268
Feature activation-2.40e-01

Pos logit contributions
affle+0.459
rimination+0.429
 offender+0.426
icut+0.415
bourne+0.411
Neg logit contributions
unity-0.332
 Yo-0.317
 Sergey-0.313
 VP-0.297
ulum-0.294
Token he
Token ID339
Feature activation+1.53e-02

Pos logit contributions
unity+0.498
 Yo+0.484
 Sergey+0.479
 VP+0.459
 travelled+0.452
Neg logit contributions
affle-0.554
rimination-0.512
 offender-0.503
icut-0.495
bourne-0.487
Token writes
Token ID6797
Feature activation+1.66e-01

Pos logit contributions
affle+0.036
rimination+0.033
 offender+0.032
icut+0.032
bourne+0.031
Neg logit contributions
unity-0.031
 Yo-0.030
 Sergey-0.030
 VP-0.029
 travelled-0.028
Token that
Token ID326
Feature activation+1.19e-01

Pos logit contributions
affle+0.403
rimination+0.374
 offender+0.370
icut+0.362
bourne+0.358
Neg logit contributions
unity-0.322
 Yo-0.310
 Sergey-0.306
 VP-0.292
 Juno-0.289
Token the
Token ID262
Feature activation+5.27e-02

Pos logit contributions
affle+0.298
rimination+0.278
 offender+0.275
icut+0.269
bourne+0.266
Neg logit contributions
unity-0.220
 Yo-0.212
 Sergey-0.209
 VP-0.199
ulum-0.197
Token EU
Token ID4576
Feature activation-2.64e-01

Pos logit contributions
affle+0.150
rimination+0.141
 offender+0.139
icut+0.136
bourne+0.135
Neg logit contributions
unity-0.081
 Yo-0.078
 Sergey-0.076
 VP-0.072
ulum-0.071
Token while
Token ID981
Feature activation-3.14e-01

Pos logit contributions
affle+0.124
rimination+0.116
 offender+0.114
icut+0.112
bourne+0.111
Neg logit contributions
unity-0.099
 Yo-0.095
 Sergey-0.094
 VP-0.090
ulum-0.089
Token research
Token ID2267
Feature activation-3.35e-01

Pos logit contributions
unity+0.602
 Yo+0.583
 Sergey+0.575
 VP+0.550
 UP+0.541
Neg logit contributions
affle-0.776
rimination-0.721
 offender-0.709
icut-0.698
bourne-0.690
Token on
Token ID319
Feature activation+9.27e-02

Pos logit contributions
unity+0.651
 Yo+0.629
 Sergey+0.618
 VP+0.593
 UP+0.583
Neg logit contributions
affle-0.822
rimination-0.766
 offender-0.750
icut-0.740
bourne-0.731
Token Asians
Token ID30852
Feature activation-2.98e-01

Pos logit contributions
affle+0.225
rimination+0.210
 offender+0.207
icut+0.203
bourne+0.200
Neg logit contributions
unity-0.181
 Yo-0.174
 Sergey-0.172
 VP-0.164
 Juno-0.162
Token and
Token ID290
Feature activation+5.43e-02

Pos logit contributions
unity+0.593
 Yo+0.575
 Sergey+0.567
 VP+0.543
 travelled+0.536
Neg logit contributions
affle-0.711
rimination-0.660
 offender-0.647
icut-0.636
bourne-0.628
Token Latinos
Token ID33877
Feature activation-1.13e-02

Pos logit contributions
affle+0.131
rimination+0.122
 offender+0.120
icut+0.118
bourne+0.116
Neg logit contributions
unity-0.107
 Yo-0.103
 Sergey-0.102
 VP-0.097
 Juno-0.096
Token appears
Token ID3568
Feature activation+2.73e-01

Pos logit contributions
unity+0.023
 Yo+0.022
 Sergey+0.022
 VP+0.021
 travelled+0.020
Neg logit contributions
affle-0.027
rimination-0.025
 offender-0.024
icut-0.024
bourne-0.024
Token scant
Token ID35183
Feature activation+2.66e-02

Pos logit contributions
affle+0.690
rimination+0.643
 offender+0.636
icut+0.625
aba+0.616
Neg logit contributions
unity-0.503
 Yo-0.485
 Sergey-0.479
 VP-0.457
 Juno-0.451
Token.
Token ID13
Feature activation-6.76e-02

Pos logit contributions
affle+0.068
rimination+0.064
 offender+0.063
icut+0.062
bourne+0.061
Neg logit contributions
unity-0.048
 Yo-0.046
 Sergey-0.046
 VP-0.043
 Juno-0.043
Token We
Token ID775
Feature activation-7.05e-02

Pos logit contributions
unity+0.130
 Yo+0.125
 Sergey+0.123
 VP+0.118
 travelled+0.117
Neg logit contributions
affle-0.166
rimination-0.155
 offender-0.152
icut-0.150
bourne-0.148
Token were
Token ID547
Feature activation-1.71e-01

Pos logit contributions
unity+0.136
 Yo+0.131
 Sergey+0.129
 VP+0.123
 Juno+0.121
Neg logit contributions
affle-0.173
rimination-0.161
 offender-0.159
icut-0.156
bourne-0.154
Token 2
Token ID362
Feature activation-4.13e-02

Pos logit contributions
unity+0.123
 Yo+0.120
 Sergey+0.118
 VP+0.113
 Juno+0.111
Neg logit contributions
affle-0.147
rimination-0.136
 offender-0.134
icut-0.131
bourne-0.130
Token.
Token ID13
Feature activation-1.01e-01

Pos logit contributions
unity+0.084
 Yo+0.080
 Sergey+0.080
 VP+0.076
 Juno+0.075
Neg logit contributions
affle-0.098
rimination-0.091
 offender-0.089
icut-0.087
aba-0.086
Token5
Token ID20
Feature activation-1.93e-01

Pos logit contributions
unity+0.237
 Yo+0.231
 Sergey+0.228
 VP+0.220
 Juno+0.217
Neg logit contributions
affle-0.206
rimination-0.189
 offender-0.186
icut-0.182
bourne-0.179
Token per
Token ID583
Feature activation-4.68e-01

Pos logit contributions
unity+0.429
 Yo+0.412
 Sergey+0.410
 VP+0.393
ulum+0.388
Neg logit contributions
affle-0.417
rimination-0.383
 offender-0.378
icut-0.367
bourne-0.363
Token cent
Token ID1247
Feature activation-1.68e-01

Pos logit contributions
unity+0.746
 Yo+0.735
 Sergey+0.717
 VP+0.692
 EPS+0.679
Neg logit contributions
affle-1.299
rimination-1.219
 offender-1.175
icut-1.168
uyomi-1.158
Token increase
Token ID2620
Feature activation-5.84e-02

Pos logit contributions
unity+0.350
 Yo+0.341
 Sergey+0.336
 VP+0.323
 UP+0.318
Neg logit contributions
affle-0.385
rimination-0.357
 offender-0.350
icut-0.344
bourne-0.339
Token in
Token ID287
Feature activation-2.47e-01

Pos logit contributions
unity+0.105
 Yo+0.100
 Sergey+0.099
 VP+0.094
ulum+0.093
Neg logit contributions
affle-0.151
rimination-0.141
 offender-0.140
icut-0.137
bourne-0.135
Token the
Token ID262
Feature activation-9.98e-02

Pos logit contributions
unity+0.475
 Yo+0.458
 Sergey+0.452
 VP+0.432
 Juno+0.425
Neg logit contributions
affle-0.607
rimination-0.564
 offender-0.556
icut-0.546
bourne-0.539
Token first
Token ID717
Feature activation+1.56e-01

Pos logit contributions
unity+0.195
 Yo+0.188
 Sergey+0.186
 VP+0.178
 Juno+0.175
Neg logit contributions
affle-0.242
rimination-0.225
 offender-0.222
icut-0.218
bourne-0.215
Token year
Token ID614
Feature activation+1.56e-02

Pos logit contributions
affle+0.391
rimination+0.365
 offender+0.360
icut+0.353
bourne+0.349
Neg logit contributions
unity-0.292
 Yo-0.281
 Sergey-0.277
 VP-0.265
 Juno-0.260
Token and
Token ID290
Feature activation+5.99e-03

Pos logit contributions
affle+0.038
rimination+0.035
 offender+0.035
icut+0.034
bourne+0.034
Neg logit contributions
unity-0.030
 Yo-0.029
 Sergey-0.029
 VP-0.028
 Juno-0.027
Token.
Token ID13
Feature activation-8.74e-02

Pos logit contributions
affle+0.050
rimination+0.046
 offender+0.046
icut+0.045
aba+0.044
Neg logit contributions
unity-0.040
 Yo-0.039
 Sergey-0.038
 VP-0.037
ulum-0.036
Token But
Token ID887
Feature activation+5.93e-02

Pos logit contributions
unity+0.166
 Yo+0.159
 Sergey+0.157
 VP+0.150
 travelled+0.149
Neg logit contributions
affle-0.216
rimination-0.201
 offender-0.198
icut-0.195
bourne-0.193
Token how
Token ID703
Feature activation-7.47e-02

Pos logit contributions
affle+0.146
rimination+0.135
 offender+0.134
icut+0.131
bourne+0.129
Neg logit contributions
unity-0.114
 Yo-0.110
 Sergey-0.108
 VP-0.103
ulum-0.102
Token we
Token ID356
Feature activation-1.86e-01

Pos logit contributions
unity+0.153
 Yo+0.148
 Sergey+0.146
 VP+0.139
 Juno+0.138
Neg logit contributions
affle-0.175
rimination-0.162
 offender-0.160
icut-0.156
bourne-0.155
Token approach
Token ID3164
Feature activation+1.52e-01

Pos logit contributions
unity+0.372
 Yo+0.360
 Sergey+0.355
 VP+0.339
 Juno+0.335
Neg logit contributions
affle-0.444
rimination-0.412
 offender-0.406
icut-0.399
bourne-0.393
Token those
Token ID883
Feature activation-4.46e-02

Pos logit contributions
affle+0.381
rimination+0.355
 offender+0.350
icut+0.344
bourne+0.339
Neg logit contributions
unity-0.285
 Yo-0.275
 Sergey-0.271
 VP-0.258
 Juno-0.254
Token problems
Token ID2761
Feature activation+3.60e-01

Pos logit contributions
unity+0.089
 Yo+0.087
 Sergey+0.085
 VP+0.082
 UP+0.081
Neg logit contributions
affle-0.106
rimination-0.099
 offender-0.096
icut-0.095
bourne-0.094
Token and
Token ID290
Feature activation+4.03e-02

Pos logit contributions
affle+0.840
rimination+0.778
 offender+0.771
icut+0.753
aba+0.742
Neg logit contributions
unity-0.734
 Yo-0.711
 Sergey-0.701
 VP-0.671
 Juno-0.663
Token the
Token ID262
Feature activation+2.85e-02

Pos logit contributions
affle+0.098
rimination+0.091
 offender+0.090
icut+0.088
bourne+0.087
Neg logit contributions
unity-0.079
 Yo-0.076
 Sergey-0.075
 VP-0.071
ulum-0.070
Token resources
Token ID4133
Feature activation-4.08e-02

Pos logit contributions
affle+0.065
rimination+0.060
 offender+0.059
icut+0.058
bourne+0.057
Neg logit contributions
unity-0.060
 Yo-0.059
 Sergey-0.058
 VP-0.055
 Juno-0.055
Token that
Token ID326
Feature activation+8.00e-02

Pos logit contributions
unity+0.078
 Yo+0.076
 Sergey+0.075
 VP+0.071
 Juno+0.070
Neg logit contributions
affle-0.100
rimination-0.093
 offender-0.092
icut-0.090
bourne-0.089
Token (
Token ID357
Feature activation-1.85e-01

Pos logit contributions
unity+0.538
 Yo+0.521
 Sergey+0.514
 VP+0.493
 UP+0.484
Neg logit contributions
affle-0.658
rimination-0.612
 offender-0.600
icut-0.590
bourne-0.583
Tokenat
Token ID265
Feature activation-7.39e-02

Pos logit contributions
unity+0.410
 Yo+0.399
 Sergey+0.394
 VP+0.379
 travelled+0.374
Neg logit contributions
affle-0.402
rimination-0.370
 offender-0.364
icut-0.357
bourne-0.351
Token least
Token ID1551
Feature activation+2.08e-01

Pos logit contributions
unity+0.172
 Yo+0.167
 Sergey+0.165
 VP+0.159
 travelled+0.157
Neg logit contributions
affle-0.152
rimination-0.139
 offender-0.137
icut-0.134
bourne-0.132
Token among
Token ID1871
Feature activation-9.12e-02

Pos logit contributions
affle+0.527
rimination+0.490
 offender+0.487
icut+0.478
bourne+0.471
Neg logit contributions
unity-0.384
 Yo-0.366
 Sergey-0.361
 VP-0.344
ulum-0.340
Token the
Token ID262
Feature activation-2.35e-01

Pos logit contributions
unity+0.169
 Yo+0.163
 Sergey+0.161
 VP+0.153
 Juno+0.150
Neg logit contributions
affle-0.231
rimination-0.216
 offender-0.212
icut-0.209
bourne-0.206
Token public
Token ID1171
Feature activation-6.96e-01

Pos logit contributions
unity+0.477
 Yo+0.466
 Sergey+0.459
 VP+0.444
 UP+0.434
Neg logit contributions
affle-0.551
rimination-0.514
 offender-0.501
icut-0.496
bourne-0.489
Token at
Token ID379
Feature activation-3.06e-01

Pos logit contributions
unity+1.296
 Yo+1.251
 Sergey+1.238
 VP+1.184
 UP+1.162
Neg logit contributions
affle-1.746
rimination-1.631
 offender-1.602
icut-1.578
bourne-1.558
Token large
Token ID1588
Feature activation-5.16e-01

Pos logit contributions
unity+0.526
 Yo+0.502
 Sergey+0.495
 VP+0.468
 travelled+0.465
Neg logit contributions
affle-0.818
rimination-0.761
 offender-0.755
icut-0.739
bourne-0.731
Token),
Token ID828
Feature activation+3.01e-01

Pos logit contributions
unity+0.994
 Yo+0.960
 Sergey+0.947
 VP+0.905
 Juno+0.891
Neg logit contributions
affle-1.268
rimination-1.180
 offender-1.163
icut-1.141
bourne-1.127
Token they
Token ID484
Feature activation-6.54e-03

Pos logit contributions
affle+0.783
rimination+0.728
 offender+0.722
icut+0.706
aba+0.697
Neg logit contributions
unity-0.534
 Yo-0.510
 Sergey-0.501
ulum-0.475
 travelled-0.474
Token aren
Token ID3588
Feature activation+2.57e-01

Pos logit contributions
unity+0.013
 Yo+0.012
 Sergey+0.012
 VP+0.012
 Juno+0.011
Neg logit contributions
affle-0.016
rimination-0.015
 offender-0.015
icut-0.014
bourne-0.014
Token cars
Token ID5006
Feature activation+1.26e-01

Pos logit contributions
affle+0.229
rimination+0.213
 offender+0.209
icut+0.205
bourne+0.203
Neg logit contributions
unity-0.194
 Yo-0.188
 Sergey-0.185
 VP-0.177
 Juno-0.175
Token his
Token ID465
Feature activation+6.77e-02

Pos logit contributions
affle+0.282
rimination+0.260
 offender+0.256
icut+0.251
bourne+0.249
Neg logit contributions
unity-0.268
 Yo-0.259
 Sergey-0.256
 VP-0.246
 Juno-0.243
Token tyre
Token ID48216
Feature activation-5.48e-01

Pos logit contributions
affle+0.163
rimination+0.152
 offender+0.149
icut+0.147
bourne+0.144
Neg logit contributions
unity-0.133
 Yo-0.130
 Sergey-0.128
 VP-0.123
 travelled-0.121
Token was
Token ID373
Feature activation+1.89e-02

Pos logit contributions
unity+0.986
 Yo+0.960
 Sergey+0.944
 VP+0.900
 travelled+0.895
Neg logit contributions
affle-1.413
rimination-1.320
 offender-1.293
icut-1.278
bourne-1.257
Token half
Token ID2063
Feature activation-5.70e-01

Pos logit contributions
affle+0.045
rimination+0.042
 offender+0.041
icut+0.040
bourne+0.040
Neg logit contributions
unity-0.038
 Yo-0.037
 Sergey-0.036
 VP-0.035
 travelled-0.034
Token flat
Token ID6228
Feature activation-6.58e-01

Pos logit contributions
unity+1.135
 Yo+1.110
 Sergey+1.095
 travelled+1.049
 VP+1.049
Neg logit contributions
affle-1.357
rimination-1.265
 offender-1.226
icut-1.217
aba-1.199
Token.
Token ID13
Feature activation-1.00e-01

Pos logit contributions
unity+1.211
 Yo+1.174
 Sergey+1.151
 VP+1.099
 travelled+1.088
Neg logit contributions
affle-1.670
rimination-1.557
 offender-1.531
icut-1.508
bourne-1.483
Token
Token ID447
Feature activation-6.62e-02

Pos logit contributions
unity+0.196
 Yo+0.187
 Sergey+0.184
 VP+0.176
ulum+0.176
Neg logit contributions
affle-0.244
rimination-0.227
 offender-0.223
icut-0.218
bourne-0.217
Token
Token ID251
Feature activation-2.22e-01

Pos logit contributions
unity+0.103
 Yo+0.099
 Sergey+0.096
 VP+0.091
 @@+0.090
Neg logit contributions
affle-0.187
rimination-0.177
 offender-0.174
icut-0.172
bourne-0.169
Token
Token ID198
Feature activation-2.16e-01

Pos logit contributions
unity+0.421
 Yo+0.400
 Sergey+0.394
 VP+0.378
ulum+0.377
Neg logit contributions
affle-0.551
rimination-0.513
 offender-0.505
icut-0.495
bourne-0.494
Token
Token ID198
Feature activation-2.06e-01

Pos logit contributions
unity+0.351
 Yo+0.344
 Sergey+0.335
 VP+0.319
 UP+0.313
Neg logit contributions
affle-0.597
rimination-0.567
 offender-0.555
icut-0.549
 pitfalls-0.537
Token,
Token ID11
Feature activation-1.42e-01

Pos logit contributions
unity+0.580
 Yo+0.560
 Sergey+0.553
 VP+0.529
 Juno+0.520
Neg logit contributions
affle-0.732
rimination-0.681
 offender-0.670
icut-0.658
bourne-0.650
Token2
Token ID17
Feature activation-3.16e-01

Pos logit contributions
unity+0.331
 Yo+0.322
 Sergey+0.319
 VP+0.307
 Juno+0.304
Neg logit contributions
affle-0.291
rimination-0.266
 offender-0.262
icut-0.255
bourne-0.252
Token,
Token ID11
Feature activation-2.45e-02

Pos logit contributions
unity+0.617
 Yo+0.597
 Sergey+0.589
 VP+0.563
 Juno+0.554
Neg logit contributions
affle-0.769
rimination-0.715
 offender-0.703
icut-0.691
bourne-0.682
Token4
Token ID19
Feature activation-2.90e-01

Pos logit contributions
unity+0.058
 Yo+0.056
 Sergey+0.055
 VP+0.053
 Juno+0.053
Neg logit contributions
affle-0.050
rimination-0.045
 offender-0.045
icut-0.043
bourne-0.043
Token)
Token ID8
Feature activation-2.21e-01

Pos logit contributions
unity+0.565
 Yo+0.547
 Sergey+0.539
 VP+0.516
 Juno+0.508
Neg logit contributions
affle-0.704
rimination-0.655
 offender-0.644
icut-0.633
bourne-0.625
Token Mystery
Token ID18208
Feature activation-6.63e-01

Pos logit contributions
unity+0.420
 Yo+0.408
 Sergey+0.402
 VP+0.384
 travelled+0.378
Neg logit contributions
affle-0.546
rimination-0.508
 offender-0.499
icut-0.492
bourne-0.485
Token fellow
Token ID5891
Feature activation-6.62e-01

Pos logit contributions
unity+1.161
 Yo+1.121
 Sergey+1.098
 VP+1.054
 travelled+1.034
Neg logit contributions
affle-1.744
rimination-1.636
 offender-1.592
icut-1.577
bourne-1.560
Token
Token ID447
Feature activation+1.67e-01

Pos logit contributions
unity+1.242
 Yo+1.203
 Sergey+1.185
 VP+1.136
 travelled+1.128
Neg logit contributions
affle-1.649
rimination-1.545
 offender-1.503
icut-1.490
bourne-1.468
Token
Token ID247
Feature activation+8.90e-02

Pos logit contributions
affle+0.543
rimination+0.515
 offender+0.509
icut+0.502
bourne+0.497
Neg logit contributions
unity-0.189
 Yo-0.178
 Sergey-0.174
 VP-0.160
 travelled-0.156
Token
Token ID784
Feature activation-8.63e-02

Pos logit contributions
affle+0.216
rimination+0.201
 offender+0.198
icut+0.194
bourne+0.192
Neg logit contributions
unity-0.174
 Yo-0.168
 Sergey-0.166
 VP-0.158
 Juno-0.156
Token MR
Token ID17242
Feature activation-1.39e-01

Pos logit contributions
unity+0.167
 Yo+0.161
 Sergey+0.159
 VP+0.152
 Juno+0.149
Neg logit contributions
affle-0.211
rimination-0.197
 offender-0.194
icut-0.190
bourne-0.188
Token,
Token ID11
Feature activation+7.99e-02

Pos logit contributions
affle+1.423
rimination+1.310
 offender+1.300
icut+1.264
aba+1.251
Neg logit contributions
unity-1.345
 Yo-1.292
 Sergey-1.283
 VP-1.228
ulum-1.218
Token computer
Token ID3644
Feature activation-8.36e-02

Pos logit contributions
affle+0.185
rimination+0.171
 offender+0.169
icut+0.166
bourne+0.163
Neg logit contributions
unity-0.165
 Yo-0.159
 Sergey-0.157
 VP-0.150
ulum-0.149
Token or
Token ID393
Feature activation-8.92e-02

Pos logit contributions
unity+0.171
 Yo+0.165
 Sergey+0.163
 VP+0.157
 Juno+0.154
Neg logit contributions
affle-0.195
rimination-0.181
 offender-0.178
icut-0.175
bourne-0.172
Token laptop
Token ID13224
Feature activation+3.91e-01

Pos logit contributions
unity+0.182
 Yo+0.175
 Sergey+0.173
 VP+0.166
 Juno+0.164
Neg logit contributions
affle-0.209
rimination-0.194
 offender-0.191
icut-0.187
bourne-0.184
Token,
Token ID11
Feature activation+9.24e-02

Pos logit contributions
affle+0.950
rimination+0.882
 offender+0.877
icut+0.854
aba+0.842
Neg logit contributions
unity-0.766
 Yo-0.734
 Sergey-0.724
 VP-0.690
ulum-0.686
Token cooler
Token ID19346
Feature activation-7.28e-01

Pos logit contributions
affle+0.219
rimination+0.203
 offender+0.201
icut+0.197
bourne+0.193
Neg logit contributions
unity-0.186
 Yo-0.178
 Sergey-0.176
 VP-0.168
ulum-0.167
Token or
Token ID393
Feature activation+2.82e-02

Pos logit contributions
unity+1.392
 Yo+1.357
 Sergey+1.334
 VP+1.283
 travelled+1.273
Neg logit contributions
affle-1.784
rimination-1.671
 offender-1.626
icut-1.609
bourne-1.588
Token AC
Token ID7125
Feature activation-1.36e-01

Pos logit contributions
affle+0.067
rimination+0.062
 offender+0.062
icut+0.060
bourne+0.060
Neg logit contributions
unity-0.056
 Yo-0.054
 Sergey-0.053
 VP-0.051
ulum-0.050
Token and
Token ID290
Feature activation-4.63e-02

Pos logit contributions
unity+0.284
 Yo+0.274
 Sergey+0.271
 VP+0.260
 Juno+0.256
Neg logit contributions
affle-0.313
rimination-0.289
 offender-0.285
icut-0.279
bourne-0.275
Token refrigerator
Token ID30500
Feature activation-2.47e-01

Pos logit contributions
unity+0.089
 Yo+0.086
 Sergey+0.085
 VP+0.081
 Juno+0.080
Neg logit contributions
affle-0.113
rimination-0.105
 offender-0.104
icut-0.102
bourne-0.101
Token.
Token ID13
Feature activation-1.89e-01

Pos logit contributions
unity+0.477
 Yo+0.461
 Sergey+0.455
 VP+0.435
 travelled+0.428
Neg logit contributions
affle-0.606
rimination-0.564
 offender-0.555
icut-0.545
bourne-0.539
Token.
Token ID13
Feature activation+1.18e-01

Pos logit contributions
affle+0.044
rimination+0.041
 offender+0.040
icut+0.040
aba+0.039
Neg logit contributions
unity-0.029
 Yo-0.028
 Sergey-0.028
 VP-0.026
ulum-0.026
Token However
Token ID2102
Feature activation+2.52e-01

Pos logit contributions
affle+0.285
rimination+0.265
 offender+0.261
icut+0.256
bourne+0.253
Neg logit contributions
unity-0.231
 Yo-0.222
 Sergey-0.219
 VP-0.209
 travelled-0.207
Token,
Token ID11
Feature activation+7.66e-02

Pos logit contributions
affle+0.547
rimination+0.503
 offender+0.503
icut+0.490
aba+0.484
Neg logit contributions
unity-0.558
 Yo-0.535
 Sergey-0.526
 VP-0.506
ulum-0.502
Token this
Token ID428
Feature activation-5.72e-02

Pos logit contributions
affle+0.187
rimination+0.174
 offender+0.171
icut+0.168
bourne+0.166
Neg logit contributions
unity-0.148
 Yo-0.143
 Sergey-0.141
 VP-0.135
 Juno-0.133
Token prudent
Token ID34998
Feature activation-2.83e-01

Pos logit contributions
unity+0.117
 Yo+0.114
 Sergey+0.112
 VP+0.108
 travelled+0.106
Neg logit contributions
affle-0.133
rimination-0.123
 offender-0.121
icut-0.119
bourne-0.118
Token check
Token ID2198
Feature activation-7.55e-01

Pos logit contributions
unity+0.574
 Yo+0.557
 Sergey+0.550
 VP+0.528
 UP+0.519
Neg logit contributions
affle-0.667
rimination-0.620
 offender-0.604
icut-0.596
bourne-0.588
Token on
Token ID319
Feature activation-1.23e-01

Pos logit contributions
unity+1.527
 Yo+1.468
 Sergey+1.444
 VP+1.385
ulum+1.381
Neg logit contributions
affle-1.774
rimination-1.657
 offender-1.617
icut-1.594
bourne-1.569
Token uncontrolled
Token ID47913
Feature activation+1.88e-01

Pos logit contributions
unity+0.299
 Yo+0.292
 Sergey+0.289
 VP+0.279
 Juno+0.275
Neg logit contributions
affle-0.239
rimination-0.218
 offender-0.212
icut-0.208
bourne-0.205
Token prescriptions
Token ID34092
Feature activation-1.56e-01

Pos logit contributions
affle+0.322
rimination+0.290
 offender+0.283
icut+0.276
bourne+0.271
Neg logit contributions
unity-0.503
 Yo-0.491
 Sergey-0.486
 VP-0.472
 Juno-0.466
Token need
Token ID761
Feature activation-1.69e-01

Pos logit contributions
unity+0.315
 Yo+0.306
 Sergey+0.303
 VP+0.289
 travelled+0.287
Neg logit contributions
affle-0.367
rimination-0.340
 offender-0.332
icut-0.328
bourne-0.323
Token not
Token ID407
Feature activation-1.96e-01

Pos logit contributions
unity+0.301
 Yo+0.289
 Sergey+0.285
 VP+0.271
 travelled+0.267
Neg logit contributions
affle-0.439
rimination-0.410
 offender-0.404
icut-0.397
bourne-0.393