TOP ACTIVATIONS
MAX = 2.252

Remember Na V or ro Bowman at the goal line
Barack Hussein Obama With low birth rate , America needs future
. uk or call 0 207 7 82 4 368 <|endoftext|>
co . uk or call 0 207 7 82 4 368
. org / 10 . 13 71 / journal . p
" The Trans atlantic Trade and Investment Partnership is a series
Kim b rough and Ros cos mos cos mon auts Sergey
s been Nikol aj Eh lers and Patri k
parallel compression without time mis al ignment . -
George W . Carey , a Fore word by Patrick J
space station operations . A Soy uz carrying NASA astronaut Shane
The Bh ag av ad G ita - and
and running back Sam aj e Per ine lead through the
ler ( Gar min - C er vel o ) s
- k ings , Watts Up With That is now the
i ( Ag 2 r - La Mond ial e )
Fuj ita , H arg ro ve , Smith ) v
own and do not represent the views of Town hall .
bloggers like John Scal zi from ever sweeping
ian . com or call 03 30 333 68 46 .

MIN ACTIVATIONS
MIN = -2.660

link for buying the second edition of my 1993 book ,
takes steps to open flights to US on sidelines of Trump
Big Bang Theory CBS Amy Poe hler Parks and Recreation NBC
ve written a couple of books , which you
takes steps to open flights to US on sidelines of Trump
Ric her t and David Gordon ( IS I Books ,
WikiLeaks about DNC emails Trump urges North Korea to den uclear
a terrible year for Tan ne hill and the Dolphins ,
takes steps to open flights to US on sidelines of Trump
MORE and Hillary Clinton Hillary Diane Rodham Clinton Sanders : '
MORE and Hillary Clinton Hillary Diane Rodham Clinton Sanders : '
presidential nominee Hillary Clinton Hillary Diane Rodham Clinton Sanders : '
Chandler Parsons , Dirk Now itz ki , Mont a Ellis
are these ? E - mail this to a friend Print
flights to US on sidelines of Trump - Kim summit Manafort
are these ? E - mail this to a friend Print
flights to US on sidelines of Trump - Kim summit Manafort
F Co - President Annie Laurie G aylor . " V
said . " I love Hels ing borg and Sweden ,
is the link for buying the second edition of my 1993

INTERVAL 1.024 - 2.252
CONTAINS 0.086%

) DOI : 10 . 10 86 / 34 110 7
ilities , family - and - children , consumer - f
on Saturday . Bull dogs Head Phys i other
sympathetic ( fight or flight ) and
she sank quickly into a mud pool that froze and preserved

INTERVAL -0.204 - 1.024
CONTAINS 83.917%

will be monitoring over the coming years . <|endoftext|> I personally
Trump cabinet is a who s -
help defend against the latest threats ." However , the Department
celer ating water removal from ash ponds at all retired coal
favorite chess site : In - game replay

INTERVAL -1.432 - -0.204
CONTAINS 15.977%

( ACT ) and the Northern Territory ( NT ). In
when they use that information to take a disciplinary action that
when he woke up around 3 : 48 a . m
you may find yourself stuck with the Token while your opponent
non - profit group , comm utes from her home in

INTERVAL -2.660 - -1.432
CONTAINS 0.020%

Walking Dead and An American Werewolf in London .
Chris Sutton , probably no Kenny Dal g lish either ,
Invisible Man , The H unch back of Notre Dame ,
the director is eyeing The New 52 for inspiration and hoping
Big Bang Theory CBS Amy Poe hler Parks and Recreation NBC
Token
Token ID198
Feature activation+6.02e-02

Pos logit contributions
 Ake+0.026
 Scand+0.024
ewski+0.023
do+0.022
arov+0.021
Neg logit contributions
retty-0.030
emouth-0.027
ergus-0.026
idth-0.025
edom-0.024
TokenRemember
Token ID16676
Feature activation+8.92e-02

Pos logit contributions
 Ake+0.041
 Scand+0.039
ewski+0.036
do+0.035
arov+0.034
Neg logit contributions
retty-0.051
emouth-0.046
ergus-0.043
idth-0.042
edom-0.042
Token Na
Token ID11013
Feature activation-3.46e-01

Pos logit contributions
 Ake+0.062
 Scand+0.059
ewski+0.056
do+0.053
arov+0.052
Neg logit contributions
retty-0.073
emouth-0.066
ergus-0.063
idth-0.061
edom-0.060
TokenV
Token ID53
Feature activation+1.36e-02

Pos logit contributions
retty+0.279
emouth+0.252
ergus+0.238
idth+0.232
edom+0.227
Neg logit contributions
 Ake-0.245
 Scand-0.235
ewski-0.221
do-0.212
arov-0.206
Tokenor
Token ID273
Feature activation-6.78e-02

Pos logit contributions
 Ake+0.010
 Scand+0.010
ewski+0.009
do+0.009
arov+0.009
Neg logit contributions
retty-0.010
emouth-0.009
ergus-0.009
idth-0.008
edom-0.008
Tokenro
Token ID305
Feature activation+2.25e+00

Pos logit contributions
retty+0.046
emouth+0.040
ergus+0.038
idth+0.036
edom+0.035
Neg logit contributions
 Ake-0.057
 Scand-0.055
ewski-0.052
do-0.051
arov-0.050
Token Bowman
Token ID38774
Feature activation-1.50e-02

Pos logit contributions
 Ake+1.910
 Scand+1.824
ewski+1.780
arov+1.694
do+1.673
Neg logit contributions
retty-1.461
emouth-1.270
ergus-1.204
edom-1.158
idth-1.157
Token at
Token ID379
Feature activation+2.08e-01

Pos logit contributions
retty+0.012
emouth+0.011
ergus+0.010
idth+0.010
edom+0.010
Neg logit contributions
 Ake-0.010
 Scand-0.010
ewski-0.009
do-0.009
arov-0.009
Token the
Token ID262
Feature activation-2.71e-01

Pos logit contributions
 Ake+0.144
 Scand+0.138
ewski+0.130
do+0.125
arov+0.122
Neg logit contributions
retty-0.170
emouth-0.153
ergus-0.145
idth-0.141
edom-0.139
Token goal
Token ID3061
Feature activation-3.90e-01

Pos logit contributions
retty+0.209
emouth+0.187
ergus+0.177
idth+0.172
edom+0.168
Neg logit contributions
 Ake-0.203
 Scand-0.195
ewski-0.184
do-0.177
arov-0.172
Token line
Token ID1627
Feature activation-6.94e-02

Pos logit contributions
retty+0.313
emouth+0.282
ergus+0.267
idth+0.260
edom+0.254
Neg logit contributions
 Ake-0.277
 Scand-0.266
ewski-0.250
do-0.241
arov-0.234
Token Barack
Token ID8732
Feature activation+3.03e-01

Pos logit contributions
retty+0.272
emouth+0.245
ergus+0.232
idth+0.227
edom+0.222
Neg logit contributions
 Ake-0.225
 Scand-0.216
ewski-0.203
do-0.195
arov-0.189
Token Hussein
Token ID22983
Feature activation-1.31e+00

Pos logit contributions
 Ake+0.227
 Scand+0.218
ewski+0.206
do+0.198
arov+0.194
Neg logit contributions
retty-0.232
emouth-0.208
ergus-0.196
idth-0.191
edom-0.187
Token Obama
Token ID2486
Feature activation-2.64e-01

Pos logit contributions
retty+1.032
emouth+0.938
ergus+0.876
idth+0.857
edom+0.837
Neg logit contributions
 Ake-0.958
 Scand-0.915
ewski-0.859
do-0.825
der-0.804
TokenWith
Token ID3152
Feature activation+2.49e-02

Pos logit contributions
retty+0.215
emouth+0.195
ergus+0.184
idth+0.180
edom+0.176
Neg logit contributions
 Ake-0.185
 Scand-0.177
ewski-0.167
do-0.160
arov-0.155
Token low
Token ID1877
Feature activation+1.30e+00

Pos logit contributions
 Ake+0.019
 Scand+0.018
ewski+0.017
do+0.016
arov+0.016
Neg logit contributions
retty-0.019
emouth-0.017
ergus-0.016
idth-0.016
edom-0.015
Token birth
Token ID4082
Feature activation+2.03e+00

Pos logit contributions
 Ake+0.935
 Scand+0.897
ewski+0.859
do+0.810
arov+0.795
Neg logit contributions
retty-1.011
emouth-0.916
ergus-0.871
idth-0.846
edom-0.836
Token rate
Token ID2494
Feature activation-1.57e-01

Pos logit contributions
 Ake+1.672
 Scand+1.588
ewski+1.516
do+1.425
arov+1.425
Neg logit contributions
retty-1.405
emouth-1.273
ergus-1.182
idth-1.140
 PID-1.128
Token,
Token ID11
Feature activation+4.74e-02

Pos logit contributions
retty+0.130
emouth+0.117
ergus+0.111
idth+0.108
edom+0.106
Neg logit contributions
 Ake-0.108
 Scand-0.103
ewski-0.097
do-0.093
arov-0.090
Token America
Token ID2253
Feature activation-7.82e-02

Pos logit contributions
 Ake+0.033
 Scand+0.032
ewski+0.030
do+0.029
arov+0.028
Neg logit contributions
retty-0.038
emouth-0.034
ergus-0.033
idth-0.032
edom-0.031
Token needs
Token ID2476
Feature activation-1.30e+00

Pos logit contributions
retty+0.062
emouth+0.056
ergus+0.053
idth+0.052
edom+0.051
Neg logit contributions
 Ake-0.056
 Scand-0.054
ewski-0.051
do-0.049
arov-0.047
Token future
Token ID2003
Feature activation-9.30e-01

Pos logit contributions
retty+1.097
emouth+0.987
ergus+0.937
idth+0.923
edom+0.893
Neg logit contributions
 Ake-0.883
 Scand-0.835
ewski-0.788
do-0.760
arov-0.740
Token.
Token ID13
Feature activation-3.80e-01

Pos logit contributions
 Ake+0.070
 Scand+0.067
ewski+0.063
do+0.061
arov+0.059
Neg logit contributions
retty-0.078
emouth-0.070
ergus-0.066
idth-0.065
edom-0.063
Tokenuk
Token ID2724
Feature activation-4.87e-01

Pos logit contributions
retty+0.259
emouth+0.228
ergus+0.213
idth+0.208
edom+0.202
Neg logit contributions
 Ake-0.317
 Scand-0.305
ewski-0.291
do-0.282
arov-0.275
Token or
Token ID393
Feature activation-4.49e-01

Pos logit contributions
retty+0.409
emouth+0.370
ergus+0.350
idth+0.343
edom+0.336
Neg logit contributions
 Ake-0.328
 Scand-0.315
ewski-0.296
do-0.284
arov-0.275
Token call
Token ID869
Feature activation+9.74e-01

Pos logit contributions
retty+0.338
emouth+0.304
ergus+0.284
idth+0.278
edom+0.272
Neg logit contributions
 Ake-0.342
 Scand-0.329
ewski-0.310
do-0.302
arov-0.292
Token 0
Token ID657
Feature activation+1.98e+00

Pos logit contributions
 Ake+0.679
 Scand+0.650
ewski+0.616
do+0.585
arov+0.574
Neg logit contributions
retty-0.795
emouth-0.715
ergus-0.684
idth-0.655
edom-0.647
Token207
Token ID22745
Feature activation+2.01e+00

Pos logit contributions
 Ake+1.412
 Scand+1.370
ewski+1.289
do+1.211
arov+1.202
Neg logit contributions
retty-1.546
emouth-1.384
ergus-1.340
idth-1.289
edom-1.284
Token 7
Token ID767
Feature activation+8.72e-01

Pos logit contributions
 Ake+1.403
 Scand+1.332
ewski+1.256
do+1.212
arov+1.182
Neg logit contributions
retty-1.622
emouth-1.470
ergus-1.386
idth-1.369
 PID-1.362
Token82
Token ID6469
Feature activation+8.52e-01

Pos logit contributions
 Ake+0.635
 Scand+0.609
ewski+0.577
do+0.552
arov+0.545
Neg logit contributions
retty-0.681
emouth-0.610
ergus-0.580
idth-0.565
edom-0.554
Token 4
Token ID604
Feature activation+9.03e-01

Pos logit contributions
 Ake+0.564
 Scand+0.540
ewski+0.509
do+0.485
arov+0.472
Neg logit contributions
retty-0.719
emouth-0.653
ergus-0.620
idth-0.604
edom-0.593
Token368
Token ID27412
Feature activation+1.54e-01

Pos logit contributions
 Ake+0.570
 Scand+0.543
ewski+0.508
do+0.483
arov+0.472
Neg logit contributions
retty-0.793
emouth-0.720
ergus-0.691
idth-0.673
edom-0.661
Token<|endoftext|>
Token ID50256
Feature activation+1.47e-01

Pos logit contributions
 Ake+0.105
 Scand+0.100
ewski+0.094
do+0.090
arov+0.088
Neg logit contributions
retty-0.128
emouth-0.116
ergus-0.110
idth-0.107
edom-0.105
Tokenco
Token ID1073
Feature activation+9.77e-02

Pos logit contributions
retty+0.328
emouth+0.300
ergus+0.285
idth+0.279
edom+0.274
Neg logit contributions
 Ake-0.212
 Scand-0.202
ewski-0.187
do-0.179
arov-0.172
Token.
Token ID13
Feature activation-3.80e-01

Pos logit contributions
 Ake+0.070
 Scand+0.067
ewski+0.063
do+0.061
arov+0.059
Neg logit contributions
retty-0.078
emouth-0.070
ergus-0.066
idth-0.065
edom-0.063
Tokenuk
Token ID2724
Feature activation-4.87e-01

Pos logit contributions
retty+0.259
emouth+0.228
ergus+0.213
idth+0.208
edom+0.202
Neg logit contributions
 Ake-0.317
 Scand-0.305
ewski-0.291
do-0.282
arov-0.275
Token or
Token ID393
Feature activation-4.49e-01

Pos logit contributions
retty+0.409
emouth+0.370
ergus+0.350
idth+0.343
edom+0.336
Neg logit contributions
 Ake-0.328
 Scand-0.315
ewski-0.296
do-0.284
arov-0.275
Token call
Token ID869
Feature activation+9.74e-01

Pos logit contributions
retty+0.338
emouth+0.304
ergus+0.284
idth+0.278
edom+0.272
Neg logit contributions
 Ake-0.342
 Scand-0.329
ewski-0.310
do-0.302
arov-0.292
Token 0
Token ID657
Feature activation+1.98e+00

Pos logit contributions
 Ake+0.679
 Scand+0.650
ewski+0.616
do+0.585
arov+0.574
Neg logit contributions
retty-0.795
emouth-0.715
ergus-0.684
idth-0.655
edom-0.647
Token207
Token ID22745
Feature activation+2.01e+00

Pos logit contributions
 Ake+1.412
 Scand+1.370
ewski+1.289
do+1.211
arov+1.202
Neg logit contributions
retty-1.546
emouth-1.384
ergus-1.340
idth-1.289
edom-1.284
Token 7
Token ID767
Feature activation+8.72e-01

Pos logit contributions
 Ake+1.403
 Scand+1.332
ewski+1.256
do+1.212
arov+1.182
Neg logit contributions
retty-1.622
emouth-1.470
ergus-1.386
idth-1.369
 PID-1.362
Token82
Token ID6469
Feature activation+8.52e-01

Pos logit contributions
 Ake+0.635
 Scand+0.609
ewski+0.577
do+0.552
arov+0.545
Neg logit contributions
retty-0.681
emouth-0.610
ergus-0.580
idth-0.565
edom-0.554
Token 4
Token ID604
Feature activation+9.03e-01

Pos logit contributions
 Ake+0.564
 Scand+0.540
ewski+0.509
do+0.485
arov+0.472
Neg logit contributions
retty-0.719
emouth-0.653
ergus-0.620
idth-0.604
edom-0.593
Token368
Token ID27412
Feature activation+1.54e-01

Pos logit contributions
 Ake+0.570
 Scand+0.543
ewski+0.508
do+0.483
arov+0.472
Neg logit contributions
retty-0.793
emouth-0.720
ergus-0.691
idth-0.673
edom-0.661
Token.
Token ID13
Feature activation+4.21e-01

Pos logit contributions
 Ake+0.366
 Scand+0.352
ewski+0.330
do+0.317
arov+0.310
Neg logit contributions
retty-0.398
emouth-0.359
ergus-0.339
idth-0.330
edom-0.323
Tokenorg
Token ID2398
Feature activation+3.24e-01

Pos logit contributions
 Ake+0.364
 Scand+0.352
ewski+0.334
do+0.322
arov+0.316
Neg logit contributions
retty-0.274
emouth-0.240
ergus-0.224
idth-0.217
edom-0.211
Token/
Token ID14
Feature activation+8.43e-01

Pos logit contributions
 Ake+0.225
 Scand+0.216
ewski+0.203
do+0.194
arov+0.189
Neg logit contributions
retty-0.265
emouth-0.239
ergus-0.226
idth-0.221
edom-0.217
Token10
Token ID940
Feature activation+6.58e-01

Pos logit contributions
 Ake+0.488
 Scand+0.463
ewski+0.430
do+0.403
arov+0.394
Neg logit contributions
retty-0.789
emouth-0.720
ergus-0.687
idth-0.675
edom-0.662
Token.
Token ID13
Feature activation+1.13e+00

Pos logit contributions
 Ake+0.479
 Scand+0.460
ewski+0.433
do+0.413
arov+0.406
Neg logit contributions
retty-0.514
emouth-0.463
ergus-0.438
idth-0.426
edom-0.418
Token13
Token ID1485
Feature activation+1.95e+00

Pos logit contributions
 Ake+0.623
 Scand+0.583
ewski+0.541
do+0.500
arov+0.492
Neg logit contributions
retty-1.087
emouth-0.996
ergus-0.953
idth-0.941
edom-0.923
Token71
Token ID4869
Feature activation+5.71e-01

Pos logit contributions
 Ake+1.252
 Scand+1.208
ewski+1.129
do+1.070
arov+1.068
Neg logit contributions
retty-1.664
emouth-1.507
ergus-1.432
idth-1.416
edom-1.376
Token/
Token ID14
Feature activation+3.71e-01

Pos logit contributions
 Ake+0.399
 Scand+0.383
ewski+0.359
do+0.344
arov+0.336
Neg logit contributions
retty-0.462
emouth-0.418
ergus-0.396
idth-0.386
edom-0.378
Tokenjournal
Token ID24891
Feature activation-3.11e-01

Pos logit contributions
 Ake+0.297
 Scand+0.286
ewski+0.271
do+0.261
arov+0.256
Neg logit contributions
retty-0.264
emouth-0.235
ergus-0.220
idth-0.214
edom-0.209
Token.
Token ID13
Feature activation-6.93e-01

Pos logit contributions
retty+0.251
emouth+0.226
ergus+0.214
idth+0.208
edom+0.205
Neg logit contributions
 Ake-0.219
 Scand-0.210
ewski-0.198
do-0.191
arov-0.186
Tokenp
Token ID79
Feature activation+1.51e+00

Pos logit contributions
retty+0.579
emouth+0.524
ergus+0.496
idth+0.484
edom+0.477
Neg logit contributions
 Ake-0.466
 Scand-0.449
ewski-0.424
do-0.409
arov-0.394
Token "
Token ID366
Feature activation+1.28e-01

Pos logit contributions
 Ake+0.154
 Scand+0.147
ewski+0.139
do+0.133
arov+0.130
Neg logit contributions
retty-0.174
emouth-0.156
ergus-0.148
idth-0.144
edom-0.141
TokenThe
Token ID464
Feature activation+1.71e-01

Pos logit contributions
 Ake+0.087
 Scand+0.083
ewski+0.078
do+0.075
arov+0.073
Neg logit contributions
retty-0.107
emouth-0.097
ergus-0.092
idth-0.090
edom-0.088
Token Trans
Token ID3602
Feature activation+5.75e-02

Pos logit contributions
 Ake+0.121
 Scand+0.116
ewski+0.109
do+0.105
arov+0.102
Neg logit contributions
retty-0.139
emouth-0.125
ergus-0.118
idth-0.115
edom-0.113
Tokenatlantic
Token ID43342
Feature activation+2.95e-01

Pos logit contributions
 Ake+0.042
 Scand+0.041
ewski+0.038
do+0.037
arov+0.036
Neg logit contributions
retty-0.045
emouth-0.040
ergus-0.038
idth-0.037
edom-0.036
Token Trade
Token ID9601
Feature activation-4.76e-01

Pos logit contributions
 Ake+0.167
 Scand+0.158
ewski+0.147
do+0.139
arov+0.135
Neg logit contributions
retty-0.279
emouth-0.256
ergus-0.245
idth-0.239
edom-0.235
Token and
Token ID290
Feature activation+1.90e+00

Pos logit contributions
retty+0.400
emouth+0.362
ergus+0.342
idth+0.335
edom+0.328
Neg logit contributions
 Ake-0.322
 Scand-0.309
ewski-0.289
do-0.278
arov-0.269
Token Investment
Token ID20877
Feature activation+1.00e+00

Pos logit contributions
 Ake+1.168
 Scand+1.115
ewski+1.056
do+0.995
+0.976
Neg logit contributions
retty-1.684
emouth-1.538
ergus-1.483
idth-1.446
 PID-1.422
Token Partnership
Token ID23270
Feature activation-1.05e-01

Pos logit contributions
 Ake+0.555
 Scand+0.525
ewski+0.489
do+0.460
arov+0.447
Neg logit contributions
retty-0.953
emouth-0.877
ergus-0.842
idth-0.821
 PID-0.807
Token is
Token ID318
Feature activation-1.19e-01

Pos logit contributions
retty+0.084
emouth+0.076
ergus+0.072
idth+0.070
edom+0.069
Neg logit contributions
 Ake-0.074
 Scand-0.071
ewski-0.067
do-0.064
arov-0.063
Token a
Token ID257
Feature activation-6.54e-02

Pos logit contributions
retty+0.096
emouth+0.087
ergus+0.082
idth+0.080
edom+0.079
Neg logit contributions
 Ake-0.084
 Scand-0.081
ewski-0.076
do-0.073
arov-0.071
Token series
Token ID2168
Feature activation-1.92e-01

Pos logit contributions
retty+0.050
emouth+0.045
ergus+0.043
idth+0.041
edom+0.041
Neg logit contributions
 Ake-0.049
 Scand-0.047
ewski-0.044
do-0.043
arov-0.042
Token Kim
Token ID6502
Feature activation+5.65e-01

Pos logit contributions
 Ake+0.317
 Scand+0.303
ewski+0.286
do+0.274
arov+0.268
Neg logit contributions
retty-0.368
emouth-0.332
ergus-0.314
idth-0.306
edom-0.301
Tokenb
Token ID65
Feature activation-5.35e-02

Pos logit contributions
 Ake+0.407
 Scand+0.391
ewski+0.367
do+0.353
arov+0.344
Neg logit contributions
retty-0.448
emouth-0.404
ergus-0.381
idth-0.371
edom-0.365
Tokenrough
Token ID740
Feature activation+6.27e-02

Pos logit contributions
retty+0.045
emouth+0.041
ergus+0.039
idth+0.038
edom+0.037
Neg logit contributions
 Ake-0.036
 Scand-0.035
ewski-0.032
do-0.031
arov-0.030
Token and
Token ID290
Feature activation+1.88e-01

Pos logit contributions
 Ake+0.044
 Scand+0.042
ewski+0.040
do+0.038
arov+0.037
Neg logit contributions
retty-0.051
emouth-0.046
ergus-0.044
idth-0.042
edom-0.042
Token Ros
Token ID10018
Feature activation+5.29e-01

Pos logit contributions
 Ake+0.132
 Scand+0.127
ewski+0.119
do+0.114
arov+0.111
Neg logit contributions
retty-0.153
emouth-0.138
ergus-0.131
idth-0.128
edom-0.125
Tokencos
Token ID6966
Feature activation+1.89e+00

Pos logit contributions
 Ake+0.406
 Scand+0.391
ewski+0.369
do+0.354
arov+0.348
Neg logit contributions
retty-0.393
emouth-0.352
ergus-0.332
idth-0.322
edom-0.315
Tokenmos
Token ID16785
Feature activation+6.68e-01

Pos logit contributions
 Ake+1.327
 Scand+1.266
ewski+1.190
do+1.141
+1.109
Neg logit contributions
retty-1.537
emouth-1.379
ergus-1.323
idth-1.275
 PID-1.254
Token cos
Token ID8615
Feature activation+1.04e+00

Pos logit contributions
 Ake+0.488
 Scand+0.468
ewski+0.442
do+0.424
arov+0.415
Neg logit contributions
retty-0.523
emouth-0.469
ergus-0.444
idth-0.432
edom-0.424
Tokenmon
Token ID2144
Feature activation+8.41e-01

Pos logit contributions
 Ake+0.439
 Scand+0.411
ewski+0.367
do+0.335
arov+0.323
Neg logit contributions
retty-1.132
emouth-1.051
ergus-1.015
idth-0.992
edom-0.984
Tokenauts
Token ID17712
Feature activation+1.13e-01

Pos logit contributions
 Ake+0.787
 Scand+0.764
ewski+0.728
do+0.707
arov+0.696
Neg logit contributions
retty-0.484
emouth-0.418
ergus-0.388
idth-0.372
edom-0.362
Token Sergey
Token ID36106
Feature activation+1.01e+00

Pos logit contributions
 Ake+0.078
 Scand+0.075
ewski+0.071
do+0.068
arov+0.066
Neg logit contributions
retty-0.093
emouth-0.084
ergus-0.080
idth-0.078
edom-0.076
Token
Token ID447
Feature activation-8.28e-02

Pos logit contributions
retty+0.254
emouth+0.230
ergus+0.218
idth+0.213
edom+0.208
Neg logit contributions
 Ake-0.204
 Scand-0.195
ewski-0.183
do-0.176
arov-0.171
Token
Token ID247
Feature activation-2.10e-01

Pos logit contributions
retty+0.071
emouth+0.064
ergus+0.061
idth+0.060
edom+0.059
Neg logit contributions
 Ake-0.055
 Scand-0.052
ewski-0.049
do-0.047
arov-0.045
Tokens
Token ID82
Feature activation-3.57e-02

Pos logit contributions
retty+0.148
emouth+0.131
ergus+0.123
idth+0.119
edom+0.116
Neg logit contributions
 Ake-0.170
 Scand-0.164
ewski-0.156
do-0.151
arov-0.147
Token been
Token ID587
Feature activation+1.13e-01

Pos logit contributions
retty+0.027
emouth+0.025
ergus+0.023
idth+0.022
edom+0.022
Neg logit contributions
 Ake-0.027
 Scand-0.026
ewski-0.024
do-0.023
arov-0.023
Token Nikol
Token ID48127
Feature activation+5.82e-01

Pos logit contributions
 Ake+0.082
 Scand+0.078
ewski+0.074
do+0.071
arov+0.069
Neg logit contributions
retty-0.089
emouth-0.080
ergus-0.075
idth-0.073
edom-0.072
Tokenaj
Token ID1228
Feature activation+1.89e+00

Pos logit contributions
 Ake+0.410
 Scand+0.392
ewski+0.369
do+0.354
arov+0.345
Neg logit contributions
retty-0.471
emouth-0.424
ergus-0.403
idth-0.393
edom-0.385
Token Eh
Token ID31480
Feature activation-4.24e-01

Pos logit contributions
 Ake+1.369
 Scand+1.314
ewski+1.236
do+1.218
+1.169
Neg logit contributions
retty-1.457
emouth-1.318
ergus-1.234
idth-1.224
edom-1.196
Tokenlers
Token ID8116
Feature activation+1.42e-01

Pos logit contributions
retty+0.296
emouth+0.262
ergus+0.245
idth+0.238
edom+0.232
Neg logit contributions
 Ake-0.346
 Scand-0.335
ewski-0.317
do-0.308
arov-0.300
Token and
Token ID290
Feature activation-3.29e-03

Pos logit contributions
 Ake+0.100
 Scand+0.096
ewski+0.090
do+0.087
arov+0.084
Neg logit contributions
retty-0.115
emouth-0.104
ergus-0.098
idth-0.096
edom-0.094
Token Patri
Token ID9606
Feature activation+7.23e-01

Pos logit contributions
retty+0.003
emouth+0.002
ergus+0.002
idth+0.002
edom+0.002
Neg logit contributions
 Ake-0.002
 Scand-0.002
ewski-0.002
do-0.002
arov-0.002
Tokenk
Token ID74
Feature activation-2.44e-01

Pos logit contributions
 Ake+0.440
 Scand+0.415
ewski+0.391
do+0.370
arov+0.361
Neg logit contributions
retty-0.653
emouth-0.596
ergus-0.568
idth-0.556
edom-0.546
Token parallel
Token ID10730
Feature activation-2.53e-01

Pos logit contributions
 Ake+0.245
 Scand+0.235
ewski+0.221
do+0.213
arov+0.207
Neg logit contributions
retty-0.286
emouth-0.258
ergus-0.244
idth-0.238
edom-0.234
Token compression
Token ID19794
Feature activation-9.53e-03

Pos logit contributions
retty+0.198
emouth+0.178
ergus+0.168
idth+0.163
edom+0.160
Neg logit contributions
 Ake-0.185
 Scand-0.178
ewski-0.167
do-0.161
arov-0.157
Token without
Token ID1231
Feature activation-5.87e-02

Pos logit contributions
retty+0.008
emouth+0.007
ergus+0.007
idth+0.007
edom+0.006
Neg logit contributions
 Ake-0.007
 Scand-0.006
ewski-0.006
do-0.006
arov-0.006
Token time
Token ID640
Feature activation+3.69e-01

Pos logit contributions
retty+0.046
emouth+0.042
ergus+0.039
idth+0.038
edom+0.038
Neg logit contributions
 Ake-0.043
 Scand-0.041
ewski-0.039
do-0.037
arov-0.036
Token mis
Token ID2984
Feature activation+4.04e-01

Pos logit contributions
 Ake+0.270
 Scand+0.259
ewski+0.245
do+0.235
arov+0.229
Neg logit contributions
retty-0.289
emouth-0.260
ergus-0.245
idth-0.238
edom-0.234
Tokenal
Token ID282
Feature activation+1.87e+00

Pos logit contributions
 Ake+0.312
 Scand+0.301
ewski+0.284
do+0.274
arov+0.268
Neg logit contributions
retty-0.298
emouth-0.266
ergus-0.251
idth-0.244
edom-0.238
Tokenignment
Token ID16747
Feature activation+2.42e-01

Pos logit contributions
 Ake+0.660
 Scand+0.609
ewski+0.519
do+0.476
arov+0.455
Neg logit contributions
retty-2.155
emouth-2.022
ergus-1.954
idth-1.925
edom-1.901
Token.
Token ID13
Feature activation-7.42e-03

Pos logit contributions
 Ake+0.171
 Scand+0.164
ewski+0.155
do+0.149
arov+0.145
Neg logit contributions
retty-0.195
emouth-0.176
ergus-0.167
idth-0.162
edom-0.159
Token
Token ID198
Feature activation-1.62e-02

Pos logit contributions
retty+0.006
emouth+0.006
ergus+0.005
idth+0.005
edom+0.005
Neg logit contributions
 Ake-0.005
 Scand-0.005
ewski-0.005
do-0.004
arov-0.004
Token
Token ID198
Feature activation-2.16e-01

Pos logit contributions
retty+0.013
emouth+0.012
ergus+0.011
idth+0.011
edom+0.011
Neg logit contributions
 Ake-0.011
 Scand-0.011
ewski-0.010
do-0.010
arov-0.010
Token-
Token ID12
Feature activation+1.55e-01

Pos logit contributions
retty+0.182
emouth+0.165
ergus+0.156
idth+0.152
edom+0.149
Neg logit contributions
 Ake-0.146
 Scand-0.140
ewski-0.131
do-0.126
arov-0.122
Token George
Token ID4502
Feature activation+3.24e-01

Pos logit contributions
 Ake+0.864
 Scand+0.832
ewski+0.790
do+0.747
arov+0.727
Neg logit contributions
retty-1.117
emouth-1.007
ergus-0.963
idth-0.929
edom-0.907
Token W
Token ID370
Feature activation-3.06e-01

Pos logit contributions
 Ake+0.221
 Scand+0.212
ewski+0.199
do+0.191
arov+0.186
Neg logit contributions
retty-0.268
emouth-0.242
ergus-0.230
idth-0.224
edom-0.220
Token.
Token ID13
Feature activation-9.73e-01

Pos logit contributions
retty+0.247
emouth+0.223
ergus+0.210
idth+0.206
edom+0.201
Neg logit contributions
 Ake-0.216
 Scand-0.207
ewski-0.196
do-0.188
arov-0.183
Token Carey
Token ID31612
Feature activation-5.13e-01

Pos logit contributions
retty+0.899
emouth+0.827
ergus+0.777
idth+0.768
edom+0.754
Neg logit contributions
 Ake-0.583
 Scand-0.550
ewski-0.511
do-0.486
der-0.467
Token,
Token ID11
Feature activation+6.06e-01

Pos logit contributions
retty+0.429
emouth+0.389
ergus+0.368
idth+0.360
edom+0.353
Neg logit contributions
 Ake-0.349
 Scand-0.334
ewski-0.314
do-0.301
arov-0.291
Token a
Token ID257
Feature activation+1.87e+00

Pos logit contributions
 Ake+0.433
 Scand+0.417
ewski+0.393
do+0.375
arov+0.367
Neg logit contributions
retty-0.483
emouth-0.434
ergus-0.410
idth-0.400
edom-0.391
Token Fore
Token ID4558
Feature activation+2.82e-01

Pos logit contributions
 Ake+1.052
 Scand+1.001
ewski+0.941
do+0.881
arov+0.874
Neg logit contributions
retty-1.753
emouth-1.577
ergus-1.520
idth-1.510
edom-1.463
Tokenword
Token ID4775
Feature activation-1.14e-01

Pos logit contributions
 Ake+0.228
 Scand+0.220
ewski+0.209
do+0.201
arov+0.197
Neg logit contributions
retty-0.199
emouth-0.177
ergus-0.166
idth-0.161
edom-0.157
Token by
Token ID416
Feature activation-6.76e-01

Pos logit contributions
retty+0.097
emouth+0.089
ergus+0.084
idth+0.082
edom+0.081
Neg logit contributions
 Ake-0.075
 Scand-0.072
ewski-0.067
do-0.065
arov-0.063
Token Patrick
Token ID9925
Feature activation-1.62e-02

Pos logit contributions
retty+0.493
emouth+0.440
ergus+0.411
idth+0.404
edom+0.397
Neg logit contributions
 Ake-0.533
 Scand-0.511
ewski-0.480
do-0.470
arov-0.455
Token J
Token ID449
Feature activation-1.06e-01

Pos logit contributions
retty+0.017
emouth+0.015
ergus+0.015
idth+0.014
edom+0.014
Neg logit contributions
 Ake-0.008
 Scand-0.008
ewski-0.007
do-0.007
arov-0.006
Token space
Token ID2272
Feature activation+6.40e-01

Pos logit contributions
 Ake+0.113
 Scand+0.108
ewski+0.101
do+0.097
arov+0.094
Neg logit contributions
retty-0.145
emouth-0.132
ergus-0.125
idth-0.122
edom-0.120
Token station
Token ID4429
Feature activation-2.67e-01

Pos logit contributions
 Ake+0.439
 Scand+0.419
ewski+0.395
do+0.377
arov+0.368
Neg logit contributions
retty-0.530
emouth-0.479
ergus-0.454
idth-0.443
edom-0.435
Token operations
Token ID4560
Feature activation+1.67e-01

Pos logit contributions
retty+0.219
emouth+0.198
ergus+0.187
idth+0.182
edom+0.179
Neg logit contributions
 Ake-0.185
 Scand-0.177
ewski-0.167
do-0.160
arov-0.156
Token.
Token ID13
Feature activation+1.13e-01

Pos logit contributions
 Ake+0.117
 Scand+0.112
ewski+0.105
do+0.101
arov+0.098
Neg logit contributions
retty-0.135
emouth-0.122
ergus-0.116
idth-0.113
edom-0.110
Token A
Token ID317
Feature activation-3.43e-03

Pos logit contributions
 Ake+0.077
 Scand+0.074
ewski+0.069
do+0.066
arov+0.064
Neg logit contributions
retty-0.094
emouth-0.085
ergus-0.080
idth-0.078
edom-0.077
Token Soy
Token ID30022
Feature activation+1.86e+00

Pos logit contributions
retty+0.003
emouth+0.002
ergus+0.002
idth+0.002
edom+0.002
Neg logit contributions
 Ake-0.002
 Scand-0.002
ewski-0.002
do-0.002
arov-0.002
Tokenuz
Token ID10277
Feature activation+5.60e-01

Pos logit contributions
 Ake+1.391
 Scand+1.324
ewski+1.258
do+1.192
arov+1.166
Neg logit contributions
retty-1.415
emouth-1.270
ergus-1.212
idth-1.180
edom-1.144
Token carrying
Token ID6872
Feature activation+7.90e-02

Pos logit contributions
 Ake+0.372
 Scand+0.356
ewski+0.334
do+0.319
arov+0.311
Neg logit contributions
retty-0.474
emouth-0.429
ergus-0.408
idth-0.398
edom-0.392
Token NASA
Token ID8884
Feature activation+6.44e-01

Pos logit contributions
 Ake+0.057
 Scand+0.054
ewski+0.051
do+0.049
arov+0.048
Neg logit contributions
retty-0.063
emouth-0.057
ergus-0.054
idth-0.052
edom-0.051
Token astronaut
Token ID33779
Feature activation+1.10e-01

Pos logit contributions
 Ake+0.443
 Scand+0.425
ewski+0.400
do+0.383
arov+0.373
Neg logit contributions
retty-0.531
emouth-0.479
ergus-0.455
idth-0.444
edom-0.435
Token Shane
Token ID24379
Feature activation+4.53e-01

Pos logit contributions
 Ake+0.077
 Scand+0.074
ewski+0.070
do+0.067
arov+0.065
Neg logit contributions
retty-0.088
emouth-0.080
ergus-0.075
idth-0.074
edom-0.072
Token The
Token ID383
Feature activation+2.89e-01

Pos logit contributions
 Ake+0.171
 Scand+0.164
ewski+0.154
do+0.148
arov+0.144
Neg logit contributions
retty-0.212
emouth-0.192
ergus-0.182
idth-0.178
edom-0.175
Token Bh
Token ID16581
Feature activation+1.44e-01

Pos logit contributions
 Ake+0.194
 Scand+0.185
ewski+0.174
do+0.167
arov+0.162
Neg logit contributions
retty-0.243
emouth-0.220
ergus-0.208
idth-0.203
edom-0.200
Tokenag
Token ID363
Feature activation+4.36e-01

Pos logit contributions
 Ake+0.076
 Scand+0.072
ewski+0.066
do+0.063
arov+0.060
Neg logit contributions
retty-0.141
emouth-0.130
ergus-0.124
idth-0.122
edom-0.120
Tokenav
Token ID615
Feature activation+1.89e-01

Pos logit contributions
 Ake+0.271
 Scand+0.258
ewski+0.241
do+0.229
arov+0.222
Neg logit contributions
retty-0.389
emouth-0.354
ergus-0.337
idth-0.330
edom-0.324
Tokenad
Token ID324
Feature activation-3.99e-02

Pos logit contributions
 Ake+0.128
 Scand+0.123
ewski+0.115
do+0.110
arov+0.107
Neg logit contributions
retty-0.158
emouth-0.143
ergus-0.135
idth-0.132
edom-0.129
Token G
Token ID402
Feature activation+1.83e+00

Pos logit contributions
retty+0.033
emouth+0.029
ergus+0.028
idth+0.027
edom+0.027
Neg logit contributions
 Ake-0.028
 Scand-0.027
ewski-0.025
do-0.024
arov-0.024
Tokenita
Token ID5350
Feature activation-2.99e-01

Pos logit contributions
 Ake+1.034
 Scand+0.977
ewski+0.895
do+0.838
+0.836
Neg logit contributions
retty-1.731
emouth-1.592
ergus-1.518
idth-1.496
edom-1.493
Token
Token ID198
Feature activation+1.61e-02

Pos logit contributions
retty+0.247
emouth+0.224
ergus+0.212
idth+0.207
edom+0.203
Neg logit contributions
 Ake-0.205
 Scand-0.196
ewski-0.184
do-0.177
arov-0.172
Token
Token ID198
Feature activation+2.87e-02

Pos logit contributions
 Ake+0.011
 Scand+0.011
ewski+0.010
do+0.010
arov+0.009
Neg logit contributions
retty-0.013
emouth-0.012
ergus-0.011
idth-0.011
edom-0.011
Token-
Token ID12
Feature activation+2.08e-01

Pos logit contributions
 Ake+0.019
 Scand+0.018
ewski+0.017
do+0.017
arov+0.016
Neg logit contributions
retty-0.024
emouth-0.022
ergus-0.021
idth-0.020
edom-0.020
Token and
Token ID290
Feature activation+2.44e-02

Pos logit contributions
 Ake+0.143
 Scand+0.137
ewski+0.129
do+0.124
arov+0.121
Neg logit contributions
retty-0.172
emouth-0.155
ergus-0.147
idth-0.144
edom-0.141
Token and
Token ID290
Feature activation+2.00e-01

Pos logit contributions
 Ake+0.334
 Scand+0.320
ewski+0.300
do+0.288
arov+0.280
Neg logit contributions
retty-0.404
emouth-0.366
ergus-0.347
idth-0.338
edom-0.332
Token running
Token ID2491
Feature activation-1.98e-02

Pos logit contributions
 Ake+0.153
 Scand+0.147
ewski+0.139
do+0.134
arov+0.131
Neg logit contributions
retty-0.150
emouth-0.134
ergus-0.126
idth-0.122
edom-0.120
Token back
Token ID736
Feature activation+2.91e-01

Pos logit contributions
retty+0.015
emouth+0.013
ergus+0.013
idth+0.012
edom+0.012
Neg logit contributions
 Ake-0.015
 Scand-0.014
ewski-0.014
do-0.013
arov-0.013
Token Sam
Token ID3409
Feature activation+4.25e-01

Pos logit contributions
 Ake+0.203
 Scand+0.195
ewski+0.184
do+0.176
arov+0.172
Neg logit contributions
retty-0.237
emouth-0.213
ergus-0.202
idth-0.197
edom-0.193
Tokenaj
Token ID1228
Feature activation+8.15e-01

Pos logit contributions
 Ake+0.298
 Scand+0.286
ewski+0.269
do+0.258
arov+0.252
Neg logit contributions
retty-0.344
emouth-0.310
ergus-0.294
idth-0.287
edom-0.281
Tokene
Token ID68
Feature activation+1.83e+00

Pos logit contributions
 Ake+0.536
 Scand+0.514
ewski+0.480
do+0.458
arov+0.445
Neg logit contributions
retty-0.693
emouth-0.630
ergus-0.600
idth-0.587
edom-0.577
Token Per
Token ID2448
Feature activation+3.72e-01

Pos logit contributions
 Ake+1.653
 Scand+1.597
ewski+1.542
do+1.488
arov+1.459
Neg logit contributions
retty-1.094
emouth-0.944
ergus-0.904
idth-0.854
 PID-0.838
Tokenine
Token ID500
Feature activation+4.87e-01

Pos logit contributions
 Ake+0.255
 Scand+0.243
ewski+0.229
do+0.219
arov+0.214
Neg logit contributions
retty-0.308
emouth-0.278
ergus-0.263
idth-0.257
edom-0.252
Token lead
Token ID1085
Feature activation-6.51e-02

Pos logit contributions
 Ake+0.346
 Scand+0.332
ewski+0.313
do+0.300
arov+0.292
Neg logit contributions
retty-0.390
emouth-0.352
ergus-0.333
idth-0.324
edom-0.318
Token through
Token ID832
Feature activation-4.92e-01

Pos logit contributions
retty+0.053
emouth+0.048
ergus+0.045
idth+0.044
edom+0.043
Neg logit contributions
 Ake-0.046
 Scand-0.044
ewski-0.041
do-0.039
arov-0.038
Token the
Token ID262
Feature activation-5.52e-01

Pos logit contributions
retty+0.401
emouth+0.361
ergus+0.342
idth+0.334
edom+0.327
Neg logit contributions
 Ake-0.345
 Scand-0.331
ewski-0.310
do-0.298
arov-0.289
Tokenler
Token ID1754
Feature activation+1.63e-01

Pos logit contributions
retty+0.837
emouth+0.733
ergus+0.686
idth+0.671
edom+0.645
Neg logit contributions
 Ake-1.053
 Scand-1.015
ewski-0.965
do-0.945
der-0.920
Token (
Token ID357
Feature activation+3.47e-01

Pos logit contributions
 Ake+0.120
 Scand+0.115
ewski+0.109
do+0.104
arov+0.102
Neg logit contributions
retty-0.126
emouth-0.114
ergus-0.107
idth-0.104
edom-0.102
TokenGar
Token ID27676
Feature activation-1.64e-01

Pos logit contributions
 Ake+0.239
 Scand+0.228
ewski+0.215
do+0.206
arov+0.201
Neg logit contributions
retty-0.285
emouth-0.258
ergus-0.245
idth-0.238
edom-0.234
Tokenmin
Token ID1084
Feature activation+2.71e-01

Pos logit contributions
retty+0.126
emouth+0.113
ergus+0.106
idth+0.103
edom+0.101
Neg logit contributions
 Ake-0.122
 Scand-0.118
ewski-0.111
do-0.107
arov-0.104
Token-
Token ID12
Feature activation-1.53e-01

Pos logit contributions
 Ake+0.184
 Scand+0.175
ewski+0.165
do+0.158
arov+0.154
Neg logit contributions
retty-0.226
emouth-0.205
ergus-0.194
idth-0.190
edom-0.186
TokenC
Token ID34
Feature activation+1.81e+00

Pos logit contributions
retty+0.114
emouth+0.101
ergus+0.095
idth+0.093
edom+0.091
Neg logit contributions
 Ake-0.119
 Scand-0.114
ewski-0.108
do-0.104
arov-0.102
Tokener
Token ID263
Feature activation+4.40e-01

Pos logit contributions
 Ake+1.542
 Scand+1.482
ewski+1.414
do+1.357
+1.323
Neg logit contributions
retty-1.198
emouth-1.056
ergus-0.992
idth-0.951
edom-0.933
Tokenvel
Token ID626
Feature activation+8.17e-01

Pos logit contributions
 Ake+0.298
 Scand+0.285
ewski+0.267
do+0.255
arov+0.249
Neg logit contributions
retty-0.368
emouth-0.333
ergus-0.316
idth-0.308
edom-0.302
Tokeno
Token ID78
Feature activation+2.40e-01

Pos logit contributions
 Ake+0.572
 Scand+0.548
ewski+0.519
do+0.493
arov+0.484
Neg logit contributions
retty-0.662
emouth-0.599
ergus-0.567
idth-0.551
edom-0.542
Token)
Token ID8
Feature activation+5.83e-01

Pos logit contributions
 Ake+0.164
 Scand+0.157
ewski+0.148
do+0.141
arov+0.138
Neg logit contributions
retty-0.199
emouth-0.180
ergus-0.171
idth-0.166
edom-0.163
Token s
Token ID264
Feature activation+2.99e-01

Pos logit contributions
 Ake+0.365
 Scand+0.348
ewski+0.326
do+0.311
arov+0.302
Neg logit contributions
retty-0.516
emouth-0.470
ergus-0.448
idth-0.437
edom-0.429
Token-
Token ID12
Feature activation-5.91e-01

Pos logit contributions
retty+0.366
emouth+0.330
ergus+0.313
idth+0.305
edom+0.299
Neg logit contributions
 Ake-0.310
 Scand-0.297
ewski-0.279
do-0.269
arov-0.261
Tokenk
Token ID74
Feature activation+6.19e-01

Pos logit contributions
retty+0.407
emouth+0.360
ergus+0.336
idth+0.327
edom+0.318
Neg logit contributions
 Ake-0.489
 Scand-0.471
ewski-0.448
do-0.436
arov-0.423
Tokenings
Token ID654
Feature activation-1.59e-01

Pos logit contributions
 Ake+0.480
 Scand+0.462
ewski+0.437
do+0.419
arov+0.411
Neg logit contributions
retty-0.457
emouth-0.409
ergus-0.385
idth-0.373
edom-0.366
Token,
Token ID11
Feature activation-1.87e-01

Pos logit contributions
retty+0.131
emouth+0.118
ergus+0.112
idth+0.109
edom+0.107
Neg logit contributions
 Ake-0.110
 Scand-0.105
ewski-0.099
do-0.095
arov-0.092
Token Watts
Token ID27555
Feature activation-2.42e-02

Pos logit contributions
retty+0.153
emouth+0.138
ergus+0.131
idth+0.127
edom+0.125
Neg logit contributions
 Ake-0.131
 Scand-0.125
ewski-0.118
do-0.113
arov-0.110
TokenUp
Token ID4933
Feature activation+1.77e+00

Pos logit contributions
retty+0.020
emouth+0.018
ergus+0.017
idth+0.016
edom+0.016
Neg logit contributions
 Ake-0.017
 Scand-0.016
ewski-0.015
do-0.015
arov-0.014
TokenWith
Token ID3152
Feature activation+7.53e-02

Pos logit contributions
 Ake+1.319
 Scand+1.274
ewski+1.204
arov+1.128
do+1.126
Neg logit contributions
retty-1.361
emouth-1.221
ergus-1.155
idth-1.121
edom-1.104
TokenThat
Token ID2504
Feature activation+2.54e-01

Pos logit contributions
 Ake+0.049
 Scand+0.047
ewski+0.044
do+0.042
arov+0.041
Neg logit contributions
retty-0.065
emouth-0.059
ergus-0.056
idth-0.054
edom-0.053
Token is
Token ID318
Feature activation-1.21e-03

Pos logit contributions
 Ake+0.175
 Scand+0.168
ewski+0.158
do+0.151
arov+0.147
Neg logit contributions
retty-0.210
emouth-0.190
ergus-0.180
idth-0.175
edom-0.172
Token now
Token ID783
Feature activation+1.91e-02

Pos logit contributions
retty+0.001
emouth+0.001
ergus+0.001
idth+0.001
edom+0.001
Neg logit contributions
 Ake-0.001
 Scand-0.001
ewski-0.001
do-0.001
arov-0.001
Token the
Token ID262
Feature activation+2.89e-02

Pos logit contributions
 Ake+0.014
 Scand+0.013
ewski+0.012
do+0.012
arov+0.011
Neg logit contributions
retty-0.015
emouth-0.014
ergus-0.013
idth-0.013
edom-0.013
Tokeni
Token ID72
Feature activation-3.46e-02

Pos logit contributions
retty+0.428
emouth+0.385
ergus+0.363
idth+0.356
edom+0.347
Neg logit contributions
 Ake-0.389
 Scand-0.376
ewski-0.353
do-0.340
arov-0.331
Token (
Token ID357
Feature activation+2.07e-01

Pos logit contributions
retty+0.027
emouth+0.024
ergus+0.023
idth+0.022
edom+0.022
Neg logit contributions
 Ake-0.025
 Scand-0.024
ewski-0.023
do-0.022
arov-0.022
TokenAg
Token ID10262
Feature activation+5.27e-01

Pos logit contributions
 Ake+0.138
 Scand+0.131
ewski+0.123
do+0.118
arov+0.115
Neg logit contributions
retty-0.176
emouth-0.160
ergus-0.152
idth-0.148
edom-0.145
Token2
Token ID17
Feature activation+5.52e-01

Pos logit contributions
 Ake+0.316
 Scand+0.300
ewski+0.279
do+0.263
arov+0.256
Neg logit contributions
retty-0.482
emouth-0.439
ergus-0.420
idth-0.410
edom-0.402
Tokenr
Token ID81
Feature activation+1.38e+00

Pos logit contributions
 Ake+0.469
 Scand+0.453
ewski+0.432
do+0.416
arov+0.407
Neg logit contributions
retty-0.365
emouth-0.321
ergus-0.301
idth-0.291
edom-0.284
Token-
Token ID12
Feature activation+1.75e+00

Pos logit contributions
 Ake+0.934
 Scand+0.898
ewski+0.852
do+0.811
arov+0.797
Neg logit contributions
retty-1.137
emouth-1.029
ergus-0.976
idth-0.955
 PID-0.938
TokenLa
Token ID14772
Feature activation+3.21e-01

Pos logit contributions
 Ake+1.168
 Scand+1.107
ewski+1.056
do+0.990
arov+0.979
Neg logit contributions
retty-1.466
emouth-1.320
ergus-1.282
idth-1.238
edom-1.221
Token Mond
Token ID27328
Feature activation+6.47e-01

Pos logit contributions
 Ake+0.247
 Scand+0.237
ewski+0.225
do+0.216
arov+0.211
Neg logit contributions
retty-0.239
emouth-0.214
ergus-0.202
idth-0.195
edom-0.192
Tokenial
Token ID498
Feature activation-4.73e-01

Pos logit contributions
 Ake+0.328
 Scand+0.309
ewski+0.283
do+0.266
arov+0.254
Neg logit contributions
retty-0.650
emouth-0.602
ergus-0.577
idth-0.561
edom-0.555
Tokene
Token ID68
Feature activation+2.44e-01

Pos logit contributions
retty+0.418
emouth+0.378
ergus+0.360
idth+0.353
edom+0.345
Neg logit contributions
 Ake-0.301
 Scand-0.287
ewski-0.266
do-0.257
arov-0.246
Token)
Token ID8
Feature activation+6.27e-01

Pos logit contributions
 Ake+0.168
 Scand+0.160
ewski+0.151
do+0.145
arov+0.141
Neg logit contributions
retty-0.202
emouth-0.183
ergus-0.173
idth-0.169
edom-0.165
Token Fuj
Token ID32671
Feature activation+4.57e-02

Pos logit contributions
retty+0.011
emouth+0.010
ergus+0.009
idth+0.009
edom+0.009
Neg logit contributions
 Ake-0.010
 Scand-0.009
ewski-0.009
do-0.008
arov-0.008
Tokenita
Token ID5350
Feature activation+2.65e-01

Pos logit contributions
 Ake+0.027
 Scand+0.025
ewski+0.023
do+0.022
arov+0.022
Neg logit contributions
retty-0.043
emouth-0.039
ergus-0.037
idth-0.036
edom-0.036
Token,
Token ID11
Feature activation+1.67e-01

Pos logit contributions
 Ake+0.181
 Scand+0.174
ewski+0.163
do+0.157
arov+0.153
Neg logit contributions
retty-0.219
emouth-0.198
ergus-0.188
idth-0.183
edom-0.180
Token H
Token ID367
Feature activation+3.40e-02

Pos logit contributions
 Ake+0.115
 Scand+0.110
ewski+0.104
do+0.099
arov+0.097
Neg logit contributions
retty-0.138
emouth-0.125
ergus-0.118
idth-0.115
edom-0.113
Tokenarg
Token ID853
Feature activation+5.55e-01

Pos logit contributions
 Ake+0.025
 Scand+0.024
ewski+0.023
do+0.022
arov+0.022
Neg logit contributions
retty-0.026
emouth-0.024
ergus-0.022
idth-0.022
edom-0.021
Tokenro
Token ID305
Feature activation+1.75e+00

Pos logit contributions
 Ake+0.415
 Scand+0.399
ewski+0.377
do+0.362
arov+0.353
Neg logit contributions
retty-0.425
emouth-0.383
ergus-0.360
idth-0.350
edom-0.344
Tokenve
Token ID303
Feature activation+3.28e-01

Pos logit contributions
 Ake+1.022
 Scand+0.974
ewski+0.899
arov+0.837
do+0.832
Neg logit contributions
retty-1.605
emouth-1.470
ergus-1.419
idth-1.376
edom-1.363
Token,
Token ID11
Feature activation+8.86e-02

Pos logit contributions
 Ake+0.227
 Scand+0.217
ewski+0.204
do+0.196
arov+0.191
Neg logit contributions
retty-0.269
emouth-0.243
ergus-0.230
idth-0.224
edom-0.220
Token Smith
Token ID4176
Feature activation+3.14e-01

Pos logit contributions
 Ake+0.062
 Scand+0.059
ewski+0.056
do+0.053
arov+0.052
Neg logit contributions
retty-0.072
emouth-0.065
ergus-0.062
idth-0.060
edom-0.059
Token)
Token ID8
Feature activation+2.36e-01

Pos logit contributions
 Ake+0.217
 Scand+0.208
ewski+0.196
do+0.188
arov+0.183
Neg logit contributions
retty-0.258
emouth-0.233
ergus-0.220
idth-0.215
edom-0.211
Token v
Token ID410
Feature activation-1.61e-01

Pos logit contributions
 Ake+0.151
 Scand+0.144
ewski+0.135
do+0.129
arov+0.125
Neg logit contributions
retty-0.205
emouth-0.187
ergus-0.178
idth-0.173
edom-0.170
Token own
Token ID898
Feature activation+3.23e-01

Pos logit contributions
 Ake+0.803
 Scand+0.772
ewski+0.728
do+0.685
arov+0.677
Neg logit contributions
retty-0.946
emouth-0.865
ergus-0.814
idth-0.790
edom-0.774
Token and
Token ID290
Feature activation+3.32e-01

Pos logit contributions
 Ake+0.224
 Scand+0.215
ewski+0.202
do+0.193
arov+0.189
Neg logit contributions
retty-0.265
emouth-0.240
ergus-0.227
idth-0.221
edom-0.217
Token do
Token ID466
Feature activation-4.31e-03

Pos logit contributions
 Ake+0.243
 Scand+0.233
ewski+0.220
do+0.211
arov+0.207
Neg logit contributions
retty-0.259
emouth-0.233
ergus-0.219
idth-0.213
edom-0.209
Token not
Token ID407
Feature activation+8.57e-01

Pos logit contributions
retty+0.003
emouth+0.003
ergus+0.003
idth+0.003
edom+0.003
Neg logit contributions
 Ake-0.003
 Scand-0.003
ewski-0.003
do-0.003
arov-0.003
Token represent
Token ID2380
Feature activation+9.78e-01

Pos logit contributions
 Ake+0.591
 Scand+0.565
ewski+0.535
do+0.510
arov+0.502
Neg logit contributions
retty-0.699
emouth-0.635
ergus-0.601
idth-0.585
edom-0.576
Token the
Token ID262
Feature activation+1.75e+00

Pos logit contributions
 Ake+0.699
 Scand+0.670
ewski+0.637
do+0.610
arov+0.599
Neg logit contributions
retty-0.770
emouth-0.700
ergus-0.658
idth-0.634
edom-0.631
Token views
Token ID5009
Feature activation+8.56e-01

Pos logit contributions
 Ake+1.051
 Scand+1.008
ewski+0.937
do+0.880
arov+0.873
Neg logit contributions
retty-1.591
emouth-1.456
ergus-1.392
idth-1.358
edom-1.340
Token of
Token ID286
Feature activation-1.34e-01

Pos logit contributions
 Ake+0.622
 Scand+0.598
ewski+0.561
do+0.539
arov+0.527
Neg logit contributions
retty-0.671
emouth-0.604
ergus-0.571
idth-0.556
edom-0.545
Token Town
Token ID8329
Feature activation-2.32e-01

Pos logit contributions
retty+0.090
emouth+0.079
ergus+0.074
idth+0.072
edom+0.070
Neg logit contributions
 Ake-0.113
 Scand-0.109
ewski-0.104
do-0.101
arov-0.098
Tokenhall
Token ID18323
Feature activation+9.42e-01

Pos logit contributions
retty+0.170
emouth+0.151
ergus+0.142
idth+0.139
edom+0.135
Neg logit contributions
 Ake-0.182
 Scand-0.175
ewski-0.166
do-0.160
arov-0.156
Token.
Token ID13
Feature activation-1.66e+00

Pos logit contributions
 Ake+0.693
 Scand+0.661
ewski+0.629
do+0.600
arov+0.592
Neg logit contributions
retty-0.732
emouth-0.656
ergus-0.621
idth-0.600
edom-0.589
Token
Token ID447
Feature activation-1.40e-01

Pos logit contributions
 Ake+0.109
 Scand+0.105
ewski+0.098
do+0.094
arov+0.092
Neg logit contributions
retty-0.125
emouth-0.113
ergus-0.107
idth-0.104
edom-0.102
Token
Token ID251
Feature activation+2.75e-02

Pos logit contributions
retty+0.114
emouth+0.103
ergus+0.097
idth+0.095
edom+0.093
Neg logit contributions
 Ake-0.098
 Scand-0.094
ewski-0.088
do-0.084
arov-0.082
Token bloggers
Token ID30357
Feature activation-1.52e-01

Pos logit contributions
 Ake+0.020
 Scand+0.020
ewski+0.019
do+0.018
arov+0.017
Neg logit contributions
retty-0.021
emouth-0.019
ergus-0.018
idth-0.017
edom-0.017
Token like
Token ID588
Feature activation+6.84e-02

Pos logit contributions
retty+0.116
emouth+0.104
ergus+0.098
idth+0.095
edom+0.093
Neg logit contributions
 Ake-0.114
 Scand-0.110
ewski-0.104
do-0.100
arov-0.098
Token John
Token ID1757
Feature activation-3.02e-01

Pos logit contributions
 Ake+0.047
 Scand+0.045
ewski+0.043
do+0.041
arov+0.040
Neg logit contributions
retty-0.056
emouth-0.051
ergus-0.048
idth-0.047
edom-0.046
Token Scal
Token ID34529
Feature activation+1.75e+00

Pos logit contributions
retty+0.250
emouth+0.226
ergus+0.214
idth+0.209
edom+0.205
Neg logit contributions
 Ake-0.207
 Scand-0.199
ewski-0.186
do-0.179
arov-0.174
Tokenzi
Token ID17027
Feature activation-3.24e-02

Pos logit contributions
 Ake+1.534
 Scand+1.488
ewski+1.402
do+1.340
+1.337
Neg logit contributions
retty-1.108
emouth-0.972
ergus-0.915
idth-0.864
edom-0.863
Token
Token ID960
Feature activation-1.83e-01

Pos logit contributions
retty+0.025
emouth+0.022
ergus+0.021
idth+0.020
edom+0.020
Neg logit contributions
 Ake-0.024
 Scand-0.023
ewski-0.022
do-0.021
arov-0.021
Tokenfrom
Token ID6738
Feature activation-5.69e-02

Pos logit contributions
retty+0.143
emouth+0.128
ergus+0.121
idth+0.118
edom+0.116
Neg logit contributions
 Ake-0.134
 Scand-0.129
ewski-0.122
do-0.117
arov-0.114
Token ever
Token ID1683
Feature activation+8.86e-02

Pos logit contributions
retty+0.044
emouth+0.040
ergus+0.038
idth+0.037
edom+0.036
Neg logit contributions
 Ake-0.042
 Scand-0.040
ewski-0.038
do-0.036
arov-0.035
Token sweeping
Token ID18404
Feature activation-2.89e-01

Pos logit contributions
 Ake+0.064
 Scand+0.062
ewski+0.058
do+0.056
arov+0.054
Neg logit contributions
retty-0.070
emouth-0.063
ergus-0.059
idth-0.058
edom-0.057
Tokenian
Token ID666
Feature activation-1.42e-01

Pos logit contributions
retty+0.274
emouth+0.235
ergus+0.216
idth+0.208
edom+0.201
Neg logit contributions
 Ake-0.460
 Scand-0.446
ewski-0.427
do-0.417
arov-0.408
Token.
Token ID13
Feature activation-5.62e-01

Pos logit contributions
retty+0.114
emouth+0.103
ergus+0.097
idth+0.095
edom+0.093
Neg logit contributions
 Ake-0.101
 Scand-0.097
ewski-0.091
do-0.088
arov-0.085
Tokencom
Token ID785
Feature activation-5.45e-02

Pos logit contributions
retty+0.341
emouth+0.295
ergus+0.273
idth+0.265
edom+0.255
Neg logit contributions
 Ake-0.511
 Scand-0.495
ewski-0.473
do-0.460
arov-0.448
Token or
Token ID393
Feature activation-1.55e+00

Pos logit contributions
retty+0.045
emouth+0.041
ergus+0.039
idth+0.038
edom+0.037
Neg logit contributions
 Ake-0.037
 Scand-0.036
ewski-0.034
do-0.032
arov-0.031
Token call
Token ID869
Feature activation+3.94e-01

Pos logit contributions
retty+1.207
emouth+1.097
idth+1.013
ergus+1.009
edom+0.989
Neg logit contributions
 Ake-1.133
 Scand-1.102
ewski-1.029
do-1.014
arov-0.973
Token 03
Token ID7643
Feature activation+1.73e+00

Pos logit contributions
 Ake+0.263
 Scand+0.252
ewski+0.237
do+0.226
arov+0.220
Neg logit contributions
retty-0.333
emouth-0.301
ergus-0.286
idth-0.278
edom-0.274
Token30
Token ID1270
Feature activation+1.05e+00

Pos logit contributions
 Ake+1.001
 Scand+0.951
ewski+0.891
do+0.828
arov+0.811
Neg logit contributions
retty-1.604
emouth-1.462
ergus-1.393
idth-1.369
edom-1.360
Token 333
Token ID23460
Feature activation+1.09e+00

Pos logit contributions
 Ake+0.637
 Scand+0.606
ewski+0.569
do+0.536
arov+0.529
Neg logit contributions
retty-0.942
emouth-0.864
ergus-0.825
idth-0.807
edom-0.792
Token 68
Token ID8257
Feature activation+1.11e+00

Pos logit contributions
 Ake+0.799
 Scand+0.770
ewski+0.730
do+0.699
arov+0.688
Neg logit contributions
retty-0.835
emouth-0.751
ergus-0.712
idth-0.692
edom-0.679
Token46
Token ID3510
Feature activation+7.27e-01

Pos logit contributions
 Ake+0.899
 Scand+0.862
ewski+0.828
do+0.792
arov+0.782
Neg logit contributions
retty-0.774
emouth-0.682
ergus-0.646
idth-0.626
edom-0.618
Token.
Token ID13
Feature activation+3.43e-01

Pos logit contributions
 Ake+0.528
 Scand+0.507
ewski+0.479
do+0.457
arov+0.449
Neg logit contributions
retty-0.572
emouth-0.514
ergus-0.487
idth-0.472
edom-0.464
Token link
Token ID2792
Feature activation+1.29e+00

Pos logit contributions
 Ake+0.882
 Scand+0.848
ewski+0.804
do+0.765
arov+0.756
Neg logit contributions
retty-0.921
emouth-0.823
ergus-0.786
idth-0.755
edom-0.751
Token for
Token ID329
Feature activation-1.19e+00

Pos logit contributions
 Ake+0.916
 Scand+0.888
ewski+0.842
do+0.795
arov+0.791
Neg logit contributions
retty-1.021
emouth-0.922
ergus-0.876
idth-0.847
edom-0.830
Token buying
Token ID7067
Feature activation-5.76e-01

Pos logit contributions
retty+1.020
emouth+0.932
ergus+0.881
idth+0.867
 PID+0.841
Neg logit contributions
 Ake-0.773
 Scand-0.744
ewski-0.685
do-0.672
der-0.642
Token the
Token ID262
Feature activation-1.97e+00

Pos logit contributions
retty+0.479
emouth+0.433
ergus+0.410
idth+0.402
edom+0.391
Neg logit contributions
 Ake-0.395
 Scand-0.380
ewski-0.353
do-0.341
arov-0.331
Token second
Token ID1218
Feature activation-9.96e-01

Pos logit contributions
retty+1.654
emouth+1.488
ergus+1.412
idth+1.404
 PID+1.345
Neg logit contributions
 Ake-1.362
 Scand-1.302
ewski-1.187
do-1.170
arov-1.132
Token edition
Token ID8313
Feature activation-2.66e+00

Pos logit contributions
retty+0.689
emouth+0.605
ergus+0.572
idth+0.559
edom+0.534
Neg logit contributions
 Ake-0.827
 Scand-0.797
ewski-0.744
do-0.736
arov-0.714
Token of
Token ID286
Feature activation-1.40e+00

Pos logit contributions
retty+2.320
emouth+2.097
ergus+2.039
idth+2.014
edom+1.962
Neg logit contributions
 Ake-1.716
 Scand-1.613
ewski-1.491
do-1.480
arov-1.420
Token my
Token ID616
Feature activation-1.50e+00

Pos logit contributions
retty+1.176
emouth+1.067
ergus+1.012
idth+0.999
edom+0.976
Neg logit contributions
 Ake-0.939
 Scand-0.897
ewski-0.830
do-0.812
arov-0.781
Token 1993
Token ID9656
Feature activation+4.47e-02

Pos logit contributions
retty+1.388
emouth+1.261
ergus+1.206
idth+1.201
edom+1.164
Neg logit contributions
 Ake-0.883
 Scand-0.847
ewski-0.773
do-0.746
arov-0.714
Token book
Token ID1492
Feature activation+5.10e-02

Pos logit contributions
 Ake+0.033
 Scand+0.032
ewski+0.030
do+0.029
arov+0.028
Neg logit contributions
retty-0.035
emouth-0.031
ergus-0.029
idth-0.028
edom-0.028
Token,
Token ID11
Feature activation-1.04e+00

Pos logit contributions
 Ake+0.035
 Scand+0.034
ewski+0.032
do+0.030
arov+0.030
Neg logit contributions
retty-0.042
emouth-0.038
ergus-0.036
idth-0.035
edom-0.034
Token takes
Token ID2753
Feature activation-3.95e-01

Pos logit contributions
retty+1.191
emouth+1.069
ergus+1.007
idth+0.986
edom+0.950
Neg logit contributions
 Ake-1.083
 Scand-1.030
ewski-0.968
do-0.936
der-0.906
Token steps
Token ID4831
Feature activation-4.56e-01

Pos logit contributions
retty+0.358
emouth+0.327
ergus+0.311
idth+0.305
edom+0.299
Neg logit contributions
 Ake-0.240
 Scand-0.230
ewski-0.212
do-0.203
arov-0.196
Token to
Token ID284
Feature activation-1.54e+00

Pos logit contributions
retty+0.390
emouth+0.352
ergus+0.335
idth+0.327
edom+0.319
Neg logit contributions
 Ake-0.304
 Scand-0.290
ewski-0.272
do-0.259
arov-0.253
Token open
Token ID1280
Feature activation-7.18e-01

Pos logit contributions
retty+1.209
emouth+1.083
ergus+1.021
idth+1.004
edom+0.960
Neg logit contributions
 Ake-1.141
 Scand-1.100
ewski-1.019
do-1.003
arov-0.960
Token flights
Token ID13956
Feature activation-1.68e+00

Pos logit contributions
retty+0.604
emouth+0.544
ergus+0.518
idth+0.505
edom+0.493
Neg logit contributions
 Ake-0.481
 Scand-0.466
ewski-0.437
do-0.416
der-0.403
Token to
Token ID284
Feature activation-2.52e+00

Pos logit contributions
retty+1.494
emouth+1.366
ergus+1.287
idth+1.269
edom+1.229
Neg logit contributions
 Ake-1.061
 Scand-1.020
ewski-0.940
do-0.900
arov-0.879
Token US
Token ID1294
Feature activation+2.94e-01

Pos logit contributions
retty+2.330
emouth+2.086
ergus+1.970
idth+1.957
edom+1.883
Neg logit contributions
 Ake-1.528
 Scand-1.518
ewski-1.336
do-1.324
arov-1.259
Token on
Token ID319
Feature activation-9.08e-02

Pos logit contributions
 Ake+0.195
 Scand+0.186
ewski+0.175
do+0.167
arov+0.163
Neg logit contributions
retty-0.250
emouth-0.227
ergus-0.216
idth-0.210
edom-0.207
Token sidelines
Token ID29394
Feature activation-2.25e-01

Pos logit contributions
retty+0.077
emouth+0.069
ergus+0.066
idth+0.064
edom+0.063
Neg logit contributions
 Ake-0.061
 Scand-0.058
ewski-0.054
do-0.052
arov-0.051
Token of
Token ID286
Feature activation-2.04e+00

Pos logit contributions
retty+0.182
emouth+0.164
ergus+0.155
idth+0.151
edom+0.148
Neg logit contributions
 Ake-0.159
 Scand-0.153
ewski-0.144
do-0.138
arov-0.134
Token Trump
Token ID1301
Feature activation-1.59e+00

Pos logit contributions
retty+1.760
emouth+1.558
ergus+1.482
idth+1.414
edom+1.398
Neg logit contributions
 Ake-1.388
 Scand-1.338
do-1.208
ewski-1.206
der-1.145
Token Big
Token ID4403
Feature activation-7.29e-01

Pos logit contributions
retty+0.442
emouth+0.399
ergus+0.377
idth+0.368
edom+0.361
Neg logit contributions
 Ake-0.385
 Scand-0.370
ewski-0.345
do-0.333
arov-0.323
Token Bang
Token ID9801
Feature activation+1.67e-01

Pos logit contributions
retty+0.480
emouth+0.424
ergus+0.395
idth+0.382
edom+0.375
Neg logit contributions
 Ake-0.624
 Scand-0.602
ewski-0.572
do-0.557
arov-0.541
Token Theory
Token ID17003
Feature activation+1.70e-01

Pos logit contributions
 Ake+0.069
 Scand+0.064
ewski+0.057
do+0.053
arov+0.050
Neg logit contributions
retty-0.184
emouth-0.171
ergus-0.164
idth-0.161
edom-0.159
Token CBS
Token ID11133
Feature activation-2.44e-02

Pos logit contributions
 Ake+0.113
 Scand+0.108
ewski+0.101
do+0.097
arov+0.094
Neg logit contributions
retty-0.144
emouth-0.130
ergus-0.124
idth-0.121
edom-0.118
Token Amy
Token ID14235
Feature activation-1.09e-01

Pos logit contributions
retty+0.020
emouth+0.018
ergus+0.017
idth+0.017
edom+0.016
Neg logit contributions
 Ake-0.017
 Scand-0.016
ewski-0.015
do-0.015
arov-0.014
Token Poe
Token ID34815
Feature activation-2.48e+00

Pos logit contributions
retty+0.085
emouth+0.076
ergus+0.072
idth+0.070
edom+0.069
Neg logit contributions
 Ake-0.081
 Scand-0.078
ewski-0.073
do-0.070
arov-0.069
Tokenhler
Token ID49737
Feature activation+2.96e-02

Pos logit contributions
retty+1.746
emouth+1.582
ergus+1.453
idth+1.398
edom+1.380
Neg logit contributions
 Ake-2.044
 Scand-1.964
ewski-1.850
do-1.791
der-1.772
Token Parks
Token ID20604
Feature activation-3.43e-01

Pos logit contributions
 Ake+0.020
 Scand+0.020
ewski+0.018
do+0.018
arov+0.017
Neg logit contributions
retty-0.024
emouth-0.022
ergus-0.021
idth-0.020
edom-0.020
Token and
Token ID290
Feature activation-1.14e+00

Pos logit contributions
retty+0.284
emouth+0.257
ergus+0.243
idth+0.237
edom+0.233
Neg logit contributions
 Ake-0.236
 Scand-0.226
ewski-0.212
do-0.203
arov-0.197
Token Recreation
Token ID34285
Feature activation+7.19e-02

Pos logit contributions
retty+0.889
emouth+0.794
ergus+0.752
idth+0.739
edom+0.718
Neg logit contributions
 Ake-0.849
 Scand-0.822
ewski-0.764
do-0.737
arov-0.724
Token NBC
Token ID9716
Feature activation+3.55e-02

Pos logit contributions
 Ake+0.047
 Scand+0.045
ewski+0.042
do+0.040
arov+0.039
Neg logit contributions
retty-0.062
emouth-0.056
ergus-0.053
idth-0.052
edom-0.051
Token
Token ID447
Feature activation-1.49e-01

Pos logit contributions
 Ake+0.159
 Scand+0.152
ewski+0.144
do+0.138
arov+0.135
Neg logit contributions
retty-0.162
emouth-0.146
ergus-0.137
idth-0.133
edom-0.131
Token
Token ID247
Feature activation-2.98e-01

Pos logit contributions
retty+0.122
emouth+0.110
ergus+0.105
idth+0.102
edom+0.100
Neg logit contributions
 Ake-0.103
 Scand-0.099
ewski-0.093
do-0.089
arov-0.087
Tokenve
Token ID303
Feature activation-2.37e-01

Pos logit contributions
retty+0.206
emouth+0.182
ergus+0.171
idth+0.166
edom+0.161
Neg logit contributions
 Ake-0.246
 Scand-0.237
ewski-0.226
do-0.219
arov-0.213
Token written
Token ID3194
Feature activation-8.51e-01

Pos logit contributions
retty+0.228
emouth+0.210
ergus+0.200
idth+0.196
edom+0.193
Neg logit contributions
 Ake-0.131
 Scand-0.124
ewski-0.114
do-0.108
arov-0.104
Token a
Token ID257
Feature activation-1.05e+00

Pos logit contributions
retty+0.699
emouth+0.635
ergus+0.601
idth+0.586
edom+0.576
Neg logit contributions
 Ake-0.588
 Scand-0.562
ewski-0.527
do-0.508
der-0.493
Token couple
Token ID3155
Feature activation-2.44e+00

Pos logit contributions
retty+0.896
emouth+0.813
ergus+0.771
idth+0.760
edom+0.745
Neg logit contributions
 Ake-0.695
 Scand-0.666
ewski-0.618
do-0.599
der-0.577
Token of
Token ID286
Feature activation-1.97e+00

Pos logit contributions
retty+2.106
emouth+1.920
idth+1.816
ergus+1.794
edom+1.748
Neg logit contributions
 Ake-1.589
 Scand-1.554
do-1.408
ewski-1.395
der-1.324
Token books
Token ID3835
Feature activation-9.89e-01

Pos logit contributions
retty+1.697
emouth+1.550
ergus+1.461
idth+1.442
edom+1.412
Neg logit contributions
 Ake-1.271
 Scand-1.239
ewski-1.140
do-1.116
der-1.065
Token,
Token ID11
Feature activation-7.30e-01

Pos logit contributions
retty+0.842
emouth+0.757
ergus+0.724
idth+0.709
edom+0.692
Neg logit contributions
 Ake-0.660
 Scand-0.629
ewski-0.592
do-0.573
der-0.552
Token which
Token ID543
Feature activation-8.60e-01

Pos logit contributions
retty+0.600
emouth+0.546
ergus+0.516
idth+0.507
edom+0.493
Neg logit contributions
 Ake-0.508
 Scand-0.485
ewski-0.452
do-0.441
arov-0.421
Token you
Token ID345
Feature activation+3.30e-01

Pos logit contributions
retty+0.786
emouth+0.716
ergus+0.688
idth+0.674
edom+0.656
Neg logit contributions
 Ake-0.515
 Scand-0.485
ewski-0.453
do-0.441
der-0.420
Token takes
Token ID2753
Feature activation-3.89e-01

Pos logit contributions
retty+1.183
emouth+1.062
ergus+1.001
idth+0.981
edom+0.943
Neg logit contributions
 Ake-1.068
 Scand-1.015
ewski-0.954
do-0.921
der-0.891
Token steps
Token ID4831
Feature activation-4.05e-01

Pos logit contributions
retty+0.353
emouth+0.322
ergus+0.307
idth+0.300
edom+0.294
Neg logit contributions
 Ake-0.237
 Scand-0.227
ewski-0.209
do-0.200
arov-0.194
Token to
Token ID284
Feature activation-1.68e+00

Pos logit contributions
retty+0.347
emouth+0.313
ergus+0.297
idth+0.290
edom+0.284
Neg logit contributions
 Ake-0.270
 Scand-0.258
ewski-0.242
do-0.231
arov-0.225
Token open
Token ID1280
Feature activation-8.38e-01

Pos logit contributions
retty+1.334
emouth+1.197
ergus+1.130
idth+1.111
edom+1.063
Neg logit contributions
 Ake-1.232
 Scand-1.188
ewski-1.099
do-1.083
arov-1.031
Token flights
Token ID13956
Feature activation-1.76e+00

Pos logit contributions
retty+0.711
emouth+0.640
ergus+0.611
idth+0.596
edom+0.581
Neg logit contributions
 Ake-0.555
 Scand-0.539
ewski-0.505
do-0.480
der-0.466
Token to
Token ID284
Feature activation-2.44e+00

Pos logit contributions
retty+1.569
emouth+1.437
ergus+1.354
idth+1.334
edom+1.292
Neg logit contributions
 Ake-1.096
 Scand-1.059
ewski-0.974
do-0.929
arov-0.910
Token US
Token ID1294
Feature activation+4.75e-01

Pos logit contributions
retty+2.234
emouth+1.998
ergus+1.888
idth+1.874
edom+1.806
Neg logit contributions
 Ake-1.495
 Scand-1.484
ewski-1.307
do-1.292
arov-1.232
Token on
Token ID319
Feature activation+4.13e-02

Pos logit contributions
 Ake+0.315
 Scand+0.301
ewski+0.282
do+0.269
arov+0.263
Neg logit contributions
retty-0.403
emouth-0.365
ergus-0.348
idth-0.339
edom-0.333
Token sidelines
Token ID29394
Feature activation-1.96e-01

Pos logit contributions
 Ake+0.028
 Scand+0.027
ewski+0.025
do+0.024
arov+0.023
Neg logit contributions
retty-0.035
emouth-0.031
ergus-0.030
idth-0.029
edom-0.029
Token of
Token ID286
Feature activation-2.03e+00

Pos logit contributions
retty+0.158
emouth+0.143
ergus+0.135
idth+0.132
edom+0.129
Neg logit contributions
 Ake-0.139
 Scand-0.133
ewski-0.125
do-0.120
arov-0.117
Token Trump
Token ID1301
Feature activation-1.66e+00

Pos logit contributions
retty+1.760
emouth+1.557
ergus+1.485
idth+1.415
edom+1.404
Neg logit contributions
 Ake-1.370
 Scand-1.323
do-1.194
ewski-1.190
arov-1.127
Token Ric
Token ID15868
Feature activation-1.25e+00

Pos logit contributions
 Ake+0.142
 Scand+0.135
ewski+0.126
do+0.120
arov+0.117
Neg logit contributions
retty-0.205
emouth-0.187
ergus-0.178
idth-0.174
edom-0.171
Tokenher
Token ID372
Feature activation+6.92e-01

Pos logit contributions
retty+0.902
emouth+0.807
ergus+0.747
idth+0.731
 PID+0.718
Neg logit contributions
 Ake-0.989
 Scand-0.955
ewski-0.920
do-0.885
der-0.871
Tokent
Token ID83
Feature activation-4.27e-01

Pos logit contributions
 Ake+0.444
 Scand+0.425
ewski+0.397
do+0.373
arov+0.369
Neg logit contributions
retty-0.603
emouth-0.547
ergus-0.521
idth-0.505
edom-0.499
Token and
Token ID290
Feature activation-1.51e+00

Pos logit contributions
retty+0.359
emouth+0.325
ergus+0.307
idth+0.301
edom+0.295
Neg logit contributions
 Ake-0.288
 Scand-0.277
ewski-0.260
do-0.249
arov-0.241
Token David
Token ID3271
Feature activation+1.03e-01

Pos logit contributions
retty+1.109
emouth+1.006
ergus+0.927
idth+0.907
edom+0.893
Neg logit contributions
 Ake-1.170
 Scand-1.130
ewski-1.062
do-1.038
der-1.011
Token Gordon
Token ID11646
Feature activation-2.36e+00

Pos logit contributions
 Ake+0.085
 Scand+0.082
ewski+0.078
do+0.075
arov+0.073
Neg logit contributions
retty-0.072
emouth-0.063
ergus-0.059
idth-0.058
edom-0.056
Token (
Token ID357
Feature activation-2.39e-01

Pos logit contributions
retty+1.973
emouth+1.787
ergus+1.676
idth+1.666
edom+1.618
Neg logit contributions
 Ake-1.641
 Scand-1.549
ewski-1.458
do-1.400
der-1.351
TokenIS
Token ID1797
Feature activation-7.27e-01

Pos logit contributions
retty+0.238
emouth+0.219
ergus+0.210
idth+0.205
edom+0.202
Neg logit contributions
 Ake-0.124
 Scand-0.117
ewski-0.107
do-0.102
arov-0.097
TokenI
Token ID40
Feature activation-1.08e-01

Pos logit contributions
retty+0.634
emouth+0.577
ergus+0.548
idth+0.538
edom+0.526
Neg logit contributions
 Ake-0.469
 Scand-0.443
ewski-0.416
do-0.402
der-0.388
Token Books
Token ID13661
Feature activation+2.55e-01

Pos logit contributions
retty+0.094
emouth+0.086
ergus+0.082
idth+0.080
edom+0.078
Neg logit contributions
 Ake-0.069
 Scand-0.066
ewski-0.061
do-0.059
arov-0.057
Token,
Token ID11
Feature activation+6.82e-01

Pos logit contributions
 Ake+0.177
 Scand+0.170
ewski+0.160
do+0.153
arov+0.150
Neg logit contributions
retty-0.208
emouth-0.188
ergus-0.178
idth-0.174
edom-0.170
Token WikiLeaks
Token ID19766
Feature activation+3.43e-01

Pos logit contributions
 Ake+0.525
 Scand+0.502
ewski+0.478
do+0.455
arov+0.443
Neg logit contributions
retty-0.602
emouth-0.544
ergus-0.520
idth-0.502
edom-0.493
Token about
Token ID546
Feature activation-8.72e-01

Pos logit contributions
 Ake+0.242
 Scand+0.232
ewski+0.219
do+0.209
arov+0.204
Neg logit contributions
retty-0.277
emouth-0.250
ergus-0.236
idth-0.230
edom-0.226
Token DNC
Token ID17824
Feature activation-5.49e-01

Pos logit contributions
retty+0.686
emouth+0.615
ergus+0.579
idth+0.567
edom+0.551
Neg logit contributions
 Ake-0.638
 Scand-0.614
ewski-0.577
do-0.557
arov-0.542
Token emails
Token ID7237
Feature activation-8.97e-01

Pos logit contributions
retty+0.446
emouth+0.401
ergus+0.379
idth+0.371
edom+0.362
Neg logit contributions
 Ake-0.388
 Scand-0.372
ewski-0.350
do-0.337
arov-0.327
Token Trump
Token ID1301
Feature activation-8.37e-01

Pos logit contributions
retty+0.739
emouth+0.668
ergus+0.631
idth+0.614
edom+0.602
Neg logit contributions
 Ake-0.625
 Scand-0.598
ewski-0.562
do-0.539
arov-0.526
Token urges
Token ID28804
Feature activation-2.26e+00

Pos logit contributions
retty+0.683
emouth+0.611
ergus+0.580
idth+0.568
edom+0.555
Neg logit contributions
 Ake-0.586
 Scand-0.563
ewski-0.532
do-0.510
arov-0.497
Token North
Token ID2258
Feature activation-4.42e-01

Pos logit contributions
retty+2.004
emouth+1.820
ergus+1.719
idth+1.690
edom+1.634
Neg logit contributions
 Ake-1.449
 Scand-1.401
ewski-1.287
do-1.240
arov-1.199
Token Korea
Token ID4969
Feature activation-9.23e-01

Pos logit contributions
retty+0.405
emouth+0.368
ergus+0.351
idth+0.343
edom+0.336
Neg logit contributions
 Ake-0.266
 Scand-0.253
ewski-0.234
do-0.225
arov-0.217
Token to
Token ID284
Feature activation-5.27e-01

Pos logit contributions
retty+0.801
emouth+0.720
ergus+0.689
idth+0.673
edom+0.656
Neg logit contributions
 Ake-0.605
 Scand-0.576
ewski-0.536
do-0.517
arov-0.499
Token den
Token ID2853
Feature activation-6.51e-01

Pos logit contributions
retty+0.421
emouth+0.380
ergus+0.358
idth+0.351
edom+0.342
Neg logit contributions
 Ake-0.378
 Scand-0.363
ewski-0.341
do-0.330
arov-0.318
Tokenuclear
Token ID4016
Feature activation-1.55e+00

Pos logit contributions
retty+0.432
emouth+0.380
ergus+0.352
idth+0.341
edom+0.332
Neg logit contributions
 Ake-0.557
 Scand-0.540
ewski-0.511
do-0.498
arov-0.486
Token a
Token ID257
Feature activation-2.98e-01

Pos logit contributions
 Ake+0.002
 Scand+0.002
ewski+0.001
do+0.001
arov+0.001
Neg logit contributions
retty-0.002
emouth-0.002
ergus-0.002
idth-0.001
edom-0.001
Token terrible
Token ID7818
Feature activation-4.80e-02

Pos logit contributions
retty+0.224
emouth+0.201
ergus+0.189
idth+0.184
edom+0.180
Neg logit contributions
 Ake-0.227
 Scand-0.219
ewski-0.206
do-0.199
arov-0.194
Token year
Token ID614
Feature activation+2.89e-02

Pos logit contributions
retty+0.038
emouth+0.034
ergus+0.032
idth+0.031
edom+0.031
Neg logit contributions
 Ake-0.035
 Scand-0.033
ewski-0.031
do-0.030
arov-0.029
Token for
Token ID329
Feature activation-1.28e-01

Pos logit contributions
 Ake+0.020
 Scand+0.019
ewski+0.018
do+0.017
arov+0.017
Neg logit contributions
retty-0.024
emouth-0.022
ergus-0.021
idth-0.020
edom-0.020
Token Tan
Token ID11818
Feature activation+5.77e-01

Pos logit contributions
retty+0.100
emouth+0.090
ergus+0.085
idth+0.082
edom+0.081
Neg logit contributions
 Ake-0.094
 Scand-0.091
ewski-0.085
do-0.082
arov-0.080
Tokenne
Token ID710
Feature activation-2.16e+00

Pos logit contributions
 Ake+0.387
 Scand+0.370
ewski+0.348
do+0.333
arov+0.323
Neg logit contributions
retty-0.485
emouth-0.441
ergus-0.417
idth-0.407
edom-0.401
Tokenhill
Token ID12639
Feature activation-2.05e-01

Pos logit contributions
retty+2.011
emouth+1.825
idth+1.725
ergus+1.717
 PID+1.647
Neg logit contributions
 Ake-1.284
 Scand-1.215
ewski-1.129
do-1.087
arov-1.055
Token and
Token ID290
Feature activation+2.23e-01

Pos logit contributions
retty+0.169
emouth+0.152
ergus+0.144
idth+0.141
edom+0.138
Neg logit contributions
 Ake-0.143
 Scand-0.137
ewski-0.128
do-0.123
arov-0.120
Token the
Token ID262
Feature activation-7.44e-02

Pos logit contributions
 Ake+0.159
 Scand+0.152
ewski+0.144
do+0.138
arov+0.135
Neg logit contributions
retty-0.178
emouth-0.161
ergus-0.152
idth-0.148
edom-0.145
Token Dolphins
Token ID21668
Feature activation-2.84e-01

Pos logit contributions
retty+0.060
emouth+0.055
ergus+0.052
idth+0.050
edom+0.049
Neg logit contributions
 Ake-0.052
 Scand-0.050
ewski-0.047
do-0.045
arov-0.044
Token,
Token ID11
Feature activation-2.91e-02

Pos logit contributions
retty+0.232
emouth+0.209
ergus+0.198
idth+0.193
edom+0.190
Neg logit contributions
 Ake-0.198
 Scand-0.190
ewski-0.178
do-0.171
arov-0.166
Token takes
Token ID2753
Feature activation-2.98e-01

Pos logit contributions
retty+1.152
emouth+1.038
ergus+0.982
idth+0.964
edom+0.930
Neg logit contributions
 Ake-0.925
 Scand-0.877
ewski-0.822
do-0.791
der-0.764
Token steps
Token ID4831
Feature activation-3.36e-01

Pos logit contributions
retty+0.269
emouth+0.245
ergus+0.233
idth+0.228
edom+0.224
Neg logit contributions
 Ake-0.182
 Scand-0.175
ewski-0.161
do-0.154
arov-0.150
Token to
Token ID284
Feature activation-1.76e+00

Pos logit contributions
retty+0.287
emouth+0.259
ergus+0.246
idth+0.240
edom+0.235
Neg logit contributions
 Ake-0.225
 Scand-0.215
ewski-0.201
do-0.192
arov-0.188
Token open
Token ID1280
Feature activation-8.44e-01

Pos logit contributions
retty+1.389
emouth+1.244
ergus+1.177
idth+1.156
edom+1.102
Neg logit contributions
 Ake-1.301
 Scand-1.260
ewski-1.166
do-1.146
arov-1.094
Token flights
Token ID13956
Feature activation-1.66e+00

Pos logit contributions
retty+0.713
emouth+0.641
ergus+0.611
idth+0.596
edom+0.580
Neg logit contributions
 Ake-0.563
 Scand-0.547
ewski-0.513
do-0.487
der-0.473
Token to
Token ID284
Feature activation-2.14e+00

Pos logit contributions
retty+1.473
emouth+1.346
ergus+1.269
idth+1.250
edom+1.211
Neg logit contributions
 Ake-1.047
 Scand-1.012
ewski-0.935
do-0.892
arov-0.872
Token US
Token ID1294
Feature activation+5.77e-01

Pos logit contributions
retty+1.954
emouth+1.766
ergus+1.665
idth+1.649
edom+1.594
Neg logit contributions
 Ake-1.308
 Scand-1.295
ewski-1.150
do-1.132
arov-1.083
Token on
Token ID319
Feature activation+3.72e-02

Pos logit contributions
 Ake+0.388
 Scand+0.371
ewski+0.348
do+0.331
arov+0.325
Neg logit contributions
retty-0.484
emouth-0.438
ergus-0.417
idth-0.407
edom-0.400
Token sidelines
Token ID29394
Feature activation-2.21e-01

Pos logit contributions
 Ake+0.025
 Scand+0.024
ewski+0.022
do+0.021
arov+0.021
Neg logit contributions
retty-0.031
emouth-0.028
ergus-0.027
idth-0.026
edom-0.026
Token of
Token ID286
Feature activation-1.87e+00

Pos logit contributions
retty+0.178
emouth+0.161
ergus+0.152
idth+0.148
edom+0.145
Neg logit contributions
 Ake-0.156
 Scand-0.150
ewski-0.141
do-0.136
arov-0.132
Token Trump
Token ID1301
Feature activation-1.21e+00

Pos logit contributions
retty+1.617
emouth+1.432
ergus+1.365
idth+1.305
edom+1.293
Neg logit contributions
 Ake-1.259
 Scand-1.215
do-1.098
ewski-1.097
der-1.037
Token MORE
Token ID12011
Feature activation-1.32e-01

Pos logit contributions
retty+0.990
emouth+0.891
ergus+0.833
idth+0.823
edom+0.806
Neg logit contributions
 Ake-0.865
 Scand-0.827
ewski-0.764
do-0.744
der-0.719
Token and
Token ID290
Feature activation-2.98e-01

Pos logit contributions
retty+0.109
emouth+0.099
ergus+0.094
idth+0.091
edom+0.089
Neg logit contributions
 Ake-0.091
 Scand-0.087
ewski-0.082
do-0.078
arov-0.076
Token Hillary
Token ID5073
Feature activation+3.15e-01

Pos logit contributions
retty+0.247
emouth+0.224
ergus+0.212
idth+0.207
edom+0.203
Neg logit contributions
 Ake-0.204
 Scand-0.195
ewski-0.183
do-0.176
arov-0.170
Token Clinton
Token ID2605
Feature activation+2.67e-01

Pos logit contributions
 Ake+0.171
 Scand+0.161
ewski+0.149
do+0.141
arov+0.136
Neg logit contributions
retty-0.306
emouth-0.281
ergus-0.269
idth-0.263
edom-0.259
Token Hillary
Token ID5073
Feature activation+9.71e-01

Pos logit contributions
 Ake+0.180
 Scand+0.172
ewski+0.162
do+0.155
arov+0.151
Neg logit contributions
retty-0.223
emouth-0.202
ergus-0.192
idth-0.187
edom-0.184
Token Diane
Token ID26542
Feature activation-2.14e+00

Pos logit contributions
 Ake+0.457
 Scand+0.431
ewski+0.393
do+0.371
arov+0.356
Neg logit contributions
retty-1.007
emouth-0.929
ergus-0.898
idth-0.879
 PID-0.864
Token Rodham
Token ID41848
Feature activation-7.97e-01

Pos logit contributions
retty+2.138
emouth+1.963
ergus+1.850
idth+1.820
edom+1.803
Neg logit contributions
 Ake-1.140
 Scand-1.081
ewski-0.979
do-0.922
der-0.910
Token Clinton
Token ID2605
Feature activation+1.02e-01

Pos logit contributions
retty+0.794
emouth+0.731
ergus+0.698
idth+0.685
edom+0.675
Neg logit contributions
 Ake-0.415
 Scand-0.389
ewski-0.359
do-0.340
der-0.325
TokenSanders
Token ID26747
Feature activation+9.87e-01

Pos logit contributions
 Ake+0.069
 Scand+0.066
ewski+0.062
do+0.060
arov+0.058
Neg logit contributions
retty-0.085
emouth-0.077
ergus-0.073
idth-0.071
edom-0.070
Token:
Token ID25
Feature activation-1.26e+00

Pos logit contributions
 Ake+0.738
 Scand+0.709
ewski+0.669
do+0.647
arov+0.632
Neg logit contributions
retty-0.759
emouth-0.676
ergus-0.640
idth-0.619
edom-0.611
Token '
Token ID705
Feature activation-8.06e-01

Pos logit contributions
retty+1.074
emouth+0.964
ergus+0.922
idth+0.899
edom+0.876
Neg logit contributions
 Ake-0.848
 Scand-0.804
ewski-0.747
do-0.713
arov-0.694
Token MORE
Token ID12011
Feature activation-1.52e-01

Pos logit contributions
 Ake+0.523
 Scand+0.501
ewski+0.478
do+0.456
arov+0.446
Neg logit contributions
retty-0.548
emouth-0.493
ergus-0.469
idth-0.453
 PID-0.445
Token and
Token ID290
Feature activation+1.36e-01

Pos logit contributions
retty+0.125
emouth+0.113
ergus+0.107
idth+0.105
edom+0.103
Neg logit contributions
 Ake-0.105
 Scand-0.101
ewski-0.095
do-0.091
arov-0.088
Token Hillary
Token ID5073
Feature activation+4.84e-01

Pos logit contributions
 Ake+0.097
 Scand+0.093
ewski+0.088
do+0.084
arov+0.082
Neg logit contributions
retty-0.109
emouth-0.098
ergus-0.093
idth-0.091
edom-0.089
Token Clinton
Token ID2605
Feature activation+3.48e-01

Pos logit contributions
 Ake+0.266
 Scand+0.251
ewski+0.233
do+0.220
arov+0.213
Neg logit contributions
retty-0.466
emouth-0.428
ergus-0.409
idth-0.401
edom-0.394
Token Hillary
Token ID5073
Feature activation+9.64e-01

Pos logit contributions
 Ake+0.234
 Scand+0.225
ewski+0.211
do+0.202
arov+0.196
Neg logit contributions
retty-0.292
emouth-0.264
ergus-0.251
idth-0.244
edom-0.240
Token Diane
Token ID26542
Feature activation-2.09e+00

Pos logit contributions
 Ake+0.454
 Scand+0.428
ewski+0.392
do+0.370
arov+0.354
Neg logit contributions
retty-0.999
emouth-0.920
ergus-0.890
idth-0.871
 PID-0.857
Token Rodham
Token ID41848
Feature activation-6.99e-01

Pos logit contributions
retty+2.086
emouth+1.915
ergus+1.806
idth+1.781
edom+1.759
Neg logit contributions
 Ake-1.120
 Scand-1.060
ewski-0.959
do-0.901
der-0.893
Token Clinton
Token ID2605
Feature activation+1.20e-01

Pos logit contributions
retty+0.696
emouth+0.641
ergus+0.612
idth+0.600
edom+0.591
Neg logit contributions
 Ake-0.365
 Scand-0.343
ewski-0.317
do-0.300
der-0.286
TokenSanders
Token ID26747
Feature activation+9.55e-01

Pos logit contributions
 Ake+0.081
 Scand+0.077
ewski+0.072
do+0.069
arov+0.067
Neg logit contributions
retty-0.101
emouth-0.092
ergus-0.087
idth-0.085
edom-0.083
Token:
Token ID25
Feature activation-7.70e-01

Pos logit contributions
 Ake+0.708
 Scand+0.678
ewski+0.640
do+0.619
arov+0.605
Neg logit contributions
retty-0.742
emouth-0.662
ergus-0.627
idth-0.607
edom-0.599
Token '
Token ID705
Feature activation-3.48e-01

Pos logit contributions
retty+0.648
emouth+0.583
ergus+0.555
idth+0.542
edom+0.529
Neg logit contributions
 Ake-0.524
 Scand-0.500
ewski-0.467
do-0.447
arov-0.433
Token presidential
Token ID4787
Feature activation+2.27e-01

Pos logit contributions
 Ake+0.457
 Scand+0.439
ewski+0.416
do+0.401
arov+0.392
Neg logit contributions
retty-0.445
emouth-0.399
ergus-0.375
idth-0.363
edom-0.356
Token nominee
Token ID10429
Feature activation-7.99e-02

Pos logit contributions
 Ake+0.193
 Scand+0.186
ewski+0.177
do+0.171
arov+0.168
Neg logit contributions
retty-0.150
emouth-0.132
ergus-0.124
idth-0.119
edom-0.116
Token Hillary
Token ID5073
Feature activation+3.83e-01

Pos logit contributions
retty+0.067
emouth+0.061
ergus+0.058
idth+0.056
edom+0.055
Neg logit contributions
 Ake-0.054
 Scand-0.052
ewski-0.048
do-0.046
arov-0.045
Token Clinton
Token ID2605
Feature activation+1.23e-01

Pos logit contributions
 Ake+0.208
 Scand+0.197
ewski+0.182
do+0.172
arov+0.166
Neg logit contributions
retty-0.371
emouth-0.341
ergus-0.326
idth-0.319
edom-0.314
Token Hillary
Token ID5073
Feature activation+6.94e-01

Pos logit contributions
 Ake+0.083
 Scand+0.079
ewski+0.075
do+0.071
arov+0.069
Neg logit contributions
retty-0.103
emouth-0.093
ergus-0.088
idth-0.086
edom-0.085
Token Diane
Token ID26542
Feature activation-2.08e+00

Pos logit contributions
 Ake+0.323
 Scand+0.304
ewski+0.276
do+0.259
arov+0.249
Neg logit contributions
retty-0.725
emouth-0.670
ergus-0.646
idth-0.633
edom-0.621
Token Rodham
Token ID41848
Feature activation-7.20e-01

Pos logit contributions
retty+2.073
emouth+1.901
ergus+1.798
idth+1.759
edom+1.747
Neg logit contributions
 Ake-1.113
 Scand-1.054
ewski-0.964
do-0.907
der-0.892
Token Clinton
Token ID2605
Feature activation+1.46e-01

Pos logit contributions
retty+0.716
emouth+0.659
ergus+0.629
idth+0.618
edom+0.608
Neg logit contributions
 Ake-0.376
 Scand-0.353
ewski-0.326
do-0.309
der-0.294
TokenSanders
Token ID26747
Feature activation+7.74e-01

Pos logit contributions
 Ake+0.098
 Scand+0.094
ewski+0.089
do+0.085
arov+0.082
Neg logit contributions
retty-0.122
emouth-0.110
ergus-0.105
idth-0.102
edom-0.100
Token:
Token ID25
Feature activation-7.27e-01

Pos logit contributions
 Ake+0.571
 Scand+0.548
ewski+0.517
do+0.499
arov+0.487
Neg logit contributions
retty-0.602
emouth-0.539
ergus-0.510
idth-0.494
edom-0.487
Token '
Token ID705
Feature activation-1.13e+00

Pos logit contributions
retty+0.611
emouth+0.550
ergus+0.523
idth+0.510
edom+0.499
Neg logit contributions
 Ake-0.496
 Scand-0.474
ewski-0.442
do-0.423
arov-0.412
Token Chandler
Token ID28346
Feature activation+2.85e-01

Pos logit contributions
 Ake+0.020
 Scand+0.019
ewski+0.018
do+0.018
arov+0.017
Neg logit contributions
retty-0.021
emouth-0.019
ergus-0.018
idth-0.018
edom-0.017
Token Parsons
Token ID35925
Feature activation-1.55e-01

Pos logit contributions
 Ake+0.266
 Scand+0.258
ewski+0.247
do+0.240
arov+0.235
Neg logit contributions
retty-0.165
emouth-0.142
ergus-0.131
idth-0.126
edom-0.122
Token,
Token ID11
Feature activation+2.72e-01

Pos logit contributions
retty+0.128
emouth+0.115
ergus+0.109
idth+0.106
edom+0.104
Neg logit contributions
 Ake-0.107
 Scand-0.103
ewski-0.096
do-0.092
arov-0.090
Token Dirk
Token ID42761
Feature activation-2.80e-01

Pos logit contributions
 Ake+0.189
 Scand+0.182
ewski+0.171
do+0.164
arov+0.160
Neg logit contributions
retty-0.222
emouth-0.200
ergus-0.190
idth-0.185
edom-0.181
Token Now
Token ID2735
Feature activation+5.85e-01

Pos logit contributions
retty+0.252
emouth+0.230
ergus+0.219
idth+0.214
edom+0.211
Neg logit contributions
 Ake-0.171
 Scand-0.163
ewski-0.152
do-0.145
arov-0.140
Tokenitz
Token ID4224
Feature activation-2.08e+00

Pos logit contributions
 Ake+0.466
 Scand+0.449
ewski+0.426
do+0.410
arov+0.401
Neg logit contributions
retty-0.419
emouth-0.374
ergus-0.349
idth-0.341
edom-0.333
Tokenki
Token ID4106
Feature activation-2.05e-02

Pos logit contributions
retty+1.699
emouth+1.532
ergus+1.432
idth+1.406
edom+1.365
Neg logit contributions
 Ake-1.474
 Scand-1.407
ewski-1.337
do-1.289
arov-1.250
Token,
Token ID11
Feature activation+2.51e-01

Pos logit contributions
retty+0.017
emouth+0.015
ergus+0.014
idth+0.014
edom+0.014
Neg logit contributions
 Ake-0.014
 Scand-0.014
ewski-0.013
do-0.012
arov-0.012
Token Mont
Token ID5575
Feature activation+4.04e-01

Pos logit contributions
 Ake+0.173
 Scand+0.166
ewski+0.156
do+0.150
arov+0.146
Neg logit contributions
retty-0.206
emouth-0.186
ergus-0.176
idth-0.172
edom-0.168
Tokena
Token ID64
Feature activation+1.28e-01

Pos logit contributions
 Ake+0.330
 Scand+0.318
ewski+0.302
do+0.291
arov+0.285
Neg logit contributions
retty-0.282
emouth-0.250
ergus-0.234
idth-0.227
edom-0.221
Token Ellis
Token ID21299
Feature activation-1.24e-01

Pos logit contributions
 Ake+0.090
 Scand+0.087
ewski+0.081
do+0.078
arov+0.076
Neg logit contributions
retty-0.104
emouth-0.093
ergus-0.088
idth-0.086
edom-0.084
Token are
Token ID389
Feature activation-1.08e+00

Pos logit contributions
 Ake+0.269
 Scand+0.259
ewski+0.243
do+0.233
arov+0.228
Neg logit contributions
retty-0.306
emouth-0.276
ergus-0.261
idth-0.254
edom-0.249
Token these
Token ID777
Feature activation+1.65e-01

Pos logit contributions
retty+1.006
emouth+0.907
ergus+0.872
idth+0.845
edom+0.841
Neg logit contributions
 Ake-0.639
 Scand-0.606
ewski-0.562
do-0.538
arov-0.510
Token?
Token ID30
Feature activation+9.04e-01

Pos logit contributions
 Ake+0.112
 Scand+0.107
ewski+0.100
do+0.096
arov+0.094
Neg logit contributions
retty-0.138
emouth-0.125
ergus-0.119
idth-0.116
edom-0.113
Token E
Token ID412
Feature activation+6.25e-01

Pos logit contributions
 Ake+0.826
 Scand+0.797
ewski+0.764
do+0.740
arov+0.734
Neg logit contributions
retty-0.542
emouth-0.470
ergus-0.432
idth-0.415
 PID-0.407
Token-
Token ID12
Feature activation-1.02e+00

Pos logit contributions
 Ake+0.432
 Scand+0.413
ewski+0.388
do+0.370
arov+0.363
Neg logit contributions
retty-0.514
emouth-0.464
ergus-0.440
idth-0.428
edom-0.419
Tokenmail
Token ID4529
Feature activation-2.06e+00

Pos logit contributions
retty+0.705
emouth+0.617
ergus+0.577
idth+0.564
edom+0.553
Neg logit contributions
 Ake-0.831
 Scand-0.816
ewski-0.773
do-0.754
der-0.729
Token this
Token ID428
Feature activation-3.19e-01

Pos logit contributions
retty+1.862
emouth+1.682
ergus+1.605
idth+1.591
edom+1.549
Neg logit contributions
 Ake-1.278
 Scand-1.240
ewski-1.137
do-1.088
der-1.054
Token to
Token ID284
Feature activation-9.76e-01

Pos logit contributions
retty+0.272
emouth+0.245
ergus+0.233
idth+0.228
edom+0.223
Neg logit contributions
 Ake-0.213
 Scand-0.204
ewski-0.190
do-0.183
arov-0.177
Token a
Token ID257
Feature activation-1.54e-01

Pos logit contributions
retty+0.810
emouth+0.734
ergus+0.695
idth+0.677
edom+0.666
Neg logit contributions
 Ake-0.666
 Scand-0.643
ewski-0.602
do-0.577
arov-0.558
Token friend
Token ID1545
Feature activation-3.16e-01

Pos logit contributions
retty+0.158
emouth+0.146
ergus+0.140
idth+0.137
edom+0.135
Neg logit contributions
 Ake-0.075
 Scand-0.070
ewski-0.064
do-0.060
arov-0.058
Token Print
Token ID12578
Feature activation-1.26e+00

Pos logit contributions
retty+0.266
emouth+0.241
ergus+0.228
idth+0.223
edom+0.219
Neg logit contributions
 Ake-0.212
 Scand-0.204
ewski-0.191
do-0.183
arov-0.177
Token flights
Token ID13956
Feature activation-1.68e+00

Pos logit contributions
retty+0.604
emouth+0.544
ergus+0.518
idth+0.505
edom+0.493
Neg logit contributions
 Ake-0.481
 Scand-0.466
ewski-0.437
do-0.416
der-0.403
Token to
Token ID284
Feature activation-2.52e+00

Pos logit contributions
retty+1.494
emouth+1.366
ergus+1.287
idth+1.269
edom+1.229
Neg logit contributions
 Ake-1.061
 Scand-1.020
ewski-0.940
do-0.900
arov-0.879
Token US
Token ID1294
Feature activation+2.94e-01

Pos logit contributions
retty+2.330
emouth+2.086
ergus+1.970
idth+1.957
edom+1.883
Neg logit contributions
 Ake-1.528
 Scand-1.518
ewski-1.336
do-1.324
arov-1.259
Token on
Token ID319
Feature activation-9.08e-02

Pos logit contributions
 Ake+0.195
 Scand+0.186
ewski+0.175
do+0.167
arov+0.163
Neg logit contributions
retty-0.250
emouth-0.227
ergus-0.216
idth-0.210
edom-0.207
Token sidelines
Token ID29394
Feature activation-2.25e-01

Pos logit contributions
retty+0.077
emouth+0.069
ergus+0.066
idth+0.064
edom+0.063
Neg logit contributions
 Ake-0.061
 Scand-0.058
ewski-0.054
do-0.052
arov-0.051
Token of
Token ID286
Feature activation-2.04e+00

Pos logit contributions
retty+0.182
emouth+0.164
ergus+0.155
idth+0.151
edom+0.148
Neg logit contributions
 Ake-0.159
 Scand-0.153
ewski-0.144
do-0.138
arov-0.134
Token Trump
Token ID1301
Feature activation-1.59e+00

Pos logit contributions
retty+1.760
emouth+1.558
ergus+1.482
idth+1.414
edom+1.398
Neg logit contributions
 Ake-1.388
 Scand-1.338
do-1.208
ewski-1.206
der-1.145
Token-
Token ID12
Feature activation-1.09e+00

Pos logit contributions
retty+1.358
emouth+1.214
ergus+1.147
idth+1.131
edom+1.095
Neg logit contributions
 Ake-1.072
 Scand-1.022
ewski-0.976
do-0.935
arov-0.906
TokenKim
Token ID26374
Feature activation-4.25e-01

Pos logit contributions
retty+0.908
emouth+0.811
ergus+0.761
idth+0.748
edom+0.727
Neg logit contributions
 Ake-0.757
 Scand-0.731
ewski-0.685
do-0.669
arov-0.648
Token summit
Token ID14237
Feature activation-2.37e-01

Pos logit contributions
retty+0.300
emouth+0.264
ergus+0.247
idth+0.241
edom+0.234
Neg logit contributions
 Ake-0.346
 Scand-0.333
ewski-0.316
do-0.307
arov-0.300
Token Manafort
Token ID26351
Feature activation-3.75e-01

Pos logit contributions
retty+0.191
emouth+0.172
ergus+0.162
idth+0.159
edom+0.155
Neg logit contributions
 Ake-0.168
 Scand-0.162
ewski-0.152
do-0.146
arov-0.142
Token are
Token ID389
Feature activation-1.08e+00

Pos logit contributions
 Ake+0.259
 Scand+0.249
ewski+0.234
do+0.225
arov+0.220
Neg logit contributions
retty-0.295
emouth-0.266
ergus-0.252
idth-0.245
edom-0.240
Token these
Token ID777
Feature activation+1.77e-01

Pos logit contributions
retty+1.009
emouth+0.910
ergus+0.875
idth+0.850
edom+0.845
Neg logit contributions
 Ake-0.642
 Scand-0.608
ewski-0.564
do-0.540
arov-0.513
Token?
Token ID30
Feature activation+6.67e-01

Pos logit contributions
 Ake+0.120
 Scand+0.115
ewski+0.108
do+0.103
arov+0.101
Neg logit contributions
retty-0.148
emouth-0.134
ergus-0.127
idth-0.124
edom-0.122
Token E
Token ID412
Feature activation+6.68e-01

Pos logit contributions
 Ake+0.607
 Scand+0.585
ewski+0.561
do+0.543
arov+0.537
Neg logit contributions
retty-0.403
emouth-0.350
ergus-0.322
idth-0.310
edom-0.303
Token-
Token ID12
Feature activation-1.02e+00

Pos logit contributions
 Ake+0.463
 Scand+0.443
ewski+0.415
do+0.397
arov+0.388
Neg logit contributions
retty-0.549
emouth-0.495
ergus-0.470
idth-0.457
edom-0.448
Tokenmail
Token ID4529
Feature activation-2.03e+00

Pos logit contributions
retty+0.703
emouth+0.617
ergus+0.577
idth+0.563
edom+0.552
Neg logit contributions
 Ake-0.830
 Scand-0.814
ewski-0.772
do-0.753
arov-0.728
Token this
Token ID428
Feature activation-3.55e-01

Pos logit contributions
retty+1.826
emouth+1.655
ergus+1.578
idth+1.562
edom+1.523
Neg logit contributions
 Ake-1.263
 Scand-1.225
ewski-1.124
do-1.075
der-1.042
Token to
Token ID284
Feature activation-8.79e-01

Pos logit contributions
retty+0.302
emouth+0.273
ergus+0.259
idth+0.253
edom+0.249
Neg logit contributions
 Ake-0.236
 Scand-0.226
ewski-0.211
do-0.203
arov-0.197
Token a
Token ID257
Feature activation-2.27e-01

Pos logit contributions
retty+0.728
emouth+0.659
ergus+0.625
idth+0.609
edom+0.599
Neg logit contributions
 Ake-0.602
 Scand-0.580
ewski-0.545
do-0.521
arov-0.504
Token friend
Token ID1545
Feature activation-6.50e-01

Pos logit contributions
retty+0.234
emouth+0.216
ergus+0.207
idth+0.203
edom+0.200
Neg logit contributions
 Ake-0.110
 Scand-0.103
ewski-0.094
do-0.089
arov-0.085
Token Print
Token ID12578
Feature activation-1.24e+00

Pos logit contributions
retty+0.554
emouth+0.502
ergus+0.476
idth+0.466
edom+0.456
Neg logit contributions
 Ake-0.432
 Scand-0.415
ewski-0.388
do-0.371
der-0.357
Token flights
Token ID13956
Feature activation-1.76e+00

Pos logit contributions
retty+0.711
emouth+0.640
ergus+0.611
idth+0.596
edom+0.581
Neg logit contributions
 Ake-0.555
 Scand-0.539
ewski-0.505
do-0.480
der-0.466
Token to
Token ID284
Feature activation-2.44e+00

Pos logit contributions
retty+1.569
emouth+1.437
ergus+1.354
idth+1.334
edom+1.292
Neg logit contributions
 Ake-1.096
 Scand-1.059
ewski-0.974
do-0.929
arov-0.910
Token US
Token ID1294
Feature activation+4.75e-01

Pos logit contributions
retty+2.234
emouth+1.998
ergus+1.888
idth+1.874
edom+1.806
Neg logit contributions
 Ake-1.495
 Scand-1.484
ewski-1.307
do-1.292
arov-1.232
Token on
Token ID319
Feature activation+4.13e-02

Pos logit contributions
 Ake+0.315
 Scand+0.301
ewski+0.282
do+0.269
arov+0.263
Neg logit contributions
retty-0.403
emouth-0.365
ergus-0.348
idth-0.339
edom-0.333
Token sidelines
Token ID29394
Feature activation-1.96e-01

Pos logit contributions
 Ake+0.028
 Scand+0.027
ewski+0.025
do+0.024
arov+0.023
Neg logit contributions
retty-0.035
emouth-0.031
ergus-0.030
idth-0.029
edom-0.029
Token of
Token ID286
Feature activation-2.03e+00

Pos logit contributions
retty+0.158
emouth+0.143
ergus+0.135
idth+0.132
edom+0.129
Neg logit contributions
 Ake-0.139
 Scand-0.133
ewski-0.125
do-0.120
arov-0.117
Token Trump
Token ID1301
Feature activation-1.66e+00

Pos logit contributions
retty+1.760
emouth+1.557
ergus+1.485
idth+1.415
edom+1.404
Neg logit contributions
 Ake-1.370
 Scand-1.323
do-1.194
ewski-1.190
arov-1.127
Token-
Token ID12
Feature activation-1.13e+00

Pos logit contributions
retty+1.449
emouth+1.298
ergus+1.231
idth+1.218
edom+1.177
Neg logit contributions
 Ake-1.084
 Scand-1.033
ewski-0.985
do-0.945
arov-0.908
TokenKim
Token ID26374
Feature activation-3.85e-01

Pos logit contributions
retty+0.937
emouth+0.837
ergus+0.784
idth+0.773
edom+0.749
Neg logit contributions
 Ake-0.779
 Scand-0.752
ewski-0.704
do-0.690
arov-0.665
Token summit
Token ID14237
Feature activation-9.07e-03

Pos logit contributions
retty+0.271
emouth+0.238
ergus+0.224
idth+0.218
edom+0.212
Neg logit contributions
 Ake-0.314
 Scand-0.302
ewski-0.287
do-0.278
arov-0.272
Token Manafort
Token ID26351
Feature activation-4.62e-01

Pos logit contributions
retty+0.007
emouth+0.006
ergus+0.006
idth+0.006
edom+0.006
Neg logit contributions
 Ake-0.007
 Scand-0.006
ewski-0.006
do-0.006
arov-0.006
TokenF
Token ID37
Feature activation+3.62e-01

Pos logit contributions
 Ake+0.272
 Scand+0.261
ewski+0.245
do+0.235
arov+0.229
Neg logit contributions
retty-0.321
emouth-0.290
ergus-0.275
idth-0.268
edom-0.263
Token Co
Token ID1766
Feature activation+9.58e-02

Pos logit contributions
 Ake+0.251
 Scand+0.240
ewski+0.225
do+0.217
arov+0.211
Neg logit contributions
retty-0.297
emouth-0.268
ergus-0.254
idth-0.247
edom-0.243
Token-
Token ID12
Feature activation-1.29e-01

Pos logit contributions
 Ake+0.065
 Scand+0.063
ewski+0.059
do+0.056
arov+0.055
Neg logit contributions
retty-0.080
emouth-0.072
ergus-0.068
idth-0.067
edom-0.065
TokenPresident
Token ID10364
Feature activation+1.66e-01

Pos logit contributions
retty+0.091
emouth+0.081
ergus+0.076
idth+0.074
edom+0.072
Neg logit contributions
 Ake-0.105
 Scand-0.101
ewski-0.096
do-0.093
arov-0.091
Token Annie
Token ID25860
Feature activation-7.34e-01

Pos logit contributions
 Ake+0.116
 Scand+0.111
ewski+0.104
do+0.100
arov+0.098
Neg logit contributions
retty-0.135
emouth-0.122
ergus-0.115
idth-0.112
edom-0.110
Token Laurie
Token ID40811
Feature activation-1.99e+00

Pos logit contributions
retty+0.514
emouth+0.455
ergus+0.425
idth+0.413
edom+0.403
Neg logit contributions
 Ake-0.602
 Scand-0.582
ewski-0.549
do-0.531
arov-0.517
Token G
Token ID402
Feature activation+6.82e-01

Pos logit contributions
retty+1.730
emouth+1.566
ergus+1.477
idth+1.449
edom+1.421
Neg logit contributions
 Ake-1.345
 Scand-1.279
ewski-1.185
do-1.129
der-1.073
Tokenaylor
Token ID7167
Feature activation+1.65e-01

Pos logit contributions
 Ake+0.635
 Scand+0.615
ewski+0.587
do+0.568
arov+0.559
Neg logit contributions
retty-0.397
emouth-0.345
ergus-0.319
idth-0.304
edom-0.296
Token.
Token ID13
Feature activation-1.27e-01

Pos logit contributions
 Ake+0.117
 Scand+0.112
ewski+0.105
do+0.101
arov+0.099
Neg logit contributions
retty-0.133
emouth-0.120
ergus-0.114
idth-0.111
edom-0.109
Token "
Token ID366
Feature activation-1.80e-01

Pos logit contributions
retty+0.099
emouth+0.089
ergus+0.084
idth+0.082
edom+0.080
Neg logit contributions
 Ake-0.092
 Scand-0.089
ewski-0.084
do-0.080
arov-0.078
TokenV
Token ID53
Feature activation-3.06e-01

Pos logit contributions
retty+0.150
emouth+0.136
ergus+0.129
idth+0.126
edom+0.124
Neg logit contributions
 Ake-0.122
 Scand-0.117
ewski-0.109
do-0.105
arov-0.102
Token said
Token ID531
Feature activation-1.29e-01

Pos logit contributions
 Ake+0.019
 Scand+0.018
ewski+0.017
do+0.017
arov+0.016
Neg logit contributions
retty-0.025
emouth-0.022
ergus-0.021
idth-0.021
edom-0.020
Token.
Token ID13
Feature activation-2.24e-01

Pos logit contributions
retty+0.104
emouth+0.094
ergus+0.088
idth+0.086
edom+0.085
Neg logit contributions
 Ake-0.091
 Scand-0.087
ewski-0.082
do-0.079
arov-0.077
Token "
Token ID366
Feature activation-5.20e-02

Pos logit contributions
retty+0.176
emouth+0.158
ergus+0.149
idth+0.145
edom+0.142
Neg logit contributions
 Ake-0.164
 Scand-0.158
ewski-0.149
do-0.143
arov-0.139
TokenI
Token ID40
Feature activation-1.86e-01

Pos logit contributions
retty+0.044
emouth+0.040
ergus+0.038
idth+0.037
edom+0.036
Neg logit contributions
 Ake-0.035
 Scand-0.033
ewski-0.031
do-0.030
arov-0.029
Token love
Token ID1842
Feature activation-9.64e-02

Pos logit contributions
retty+0.150
emouth+0.135
ergus+0.128
idth+0.125
edom+0.122
Neg logit contributions
 Ake-0.131
 Scand-0.126
ewski-0.118
do-0.114
arov-0.111
Token Hels
Token ID33889
Feature activation-1.99e+00

Pos logit contributions
retty+0.077
emouth+0.069
ergus+0.065
idth+0.064
edom+0.062
Neg logit contributions
 Ake-0.069
 Scand-0.066
ewski-0.062
do-0.060
arov-0.058
Tokening
Token ID278
Feature activation-3.82e-01

Pos logit contributions
retty+1.530
emouth+1.356
ergus+1.281
idth+1.242
edom+1.219
Neg logit contributions
 Ake-1.489
 Scand-1.431
ewski-1.356
do-1.319
arov-1.286
Tokenborg
Token ID23297
Feature activation-6.27e-02

Pos logit contributions
retty+0.315
emouth+0.284
ergus+0.270
idth+0.263
edom+0.258
Neg logit contributions
 Ake-0.264
 Scand-0.253
ewski-0.238
do-0.229
arov-0.222
Token and
Token ID290
Feature activation-9.28e-02

Pos logit contributions
retty+0.051
emouth+0.046
ergus+0.044
idth+0.043
edom+0.042
Neg logit contributions
 Ake-0.044
 Scand-0.042
ewski-0.040
do-0.038
arov-0.037
Token Sweden
Token ID10710
Feature activation-1.40e-01

Pos logit contributions
retty+0.076
emouth+0.069
ergus+0.065
idth+0.063
edom+0.062
Neg logit contributions
 Ake-0.065
 Scand-0.062
ewski-0.058
do-0.056
arov-0.054
Token,
Token ID11
Feature activation+7.60e-02

Pos logit contributions
retty+0.114
emouth+0.103
ergus+0.098
idth+0.095
edom+0.093
Neg logit contributions
 Ake-0.098
 Scand-0.094
ewski-0.088
do-0.085
arov-0.082
Token is
Token ID318
Feature activation-9.62e-02

Pos logit contributions
retty+0.415
emouth+0.375
ergus+0.354
idth+0.348
edom+0.339
Neg logit contributions
 Ake-0.342
 Scand-0.328
ewski-0.307
do-0.295
arov-0.286
Token the
Token ID262
Feature activation+1.19e+00

Pos logit contributions
retty+0.079
emouth+0.071
ergus+0.067
idth+0.066
edom+0.064
Neg logit contributions
 Ake-0.067
 Scand-0.064
ewski-0.060
do-0.058
arov-0.056
Token link
Token ID2792
Feature activation+1.29e+00

Pos logit contributions
 Ake+0.882
 Scand+0.848
ewski+0.804
do+0.765
arov+0.756
Neg logit contributions
retty-0.921
emouth-0.823
ergus-0.786
idth-0.755
edom-0.751
Token for
Token ID329
Feature activation-1.19e+00

Pos logit contributions
 Ake+0.916
 Scand+0.888
ewski+0.842
do+0.795
arov+0.791
Neg logit contributions
retty-1.021
emouth-0.922
ergus-0.876
idth-0.847
edom-0.830
Token buying
Token ID7067
Feature activation-5.76e-01

Pos logit contributions
retty+1.020
emouth+0.932
ergus+0.881
idth+0.867
 PID+0.841
Neg logit contributions
 Ake-0.773
 Scand-0.744
ewski-0.685
do-0.672
der-0.642
Token the
Token ID262
Feature activation-1.97e+00

Pos logit contributions
retty+0.479
emouth+0.433
ergus+0.410
idth+0.402
edom+0.391
Neg logit contributions
 Ake-0.395
 Scand-0.380
ewski-0.353
do-0.341
arov-0.331
Token second
Token ID1218
Feature activation-9.96e-01

Pos logit contributions
retty+1.654
emouth+1.488
ergus+1.412
idth+1.404
 PID+1.345
Neg logit contributions
 Ake-1.362
 Scand-1.302
ewski-1.187
do-1.170
arov-1.132
Token edition
Token ID8313
Feature activation-2.66e+00

Pos logit contributions
retty+0.689
emouth+0.605
ergus+0.572
idth+0.559
edom+0.534
Neg logit contributions
 Ake-0.827
 Scand-0.797
ewski-0.744
do-0.736
arov-0.714
Token of
Token ID286
Feature activation-1.40e+00

Pos logit contributions
retty+2.320
emouth+2.097
ergus+2.039
idth+2.014
edom+1.962
Neg logit contributions
 Ake-1.716
 Scand-1.613
ewski-1.491
do-1.480
arov-1.420
Token my
Token ID616
Feature activation-1.50e+00

Pos logit contributions
retty+1.176
emouth+1.067
ergus+1.012
idth+0.999
edom+0.976
Neg logit contributions
 Ake-0.939
 Scand-0.897
ewski-0.830
do-0.812
arov-0.781
Token 1993
Token ID9656
Feature activation+4.47e-02

Pos logit contributions
retty+1.388
emouth+1.261
ergus+1.206
idth+1.201
edom+1.164
Neg logit contributions
 Ake-0.883
 Scand-0.847
ewski-0.773
do-0.746
arov-0.714
Token)
Token ID8
Feature activation+3.66e-01

Pos logit contributions
retty+0.101
emouth+0.090
ergus+0.085
idth+0.083
edom+0.082
Neg logit contributions
 Ake-0.093
 Scand-0.089
ewski-0.084
do-0.081
arov-0.079
Token DOI
Token ID40722
Feature activation-1.34e-01

Pos logit contributions
 Ake+0.246
 Scand+0.236
ewski+0.221
do+0.212
arov+0.206
Neg logit contributions
retty-0.307
emouth-0.278
ergus-0.264
idth-0.257
edom-0.252
Token:
Token ID25
Feature activation+6.92e-01

Pos logit contributions
retty+0.115
emouth+0.105
ergus+0.099
idth+0.097
edom+0.095
Neg logit contributions
 Ake-0.088
 Scand-0.084
ewski-0.078
do-0.075
arov-0.073
Token 10
Token ID838
Feature activation+4.57e-01

Pos logit contributions
 Ake+0.439
 Scand+0.417
ewski+0.391
do+0.372
arov+0.363
Neg logit contributions
retty-0.609
emouth-0.554
ergus-0.527
idth-0.515
edom-0.505
Token.
Token ID13
Feature activation+6.66e-01

Pos logit contributions
 Ake+0.330
 Scand+0.317
ewski+0.298
do+0.286
arov+0.279
Neg logit contributions
retty-0.361
emouth-0.325
ergus-0.307
idth-0.299
edom-0.293
Token10
Token ID940
Feature activation+1.56e+00

Pos logit contributions
 Ake+0.440
 Scand+0.420
ewski+0.394
do+0.375
arov+0.366
Neg logit contributions
retty-0.566
emouth-0.513
ergus-0.488
idth-0.477
edom-0.468
Token86
Token ID4521
Feature activation+4.93e-01

Pos logit contributions
 Ake+1.075
 Scand+1.031
ewski+0.965
do+0.908
arov+0.902
Neg logit contributions
retty-1.289
emouth-1.163
ergus-1.114
idth-1.084
edom-1.079
Token/
Token ID14
Feature activation+5.87e-02

Pos logit contributions
 Ake+0.343
 Scand+0.329
ewski+0.309
do+0.296
arov+0.289
Neg logit contributions
retty-0.400
emouth-0.362
ergus-0.343
idth-0.334
edom-0.328
Token34
Token ID2682
Feature activation-3.88e-03

Pos logit contributions
 Ake+0.041
 Scand+0.039
ewski+0.037
do+0.035
arov+0.034
Neg logit contributions
retty-0.048
emouth-0.044
ergus-0.041
idth-0.040
edom-0.040
Token110
Token ID11442
Feature activation+8.69e-02

Pos logit contributions
retty+0.003
emouth+0.003
ergus+0.003
idth+0.003
edom+0.003
Neg logit contributions
 Ake-0.003
 Scand-0.002
ewski-0.002
do-0.002
arov-0.002
Token7
Token ID22
Feature activation+6.52e-01

Pos logit contributions
 Ake+0.058
 Scand+0.056
ewski+0.052
do+0.050
arov+0.049
Neg logit contributions
retty-0.073
emouth-0.066
ergus-0.063
idth-0.062
edom-0.060
Tokenilities
Token ID2410
Feature activation+4.75e-02

Pos logit contributions
retty+0.281
emouth+0.247
ergus+0.229
idth+0.223
edom+0.217
Neg logit contributions
 Ake-0.363
 Scand-0.351
ewski-0.335
do-0.324
arov-0.316
Token,
Token ID11
Feature activation-2.81e-01

Pos logit contributions
 Ake+0.033
 Scand+0.031
ewski+0.030
do+0.028
arov+0.028
Neg logit contributions
retty-0.039
emouth-0.035
ergus-0.033
idth-0.033
edom-0.032
Token family
Token ID1641
Feature activation-5.76e-01

Pos logit contributions
retty+0.230
emouth+0.207
ergus+0.196
idth+0.191
edom+0.188
Neg logit contributions
 Ake-0.196
 Scand-0.188
ewski-0.177
do-0.170
arov-0.165
Token-
Token ID12
Feature activation+9.48e-02

Pos logit contributions
retty+0.489
emouth+0.442
ergus+0.418
idth+0.409
edom+0.401
Neg logit contributions
 Ake-0.383
 Scand-0.367
ewski-0.346
do-0.332
arov-0.322
Tokenand
Token ID392
Feature activation+3.76e-01

Pos logit contributions
 Ake+0.074
 Scand+0.071
ewski+0.068
do+0.065
arov+0.064
Neg logit contributions
retty-0.069
emouth-0.062
ergus-0.058
idth-0.057
edom-0.055
Token-
Token ID12
Feature activation+1.10e+00

Pos logit contributions
 Ake+0.257
 Scand+0.246
ewski+0.231
do+0.221
arov+0.215
Neg logit contributions
retty-0.311
emouth-0.282
ergus-0.268
idth-0.261
edom-0.256
Tokenchildren
Token ID17197
Feature activation-2.73e-01

Pos logit contributions
 Ake+0.941
 Scand+0.913
ewski+0.865
arov+0.824
do+0.822
Neg logit contributions
retty-0.725
emouth-0.644
ergus-0.602
idth-0.578
edom-0.570
Token,
Token ID11
Feature activation-3.04e-01

Pos logit contributions
retty+0.226
emouth+0.205
ergus+0.194
idth+0.189
edom+0.186
Neg logit contributions
 Ake-0.187
 Scand-0.179
ewski-0.169
do-0.162
arov-0.157
Token consumer
Token ID7172
Feature activation-1.29e+00

Pos logit contributions
retty+0.249
emouth+0.224
ergus+0.212
idth+0.207
edom+0.203
Neg logit contributions
 Ake-0.212
 Scand-0.204
ewski-0.191
do-0.184
arov-0.179
Token-
Token ID12
Feature activation-1.13e+00

Pos logit contributions
retty+1.107
emouth+1.011
ergus+0.959
idth+0.931
edom+0.919
Neg logit contributions
 Ake-0.846
 Scand-0.811
ewski-0.754
do-0.732
arov-0.708
Tokenf
Token ID69
Feature activation-3.02e-01

Pos logit contributions
retty+0.921
emouth+0.834
ergus+0.784
idth+0.770
edom+0.752
Neg logit contributions
 Ake-0.781
 Scand-0.755
ewski-0.712
do-0.693
arov-0.666
Token on
Token ID319
Feature activation-6.48e-02

Pos logit contributions
retty+0.084
emouth+0.076
ergus+0.072
idth+0.070
edom+0.069
Neg logit contributions
 Ake-0.071
 Scand-0.068
ewski-0.064
do-0.061
arov-0.059
Token Saturday
Token ID3909
Feature activation-1.68e-01

Pos logit contributions
retty+0.051
emouth+0.046
ergus+0.043
idth+0.042
edom+0.041
Neg logit contributions
 Ake-0.047
 Scand-0.045
ewski-0.043
do-0.041
arov-0.040
Token.
Token ID13
Feature activation-1.19e-01

Pos logit contributions
retty+0.137
emouth+0.124
ergus+0.117
idth+0.114
edom+0.112
Neg logit contributions
 Ake-0.118
 Scand-0.113
ewski-0.106
do-0.102
arov-0.099
Token
Token ID198
Feature activation-6.55e-02

Pos logit contributions
retty+0.098
emouth+0.089
ergus+0.084
idth+0.082
edom+0.080
Neg logit contributions
 Ake-0.083
 Scand-0.079
ewski-0.074
do-0.071
arov-0.069
Token
Token ID198
Feature activation-1.43e-01

Pos logit contributions
retty+0.054
emouth+0.048
ergus+0.046
idth+0.045
edom+0.044
Neg logit contributions
 Ake-0.046
 Scand-0.044
ewski-0.041
do-0.039
arov-0.038
TokenBull
Token ID39549
Feature activation+1.28e+00

Pos logit contributions
retty+0.119
emouth+0.108
ergus+0.102
idth+0.100
edom+0.098
Neg logit contributions
 Ake-0.097
 Scand-0.093
ewski-0.087
do-0.084
arov-0.082
Tokendogs
Token ID22242
Feature activation-1.95e-01

Pos logit contributions
 Ake+1.140
 Scand+1.105
ewski+1.052
do+1.002
arov+0.993
Neg logit contributions
retty-0.791
emouth-0.699
ergus-0.646
idth-0.618
edom-0.602
Token Head
Token ID7123
Feature activation-3.76e-01

Pos logit contributions
retty+0.159
emouth+0.144
ergus+0.136
idth+0.133
edom+0.130
Neg logit contributions
 Ake-0.136
 Scand-0.130
ewski-0.122
do-0.117
arov-0.114
Token Phys
Token ID8687
Feature activation+1.87e-01

Pos logit contributions
retty+0.306
emouth+0.277
ergus+0.262
idth+0.256
edom+0.251
Neg logit contributions
 Ake-0.263
 Scand-0.252
ewski-0.237
do-0.228
arov-0.221
Tokeni
Token ID72
Feature activation-5.11e-01

Pos logit contributions
 Ake+0.137
 Scand+0.132
ewski+0.124
do+0.120
arov+0.117
Neg logit contributions
retty-0.146
emouth-0.131
ergus-0.124
idth-0.121
edom-0.118
Tokenother
Token ID847
Feature activation+2.45e-01

Pos logit contributions
retty+0.343
emouth+0.302
ergus+0.281
idth+0.274
edom+0.266
Neg logit contributions
 Ake-0.431
 Scand-0.417
ewski-0.397
do-0.384
arov-0.375
Token sympathetic
Token ID22335
Feature activation-1.38e-01

Pos logit contributions
 Ake+0.023
 Scand+0.022
ewski+0.021
do+0.020
arov+0.020
Neg logit contributions
retty-0.026
emouth-0.023
ergus-0.022
idth-0.021
edom-0.021
Token (
Token ID357
Feature activation-1.16e-01

Pos logit contributions
retty+0.113
emouth+0.101
ergus+0.096
idth+0.094
edom+0.092
Neg logit contributions
 Ake-0.096
 Scand-0.092
ewski-0.087
do-0.083
arov-0.081
Token
Token ID447
Feature activation+1.71e-01

Pos logit contributions
retty+0.092
emouth+0.083
ergus+0.078
idth+0.076
edom+0.074
Neg logit contributions
 Ake-0.083
 Scand-0.080
ewski-0.075
do-0.073
arov-0.071
Token
Token ID250
Feature activation-4.92e-02

Pos logit contributions
 Ake+0.125
 Scand+0.120
ewski+0.113
do+0.109
arov+0.106
Neg logit contributions
retty-0.134
emouth-0.120
ergus-0.114
idth-0.111
edom-0.108
Tokenfight
Token ID15481
Feature activation+4.17e-01

Pos logit contributions
retty+0.040
emouth+0.036
ergus+0.034
idth+0.033
edom+0.032
Neg logit contributions
 Ake-0.035
 Scand-0.033
ewski-0.031
do-0.030
arov-0.029
Token or
Token ID393
Feature activation+1.25e+00

Pos logit contributions
 Ake+0.291
 Scand+0.278
ewski+0.262
do+0.251
arov+0.245
Neg logit contributions
retty-0.339
emouth-0.307
ergus-0.291
idth-0.283
edom-0.277
Token flight
Token ID5474
Feature activation+1.70e-01

Pos logit contributions
 Ake+0.803
 Scand+0.762
ewski+0.716
do+0.682
arov+0.672
Neg logit contributions
retty-1.083
emouth-0.988
ergus-0.939
idth-0.916
 PID-0.910
Token
Token ID447
Feature activation+4.50e-02

Pos logit contributions
 Ake+0.118
 Scand+0.113
ewski+0.106
do+0.102
arov+0.099
Neg logit contributions
retty-0.139
emouth-0.126
ergus-0.119
idth-0.116
edom-0.114
Token
Token ID251
Feature activation+2.71e-01

Pos logit contributions
 Ake+0.031
 Scand+0.030
ewski+0.028
do+0.027
arov+0.026
Neg logit contributions
retty-0.037
emouth-0.034
ergus-0.032
idth-0.031
edom-0.031
Token)
Token ID8
Feature activation+1.40e-01

Pos logit contributions
 Ake+0.187
 Scand+0.180
ewski+0.169
do+0.162
arov+0.158
Neg logit contributions
retty-0.222
emouth-0.201
ergus-0.190
idth-0.185
edom-0.182
Token and
Token ID290
Feature activation+3.89e-01

Pos logit contributions
 Ake+0.097
 Scand+0.093
ewski+0.087
do+0.084
arov+0.081
Neg logit contributions
retty-0.116
emouth-0.104
ergus-0.099
idth-0.096
edom-0.095
Token she
Token ID673
Feature activation-2.88e-02

Pos logit contributions
retty+0.068
emouth+0.061
ergus+0.058
idth+0.057
edom+0.056
Neg logit contributions
 Ake-0.056
 Scand-0.053
ewski-0.050
do-0.048
arov-0.047
Token sank
Token ID30895
Feature activation+6.93e-02

Pos logit contributions
retty+0.023
emouth+0.021
ergus+0.020
idth+0.019
edom+0.019
Neg logit contributions
 Ake-0.020
 Scand-0.020
ewski-0.018
do-0.018
arov-0.017
Token quickly
Token ID2952
Feature activation+1.28e-02

Pos logit contributions
 Ake+0.048
 Scand+0.046
ewski+0.043
do+0.041
arov+0.040
Neg logit contributions
retty-0.057
emouth-0.052
ergus-0.049
idth-0.048
edom-0.047
Token into
Token ID656
Feature activation+2.23e-01

Pos logit contributions
 Ake+0.009
 Scand+0.008
ewski+0.008
do+0.008
arov+0.007
Neg logit contributions
retty-0.010
emouth-0.009
ergus-0.009
idth-0.009
edom-0.009
Token a
Token ID257
Feature activation+6.77e-02

Pos logit contributions
 Ake+0.157
 Scand+0.151
ewski+0.142
do+0.136
arov+0.133
Neg logit contributions
retty-0.180
emouth-0.162
ergus-0.153
idth-0.149
edom-0.147
Token mud
Token ID17492
Feature activation+1.06e+00

Pos logit contributions
 Ake+0.052
 Scand+0.050
ewski+0.048
do+0.046
arov+0.045
Neg logit contributions
retty-0.050
emouth-0.045
ergus-0.042
idth-0.041
edom-0.040
Tokenpool
Token ID7742
Feature activation+2.52e-01

Pos logit contributions
 Ake+0.780
 Scand+0.747
ewski+0.705
do+0.675
arov+0.660
Neg logit contributions
retty-0.826
emouth-0.747
ergus-0.703
idth-0.685
edom-0.671
Token that
Token ID326
Feature activation+4.20e-01

Pos logit contributions
 Ake+0.178
 Scand+0.170
ewski+0.160
do+0.154
arov+0.150
Neg logit contributions
retty-0.203
emouth-0.184
ergus-0.174
idth-0.169
edom-0.166
Token froze
Token ID37785
Feature activation-1.09e-01

Pos logit contributions
 Ake+0.289
 Scand+0.277
ewski+0.261
do+0.250
arov+0.243
Neg logit contributions
retty-0.344
emouth-0.312
ergus-0.296
idth-0.288
edom-0.283
Token and
Token ID290
Feature activation-4.53e-02

Pos logit contributions
retty+0.088
emouth+0.080
ergus+0.075
idth+0.074
edom+0.072
Neg logit contributions
 Ake-0.076
 Scand-0.073
ewski-0.069
do-0.066
arov-0.064
Token preserved
Token ID17232
Feature activation-2.45e-02

Pos logit contributions
retty+0.037
emouth+0.034
ergus+0.032
idth+0.031
edom+0.030
Neg logit contributions
 Ake-0.031
 Scand-0.030
ewski-0.028
do-0.027
arov-0.026
Token will
Token ID481
Feature activation-7.37e-02

Pos logit contributions
 Ake+0.049
 Scand+0.047
ewski+0.045
do+0.043
arov+0.042
Neg logit contributions
retty-0.054
emouth-0.049
ergus-0.046
idth-0.045
edom-0.044
Token be
Token ID307
Feature activation-1.85e-01

Pos logit contributions
retty+0.058
emouth+0.052
ergus+0.049
idth+0.048
edom+0.047
Neg logit contributions
 Ake-0.054
 Scand-0.051
ewski-0.048
do-0.047
arov-0.045
Token monitoring
Token ID9904
Feature activation+1.59e-01

Pos logit contributions
retty+0.138
emouth+0.124
ergus+0.116
idth+0.113
edom+0.111
Neg logit contributions
 Ake-0.142
 Scand-0.136
ewski-0.129
do-0.124
arov-0.121
Token over
Token ID625
Feature activation+1.78e-01

Pos logit contributions
 Ake+0.114
 Scand+0.110
ewski+0.103
do+0.099
arov+0.097
Neg logit contributions
retty-0.127
emouth-0.115
ergus-0.108
idth-0.105
edom-0.103
Token the
Token ID262
Feature activation+8.18e-02

Pos logit contributions
 Ake+0.125
 Scand+0.120
ewski+0.113
do+0.109
arov+0.106
Neg logit contributions
retty-0.144
emouth-0.130
ergus-0.123
idth-0.120
edom-0.118
Token coming
Token ID2406
Feature activation+3.47e-01

Pos logit contributions
 Ake+0.050
 Scand+0.047
ewski+0.044
do+0.042
arov+0.041
Neg logit contributions
retty-0.074
emouth-0.068
ergus-0.064
idth-0.063
edom-0.062
Token years
Token ID812
Feature activation+2.88e-02

Pos logit contributions
 Ake+0.241
 Scand+0.231
ewski+0.218
do+0.209
arov+0.203
Neg logit contributions
retty-0.283
emouth-0.256
ergus-0.243
idth-0.236
edom-0.232
Token.
Token ID13
Feature activation-2.31e-02

Pos logit contributions
 Ake+0.020
 Scand+0.019
ewski+0.018
do+0.018
arov+0.017
Neg logit contributions
retty-0.023
emouth-0.021
ergus-0.020
idth-0.019
edom-0.019
Token<|endoftext|>
Token ID50256
Feature activation+1.48e-01

Pos logit contributions
retty+0.019
emouth+0.017
ergus+0.016
idth+0.015
edom+0.015
Neg logit contributions
 Ake-0.016
 Scand-0.016
ewski-0.015
do-0.014
arov-0.014
TokenI
Token ID40
Feature activation+3.05e-01

Pos logit contributions
 Ake+0.099
 Scand+0.095
ewski+0.089
do+0.085
arov+0.083
Neg logit contributions
retty-0.126
emouth-0.114
ergus-0.108
idth-0.105
edom-0.104
Token personally
Token ID7620
Feature activation-5.48e-02

Pos logit contributions
 Ake+0.214
 Scand+0.205
ewski+0.193
do+0.185
arov+0.180
Neg logit contributions
retty-0.247
emouth-0.223
ergus-0.211
idth-0.206
edom-0.202
Token Trump
Token ID1301
Feature activation+2.02e-01

Pos logit contributions
 Ake+0.126
 Scand+0.121
ewski+0.114
do+0.109
arov+0.106
Neg logit contributions
retty-0.139
emouth-0.125
ergus-0.119
idth-0.115
edom-0.113
Token cabinet
Token ID13447
Feature activation-7.71e-02

Pos logit contributions
 Ake+0.124
 Scand+0.119
ewski+0.110
do+0.105
arov+0.102
Neg logit contributions
retty-0.181
emouth-0.165
ergus-0.157
idth-0.154
edom-0.151
Token is
Token ID318
Feature activation-1.13e-01

Pos logit contributions
retty+0.064
emouth+0.058
ergus+0.055
idth+0.053
edom+0.052
Neg logit contributions
 Ake-0.053
 Scand-0.051
ewski-0.047
do-0.046
arov-0.044
Token a
Token ID257
Feature activation-4.13e-02

Pos logit contributions
retty+0.090
emouth+0.081
ergus+0.076
idth+0.074
edom+0.073
Neg logit contributions
 Ake-0.082
 Scand-0.079
ewski-0.074
do-0.071
arov-0.069
Token
Token ID564
Feature activation-1.05e-01

Pos logit contributions
retty+0.032
emouth+0.029
ergus+0.027
idth+0.027
edom+0.026
Neg logit contributions
 Ake-0.030
 Scand-0.029
ewski-0.027
do-0.026
arov-0.026
Token
Token ID250
Feature activation+2.69e-01

Pos logit contributions
retty+0.083
emouth+0.075
ergus+0.071
idth+0.069
edom+0.067
Neg logit contributions
 Ake-0.075
 Scand-0.072
ewski-0.068
do-0.065
arov-0.064
Tokenwho
Token ID8727
Feature activation+2.73e-02

Pos logit contributions
 Ake+0.189
 Scand+0.181
ewski+0.171
do+0.163
arov+0.159
Neg logit contributions
retty-0.218
emouth-0.197
ergus-0.186
idth-0.181
edom-0.178
Token
Token ID447
Feature activation-2.54e-01

Pos logit contributions
 Ake+0.020
 Scand+0.019
ewski+0.018
do+0.017
arov+0.017
Neg logit contributions
retty-0.021
emouth-0.019
ergus-0.018
idth-0.018
edom-0.017
Token
Token ID247
Feature activation-1.94e-01

Pos logit contributions
retty+0.216
emouth+0.196
ergus+0.185
idth+0.181
edom+0.178
Neg logit contributions
 Ake-0.169
 Scand-0.161
ewski-0.151
do-0.145
arov-0.141
Tokens
Token ID82
Feature activation+3.69e-02

Pos logit contributions
retty+0.138
emouth+0.123
ergus+0.115
idth+0.112
edom+0.109
Neg logit contributions
 Ake-0.155
 Scand-0.150
ewski-0.142
do-0.137
arov-0.134
Token-
Token ID12
Feature activation-2.06e-01

Pos logit contributions
 Ake+0.027
 Scand+0.026
ewski+0.025
do+0.024
arov+0.023
Neg logit contributions
retty-0.029
emouth-0.026
ergus-0.024
idth-0.024
edom-0.023
Token help
Token ID1037
Feature activation-8.41e-02

Pos logit contributions
retty+0.049
emouth+0.044
ergus+0.042
idth+0.041
edom+0.040
Neg logit contributions
 Ake-0.042
 Scand-0.040
ewski-0.038
do-0.036
arov-0.035
Token defend
Token ID4404
Feature activation-7.05e-02

Pos logit contributions
retty+0.070
emouth+0.063
ergus+0.060
idth+0.058
edom+0.057
Neg logit contributions
 Ake-0.058
 Scand-0.055
ewski-0.052
do-0.050
arov-0.048
Token against
Token ID1028
Feature activation+2.59e-01

Pos logit contributions
retty+0.059
emouth+0.053
ergus+0.050
idth+0.049
edom+0.048
Neg logit contributions
 Ake-0.048
 Scand-0.046
ewski-0.043
do-0.041
arov-0.040
Token the
Token ID262
Feature activation+2.82e-01

Pos logit contributions
 Ake+0.192
 Scand+0.185
ewski+0.174
do+0.168
arov+0.164
Neg logit contributions
retty-0.199
emouth-0.179
ergus-0.168
idth-0.164
edom-0.161
Token latest
Token ID3452
Feature activation+1.20e-01

Pos logit contributions
 Ake+0.209
 Scand+0.201
ewski+0.190
do+0.182
arov+0.178
Neg logit contributions
retty-0.218
emouth-0.196
ergus-0.185
idth-0.180
edom-0.176
Token threats
Token ID7432
Feature activation-8.12e-02

Pos logit contributions
 Ake+0.087
 Scand+0.084
ewski+0.079
do+0.076
arov+0.074
Neg logit contributions
retty-0.094
emouth-0.084
ergus-0.080
idth-0.078
edom-0.076
Token."
Token ID526
Feature activation-1.26e-01

Pos logit contributions
retty+0.067
emouth+0.060
ergus+0.057
idth+0.056
edom+0.054
Neg logit contributions
 Ake-0.056
 Scand-0.054
ewski-0.051
do-0.049
arov-0.047
Token However
Token ID2102
Feature activation-1.88e-01

Pos logit contributions
retty+0.106
emouth+0.096
ergus+0.091
idth+0.089
edom+0.087
Neg logit contributions
 Ake-0.085
 Scand-0.081
ewski-0.076
do-0.073
arov-0.071
Token,
Token ID11
Feature activation-2.44e-01

Pos logit contributions
retty+0.155
emouth+0.140
ergus+0.133
idth+0.130
edom+0.127
Neg logit contributions
 Ake-0.130
 Scand-0.124
ewski-0.117
do-0.112
arov-0.109
Token the
Token ID262
Feature activation+2.47e-02

Pos logit contributions
retty+0.200
emouth+0.181
ergus+0.171
idth+0.167
edom+0.164
Neg logit contributions
 Ake-0.169
 Scand-0.162
ewski-0.152
do-0.146
arov-0.142
Token Department
Token ID2732
Feature activation+8.70e-02

Pos logit contributions
 Ake+0.017
 Scand+0.016
ewski+0.015
do+0.014
arov+0.014
Neg logit contributions
retty-0.021
emouth-0.019
ergus-0.018
idth-0.017
edom-0.017
Tokenceler
Token ID7015
Feature activation-1.53e-01

Pos logit contributions
 Ake+0.189
 Scand+0.181
ewski+0.171
do+0.164
arov+0.160
Neg logit contributions
retty-0.202
emouth-0.181
ergus-0.171
idth-0.167
edom-0.163
Tokenating
Token ID803
Feature activation+1.04e-02

Pos logit contributions
retty+0.120
emouth+0.107
ergus+0.101
idth+0.099
edom+0.097
Neg logit contributions
 Ake-0.112
 Scand-0.108
ewski-0.102
do-0.098
arov-0.095
Token water
Token ID1660
Feature activation+1.10e-01

Pos logit contributions
 Ake+0.008
 Scand+0.007
ewski+0.007
do+0.007
arov+0.006
Neg logit contributions
retty-0.008
emouth-0.007
ergus-0.007
idth-0.007
edom-0.007
Token removal
Token ID9934
Feature activation+1.00e-01

Pos logit contributions
 Ake+0.080
 Scand+0.077
ewski+0.072
do+0.069
arov+0.068
Neg logit contributions
retty-0.087
emouth-0.078
ergus-0.074
idth-0.072
edom-0.070
Token from
Token ID422
Feature activation+1.35e-01

Pos logit contributions
 Ake+0.070
 Scand+0.067
ewski+0.063
do+0.060
arov+0.059
Neg logit contributions
retty-0.082
emouth-0.074
ergus-0.070
idth-0.068
edom-0.067
Token ash
Token ID12530
Feature activation+1.18e-01

Pos logit contributions
 Ake+0.096
 Scand+0.092
ewski+0.086
do+0.083
arov+0.081
Neg logit contributions
retty-0.109
emouth-0.099
ergus-0.093
idth-0.091
edom-0.089
Token ponds
Token ID47339
Feature activation-1.54e-01

Pos logit contributions
 Ake+0.103
 Scand+0.099
ewski+0.095
do+0.092
arov+0.090
Neg logit contributions
retty-0.076
emouth-0.067
ergus-0.062
idth-0.060
edom-0.058
Token at
Token ID379
Feature activation-7.13e-05

Pos logit contributions
retty+0.127
emouth+0.115
ergus+0.109
idth+0.106
edom+0.104
Neg logit contributions
 Ake-0.106
 Scand-0.101
ewski-0.095
do-0.092
arov-0.089
Token all
Token ID477
Feature activation-2.03e-01

Pos logit contributions
retty+0.000
emouth+0.000
ergus+0.000
idth+0.000
edom+0.000
Neg logit contributions
 Ake-0.000
 Scand-0.000
ewski-0.000
do-0.000
arov-0.000
Token retired
Token ID9880
Feature activation-2.37e-01

Pos logit contributions
retty+0.159
emouth+0.143
ergus+0.135
idth+0.132
edom+0.129
Neg logit contributions
 Ake-0.149
 Scand-0.143
ewski-0.135
do-0.129
arov-0.126
Token coal
Token ID5655
Feature activation-2.62e-01

Pos logit contributions
retty+0.186
emouth+0.166
ergus+0.157
idth+0.153
edom+0.150
Neg logit contributions
 Ake-0.174
 Scand-0.167
ewski-0.158
do-0.152
arov-0.148
Token favorite
Token ID4004
Feature activation+2.54e-01

Pos logit contributions
 Ake+0.184
 Scand+0.177
ewski+0.167
do+0.160
arov+0.157
Neg logit contributions
retty-0.201
emouth-0.180
ergus-0.170
idth-0.166
edom-0.163
Token chess
Token ID19780
Feature activation-4.21e-01

Pos logit contributions
 Ake+0.191
 Scand+0.184
ewski+0.174
do+0.168
arov+0.164
Neg logit contributions
retty-0.193
emouth-0.173
ergus-0.163
idth-0.158
edom-0.155
Token site
Token ID2524
Feature activation+2.33e-01

Pos logit contributions
retty+0.334
emouth+0.301
ergus+0.284
idth+0.277
edom+0.271
Neg logit contributions
 Ake-0.304
 Scand-0.291
ewski-0.275
do-0.265
arov-0.257
Token:
Token ID25
Feature activation+1.31e-01

Pos logit contributions
 Ake+0.160
 Scand+0.153
ewski+0.144
do+0.138
arov+0.134
Neg logit contributions
retty-0.193
emouth-0.174
ergus-0.165
idth-0.161
edom-0.158
Token
Token ID198
Feature activation-6.52e-02

Pos logit contributions
 Ake+0.091
 Scand+0.087
ewski+0.082
do+0.078
arov+0.076
Neg logit contributions
retty-0.107
emouth-0.097
ergus-0.092
idth-0.090
edom-0.088
Token
Token ID198
Feature activation-5.08e-02

Pos logit contributions
retty+0.053
emouth+0.048
ergus+0.046
idth+0.045
edom+0.044
Neg logit contributions
 Ake-0.045
 Scand-0.043
ewski-0.041
do-0.039
arov-0.038
TokenIn
Token ID818
Feature activation+4.82e-01

Pos logit contributions
retty+0.043
emouth+0.039
ergus+0.037
idth+0.036
edom+0.035
Neg logit contributions
 Ake-0.034
 Scand-0.033
ewski-0.031
do-0.029
arov-0.029
Token-
Token ID12
Feature activation+1.17e-01

Pos logit contributions
 Ake+0.334
 Scand+0.320
ewski+0.301
do+0.288
arov+0.281
Neg logit contributions
retty-0.396
emouth-0.357
ergus-0.339
idth-0.330
edom-0.324
Tokengame
Token ID6057
Feature activation+2.69e-01

Pos logit contributions
 Ake+0.079
 Scand+0.076
ewski+0.071
do+0.068
arov+0.066
Neg logit contributions
retty-0.098
emouth-0.089
ergus-0.084
idth-0.082
edom-0.081
Token replay
Token ID24788
Feature activation-2.41e-01

Pos logit contributions
 Ake+0.191
 Scand+0.183
ewski+0.173
do+0.166
arov+0.161
Neg logit contributions
retty-0.216
emouth-0.194
ergus-0.184
idth-0.179
edom-0.176
Token
Token ID198
Feature activation-1.34e-01

Pos logit contributions
retty+0.194
emouth+0.175
ergus+0.165
idth+0.161
edom+0.158
Neg logit contributions
 Ake-0.172
 Scand-0.165
ewski-0.155
do-0.149
arov-0.145
Token (
Token ID357
Feature activation-1.92e-01

Pos logit contributions
 Ake+0.007
 Scand+0.006
ewski+0.006
do+0.006
arov+0.006
Neg logit contributions
retty-0.008
emouth-0.007
ergus-0.007
idth-0.007
edom-0.006
TokenACT
Token ID10659
Feature activation+1.75e-01

Pos logit contributions
retty+0.166
emouth+0.151
ergus+0.143
idth+0.140
edom+0.138
Neg logit contributions
 Ake-0.124
 Scand-0.118
ewski-0.111
do-0.106
arov-0.103
Token)
Token ID8
Feature activation-3.85e-02

Pos logit contributions
 Ake+0.124
 Scand+0.119
ewski+0.112
do+0.108
arov+0.105
Neg logit contributions
retty-0.140
emouth-0.127
ergus-0.120
idth-0.117
edom-0.114
Token and
Token ID290
Feature activation-4.67e-01

Pos logit contributions
retty+0.032
emouth+0.029
ergus+0.027
idth+0.027
edom+0.026
Neg logit contributions
 Ake-0.026
 Scand-0.025
ewski-0.024
do-0.023
arov-0.022
Token the
Token ID262
Feature activation-3.02e-01

Pos logit contributions
retty+0.385
emouth+0.347
ergus+0.329
idth+0.321
edom+0.315
Neg logit contributions
 Ake-0.323
 Scand-0.309
ewski-0.290
do-0.279
arov-0.270
Token Northern
Token ID8342
Feature activation-3.18e-01

Pos logit contributions
retty+0.260
emouth+0.236
ergus+0.224
idth+0.219
edom+0.215
Neg logit contributions
 Ake-0.197
 Scand-0.188
ewski-0.176
do-0.168
arov-0.163
Token Territory
Token ID25219
Feature activation+1.81e-01

Pos logit contributions
retty+0.295
emouth+0.269
ergus+0.256
idth+0.251
edom+0.246
Neg logit contributions
 Ake-0.188
 Scand-0.178
ewski-0.165
do-0.158
arov-0.152
Token (
Token ID357
Feature activation-4.70e-01

Pos logit contributions
 Ake+0.129
 Scand+0.124
ewski+0.117
do+0.112
arov+0.109
Neg logit contributions
retty-0.145
emouth-0.130
ergus-0.123
idth-0.120
edom-0.118
TokenNT
Token ID11251
Feature activation+6.11e-02

Pos logit contributions
retty+0.402
emouth+0.365
ergus+0.346
idth+0.338
edom+0.331
Neg logit contributions
 Ake-0.309
 Scand-0.296
ewski-0.278
do-0.267
arov-0.258
Token).
Token ID737
Feature activation+1.14e-01

Pos logit contributions
 Ake+0.043
 Scand+0.041
ewski+0.039
do+0.037
arov+0.036
Neg logit contributions
retty-0.050
emouth-0.045
ergus-0.042
idth-0.041
edom-0.040
Token In
Token ID554
Feature activation-2.65e-01

Pos logit contributions
 Ake+0.080
 Scand+0.076
ewski+0.072
do+0.069
arov+0.067
Neg logit contributions
retty-0.093
emouth-0.084
ergus-0.080
idth-0.078
edom-0.076
Token when
Token ID618
Feature activation+6.93e-02

Pos logit contributions
retty+0.055
emouth+0.050
ergus+0.047
idth+0.046
edom+0.045
Neg logit contributions
 Ake-0.047
 Scand-0.045
ewski-0.043
do-0.041
arov-0.040
Token they
Token ID484
Feature activation-2.84e-02

Pos logit contributions
 Ake+0.048
 Scand+0.046
ewski+0.044
do+0.042
arov+0.041
Neg logit contributions
retty-0.056
emouth-0.051
ergus-0.048
idth-0.047
edom-0.046
Token use
Token ID779
Feature activation+7.93e-02

Pos logit contributions
retty+0.023
emouth+0.021
ergus+0.019
idth+0.019
edom+0.019
Neg logit contributions
 Ake-0.020
 Scand-0.019
ewski-0.018
do-0.017
arov-0.017
Token that
Token ID326
Feature activation+2.54e-01

Pos logit contributions
 Ake+0.057
 Scand+0.055
ewski+0.051
do+0.049
arov+0.048
Neg logit contributions
retty-0.063
emouth-0.057
ergus-0.054
idth-0.052
edom-0.051
Token information
Token ID1321
Feature activation-3.08e-01

Pos logit contributions
 Ake+0.177
 Scand+0.169
ewski+0.159
do+0.153
arov+0.149
Neg logit contributions
retty-0.207
emouth-0.187
ergus-0.177
idth-0.173
edom-0.170
Token to
Token ID284
Feature activation-3.15e-01

Pos logit contributions
retty+0.258
emouth+0.233
ergus+0.221
idth+0.216
edom+0.211
Neg logit contributions
 Ake-0.209
 Scand-0.200
ewski-0.187
do-0.180
arov-0.175
Token take
Token ID1011
Feature activation-4.01e-01

Pos logit contributions
retty+0.249
emouth+0.224
ergus+0.212
idth+0.206
edom+0.202
Neg logit contributions
 Ake-0.228
 Scand-0.219
ewski-0.206
do-0.199
arov-0.193
Token a
Token ID257
Feature activation+2.85e-01

Pos logit contributions
retty+0.330
emouth+0.298
ergus+0.282
idth+0.275
edom+0.270
Neg logit contributions
 Ake-0.279
 Scand-0.267
ewski-0.251
do-0.241
arov-0.234
Token disciplinary
Token ID24737
Feature activation+2.34e-01

Pos logit contributions
 Ake+0.208
 Scand+0.199
ewski+0.189
do+0.181
arov+0.177
Neg logit contributions
retty-0.224
emouth-0.201
ergus-0.190
idth-0.185
edom-0.181
Token action
Token ID2223
Feature activation-7.62e-02

Pos logit contributions
 Ake+0.139
 Scand+0.132
ewski+0.123
do+0.117
arov+0.113
Neg logit contributions
retty-0.215
emouth-0.197
ergus-0.188
idth-0.184
edom-0.180
Token that
Token ID326
Feature activation+2.04e-01

Pos logit contributions
retty+0.063
emouth+0.057
ergus+0.054
idth+0.053
edom+0.052
Neg logit contributions
 Ake-0.052
 Scand-0.050
ewski-0.047
do-0.045
arov-0.044
Token when
Token ID618
Feature activation+3.31e-01

Pos logit contributions
 Ake+0.064
 Scand+0.062
ewski+0.058
do+0.056
arov+0.054
Neg logit contributions
retty-0.076
emouth-0.068
ergus-0.065
idth-0.063
edom-0.062
Token he
Token ID339
Feature activation+1.36e-01

Pos logit contributions
 Ake+0.227
 Scand+0.218
ewski+0.205
do+0.196
arov+0.191
Neg logit contributions
retty-0.272
emouth-0.246
ergus-0.233
idth-0.227
edom-0.223
Token woke
Token ID19092
Feature activation-3.34e-01

Pos logit contributions
 Ake+0.097
 Scand+0.094
ewski+0.088
do+0.085
arov+0.082
Neg logit contributions
retty-0.108
emouth-0.098
ergus-0.092
idth-0.090
edom-0.088
Token up
Token ID510
Feature activation-2.45e-01

Pos logit contributions
retty+0.266
emouth+0.239
ergus+0.226
idth+0.220
edom+0.216
Neg logit contributions
 Ake-0.241
 Scand-0.230
ewski-0.217
do-0.209
arov-0.203
Token around
Token ID1088
Feature activation-2.32e-01

Pos logit contributions
retty+0.202
emouth+0.182
ergus+0.173
idth+0.169
edom+0.165
Neg logit contributions
 Ake-0.170
 Scand-0.163
ewski-0.153
do-0.147
arov-0.143
Token 3
Token ID513
Feature activation-2.65e-01

Pos logit contributions
retty+0.195
emouth+0.177
ergus+0.168
idth+0.164
edom+0.161
Neg logit contributions
 Ake-0.156
 Scand-0.150
ewski-0.140
do-0.135
arov-0.130
Token:
Token ID25
Feature activation+2.00e-01

Pos logit contributions
retty+0.220
emouth+0.199
ergus+0.189
idth+0.184
edom+0.181
Neg logit contributions
 Ake-0.181
 Scand-0.173
ewski-0.162
do-0.156
arov-0.151
Token48
Token ID2780
Feature activation+1.30e-02

Pos logit contributions
 Ake+0.114
 Scand+0.109
ewski+0.101
do+0.095
arov+0.092
Neg logit contributions
retty-0.189
emouth-0.173
ergus-0.165
idth-0.161
edom-0.159
Token a
Token ID257
Feature activation+6.40e-02

Pos logit contributions
 Ake+0.009
 Scand+0.009
ewski+0.008
do+0.008
arov+0.008
Neg logit contributions
retty-0.010
emouth-0.009
ergus-0.009
idth-0.009
edom-0.008
Token.
Token ID13
Feature activation-7.24e-02

Pos logit contributions
 Ake+0.046
 Scand+0.044
ewski+0.041
do+0.040
arov+0.039
Neg logit contributions
retty-0.051
emouth-0.046
ergus-0.044
idth-0.042
edom-0.042
Tokenm
Token ID76
Feature activation-4.08e-02

Pos logit contributions
retty+0.050
emouth+0.044
ergus+0.041
idth+0.040
edom+0.039
Neg logit contributions
 Ake-0.060
 Scand-0.058
ewski-0.055
do-0.053
arov-0.052
Token you
Token ID345
Feature activation-3.10e-01

Pos logit contributions
retty+0.265
emouth+0.239
ergus+0.226
idth+0.220
edom+0.216
Neg logit contributions
 Ake-0.239
 Scand-0.230
ewski-0.216
do-0.208
arov-0.202
Token may
Token ID743
Feature activation-6.13e-01

Pos logit contributions
retty+0.254
emouth+0.229
ergus+0.217
idth+0.212
edom+0.207
Neg logit contributions
 Ake-0.217
 Scand-0.208
ewski-0.195
do-0.188
arov-0.182
Token find
Token ID1064
Feature activation-1.36e-01

Pos logit contributions
retty+0.482
emouth+0.434
ergus+0.409
idth+0.398
edom+0.391
Neg logit contributions
 Ake-0.449
 Scand-0.430
ewski-0.406
do-0.391
arov-0.381
Token yourself
Token ID3511
Feature activation-4.04e-01

Pos logit contributions
retty+0.111
emouth+0.100
ergus+0.094
idth+0.092
edom+0.090
Neg logit contributions
 Ake-0.095
 Scand-0.091
ewski-0.086
do-0.082
arov-0.080
Token stuck
Token ID7819
Feature activation-3.78e-01

Pos logit contributions
retty+0.321
emouth+0.289
ergus+0.273
idth+0.267
edom+0.261
Neg logit contributions
 Ake-0.290
 Scand-0.278
ewski-0.262
do-0.252
arov-0.246
Token with
Token ID351
Feature activation-2.07e-01

Pos logit contributions
retty+0.309
emouth+0.279
ergus+0.264
idth+0.258
edom+0.253
Neg logit contributions
 Ake-0.263
 Scand-0.252
ewski-0.237
do-0.228
arov-0.221
Token the
Token ID262
Feature activation-4.19e-01

Pos logit contributions
retty+0.168
emouth+0.151
ergus+0.143
idth+0.140
edom+0.137
Neg logit contributions
 Ake-0.146
 Scand-0.140
ewski-0.132
do-0.127
arov-0.123
Token Token
Token ID29130
Feature activation-5.67e-01

Pos logit contributions
retty+0.342
emouth+0.309
ergus+0.292
idth+0.285
edom+0.280
Neg logit contributions
 Ake-0.293
 Scand-0.281
ewski-0.264
do-0.254
arov-0.247
Token while
Token ID981
Feature activation-3.92e-01

Pos logit contributions
retty+0.466
emouth+0.420
ergus+0.398
idth+0.389
edom+0.381
Neg logit contributions
 Ake-0.393
 Scand-0.377
ewski-0.354
do-0.340
arov-0.331
Token your
Token ID534
Feature activation-3.73e-01

Pos logit contributions
retty+0.324
emouth+0.293
ergus+0.278
idth+0.271
edom+0.266
Neg logit contributions
 Ake-0.270
 Scand-0.259
ewski-0.242
do-0.233
arov-0.226
Token opponent
Token ID6125
Feature activation-3.33e-01

Pos logit contributions
retty+0.285
emouth+0.256
ergus+0.241
idth+0.234
edom+0.230
Neg logit contributions
 Ake-0.279
 Scand-0.268
ewski-0.253
do-0.244
arov-0.238
Token non
Token ID1729
Feature activation-4.63e-01

Pos logit contributions
retty+0.404
emouth+0.364
ergus+0.344
idth+0.337
edom+0.330
Neg logit contributions
 Ake-0.357
 Scand-0.343
ewski-0.321
do-0.309
arov-0.300
Token-
Token ID12
Feature activation+3.46e-03

Pos logit contributions
retty+0.390
emouth+0.353
ergus+0.335
idth+0.328
edom+0.321
Neg logit contributions
 Ake-0.310
 Scand-0.297
ewski-0.278
do-0.268
arov-0.259
Tokenprofit
Token ID9183
Feature activation-4.46e-01

Pos logit contributions
 Ake+0.002
 Scand+0.002
ewski+0.002
do+0.002
arov+0.002
Neg logit contributions
retty-0.003
emouth-0.003
ergus-0.003
idth-0.003
edom-0.003
Token group
Token ID1448
Feature activation-2.63e-02

Pos logit contributions
retty+0.349
emouth+0.313
ergus+0.296
idth+0.289
edom+0.282
Neg logit contributions
 Ake-0.327
 Scand-0.315
ewski-0.296
do-0.285
arov-0.278
Token,
Token ID11
Feature activation+2.70e-03

Pos logit contributions
retty+0.021
emouth+0.019
ergus+0.018
idth+0.018
edom+0.018
Neg logit contributions
 Ake-0.018
 Scand-0.018
ewski-0.017
do-0.016
arov-0.015
Token comm
Token ID725
Feature activation-4.66e-01

Pos logit contributions
 Ake+0.002
 Scand+0.002
ewski+0.002
do+0.002
arov+0.002
Neg logit contributions
retty-0.002
emouth-0.002
ergus-0.002
idth-0.002
edom-0.002
Tokenutes
Token ID1769
Feature activation-2.02e-01

Pos logit contributions
retty+0.355
emouth+0.318
ergus+0.300
idth+0.292
edom+0.285
Neg logit contributions
 Ake-0.350
 Scand-0.336
ewski-0.318
do-0.307
arov-0.298
Token from
Token ID422
Feature activation+1.49e-01

Pos logit contributions
retty+0.166
emouth+0.150
ergus+0.142
idth+0.139
edom+0.136
Neg logit contributions
 Ake-0.140
 Scand-0.135
ewski-0.126
do-0.121
arov-0.118
Token her
Token ID607
Feature activation-4.50e-02

Pos logit contributions
 Ake+0.102
 Scand+0.097
ewski+0.091
do+0.088
arov+0.085
Neg logit contributions
retty-0.124
emouth-0.113
ergus-0.107
idth-0.104
edom-0.102
Token home
Token ID1363
Feature activation+3.47e-02

Pos logit contributions
retty+0.038
emouth+0.034
ergus+0.032
idth+0.031
edom+0.031
Neg logit contributions
 Ake-0.031
 Scand-0.029
ewski-0.027
do-0.026
arov-0.026
Token in
Token ID287
Feature activation-3.34e-02

Pos logit contributions
 Ake+0.024
 Scand+0.023
ewski+0.022
do+0.021
arov+0.020
Neg logit contributions
retty-0.028
emouth-0.026
ergus-0.024
idth-0.024
edom-0.023
Token Walking
Token ID21276
Feature activation-1.00e+00

Pos logit contributions
retty+0.275
emouth+0.250
ergus+0.237
idth+0.231
edom+0.227
Neg logit contributions
 Ake-0.218
 Scand-0.208
ewski-0.195
do-0.187
arov-0.181
Token Dead
Token ID5542
Feature activation-5.39e-01

Pos logit contributions
retty+0.748
emouth+0.664
ergus+0.624
idth+0.609
edom+0.596
Neg logit contributions
 Ake-0.778
 Scand-0.749
ewski-0.704
do-0.682
arov-0.665
Token and
Token ID290
Feature activation+4.60e-03

Pos logit contributions
retty+0.449
emouth+0.406
ergus+0.385
idth+0.376
edom+0.369
Neg logit contributions
 Ake-0.368
 Scand-0.352
ewski-0.330
do-0.317
arov-0.307
Token An
Token ID1052
Feature activation-7.71e-01

Pos logit contributions
 Ake+0.003
 Scand+0.003
ewski+0.003
do+0.003
arov+0.003
Neg logit contributions
retty-0.004
emouth-0.003
ergus-0.003
idth-0.003
edom-0.003
Token American
Token ID1605
Feature activation-1.35e+00

Pos logit contributions
retty+0.620
emouth+0.554
ergus+0.525
idth+0.511
edom+0.499
Neg logit contributions
 Ake-0.552
 Scand-0.532
ewski-0.497
do-0.482
arov-0.468
Token Werewolf
Token ID40261
Feature activation-1.58e+00

Pos logit contributions
retty+0.918
emouth+0.807
ergus+0.754
idth+0.736
edom+0.707
Neg logit contributions
 Ake-1.141
 Scand-1.102
ewski-1.037
do-1.008
arov-0.987
Token in
Token ID287
Feature activation-9.94e-01

Pos logit contributions
retty+1.351
emouth+1.219
ergus+1.158
idth+1.130
edom+1.106
Neg logit contributions
 Ake-1.066
 Scand-1.017
ewski-0.926
do-0.911
arov-0.881
Token London
Token ID3576
Feature activation-1.96e-01

Pos logit contributions
retty+0.961
emouth+0.881
ergus+0.844
idth+0.829
edom+0.814
Neg logit contributions
 Ake-0.545
 Scand-0.520
ewski-0.472
do-0.450
der-0.432
Token.
Token ID13
Feature activation+1.71e-01

Pos logit contributions
retty+0.158
emouth+0.143
ergus+0.135
idth+0.132
edom+0.129
Neg logit contributions
 Ake-0.138
 Scand-0.132
ewski-0.125
do-0.120
arov-0.116
Token
Token ID198
Feature activation+1.22e-01

Pos logit contributions
 Ake+0.120
 Scand+0.115
ewski+0.108
do+0.103
arov+0.101
Neg logit contributions
retty-0.139
emouth-0.126
ergus-0.119
idth-0.116
edom-0.114
Token
Token ID198
Feature activation+2.94e-01

Pos logit contributions
 Ake+0.085
 Scand+0.082
ewski+0.077
do+0.074
arov+0.072
Neg logit contributions
retty-0.099
emouth-0.090
ergus-0.085
idth-0.083
edom-0.081
Token Chris
Token ID5180
Feature activation+2.14e-01

Pos logit contributions
retty+0.147
emouth+0.133
ergus+0.126
idth+0.123
edom+0.120
Neg logit contributions
 Ake-0.128
 Scand-0.123
ewski-0.115
do-0.111
arov-0.108
Token Sutton
Token ID39964
Feature activation-2.74e-01

Pos logit contributions
 Ake+0.161
 Scand+0.154
ewski+0.146
do+0.141
arov+0.137
Neg logit contributions
retty-0.163
emouth-0.146
ergus-0.137
idth-0.134
edom-0.131
Token,
Token ID11
Feature activation-1.05e-01

Pos logit contributions
retty+0.226
emouth+0.204
ergus+0.193
idth+0.189
edom+0.185
Neg logit contributions
 Ake-0.190
 Scand-0.182
ewski-0.171
do-0.164
arov-0.159
Token probably
Token ID2192
Feature activation-5.33e-01

Pos logit contributions
retty+0.086
emouth+0.078
ergus+0.074
idth+0.072
edom+0.071
Neg logit contributions
 Ake-0.073
 Scand-0.070
ewski-0.066
do-0.063
arov-0.061
Token no
Token ID645
Feature activation-3.92e-01

Pos logit contributions
retty+0.434
emouth+0.391
ergus+0.371
idth+0.362
edom+0.354
Neg logit contributions
 Ake-0.374
 Scand-0.358
ewski-0.336
do-0.323
arov-0.314
Token Kenny
Token ID22102
Feature activation-1.68e+00

Pos logit contributions
retty+0.316
emouth+0.285
ergus+0.269
idth+0.263
edom+0.257
Neg logit contributions
 Ake-0.278
 Scand-0.266
ewski-0.250
do-0.240
arov-0.233
Token Dal
Token ID12348
Feature activation+4.27e-01

Pos logit contributions
retty+1.363
emouth+1.223
ergus+1.160
idth+1.143
edom+1.120
Neg logit contributions
 Ake-1.195
 Scand-1.136
ewski-1.062
do-1.021
arov-0.991
Tokeng
Token ID70
Feature activation-2.47e-01

Pos logit contributions
 Ake+0.251
 Scand+0.239
ewski+0.222
do+0.210
arov+0.203
Neg logit contributions
retty-0.395
emouth-0.362
ergus-0.346
idth-0.338
edom-0.332
Tokenlish
Token ID1836
Feature activation-2.12e-01

Pos logit contributions
retty+0.217
emouth+0.197
ergus+0.188
idth+0.183
edom+0.180
Neg logit contributions
 Ake-0.157
 Scand-0.150
ewski-0.140
do-0.134
arov-0.130
Token either
Token ID2035
Feature activation+5.42e-02

Pos logit contributions
retty+0.174
emouth+0.157
ergus+0.149
idth+0.145
edom+0.142
Neg logit contributions
 Ake-0.147
 Scand-0.141
ewski-0.133
do-0.127
arov-0.124
Token,
Token ID11
Feature activation-1.57e-01

Pos logit contributions
 Ake+0.038
 Scand+0.037
ewski+0.035
do+0.033
arov+0.032
Neg logit contributions
retty-0.044
emouth-0.039
ergus-0.037
idth-0.036
edom-0.036
Token Invisible
Token ID39571
Feature activation-5.60e-01

Pos logit contributions
retty+0.242
emouth+0.219
ergus+0.208
idth+0.203
edom+0.199
Neg logit contributions
 Ake-0.199
 Scand-0.190
ewski-0.178
do-0.171
arov-0.166
Token Man
Token ID1869
Feature activation-2.54e-01

Pos logit contributions
retty+0.506
emouth+0.462
ergus+0.439
idth+0.430
edom+0.423
Neg logit contributions
 Ake-0.344
 Scand-0.328
ewski-0.302
do-0.290
arov-0.280
Token,
Token ID11
Feature activation+7.89e-02

Pos logit contributions
retty+0.210
emouth+0.190
ergus+0.180
idth+0.176
edom+0.172
Neg logit contributions
 Ake-0.175
 Scand-0.167
ewski-0.157
do-0.151
arov-0.147
Token The
Token ID383
Feature activation-2.57e-01

Pos logit contributions
 Ake+0.054
 Scand+0.052
ewski+0.049
do+0.047
arov+0.045
Neg logit contributions
retty-0.065
emouth-0.059
ergus-0.056
idth-0.055
edom-0.054
Token H
Token ID367
Feature activation-7.93e-01

Pos logit contributions
retty+0.216
emouth+0.196
ergus+0.186
idth+0.181
edom+0.178
Neg logit contributions
 Ake-0.173
 Scand-0.166
ewski-0.155
do-0.149
arov-0.145
Tokenunch
Token ID3316
Feature activation-1.61e+00

Pos logit contributions
retty+0.496
emouth+0.436
ergus+0.401
idth+0.389
edom+0.378
Neg logit contributions
 Ake-0.702
 Scand-0.680
ewski-0.651
do-0.631
arov-0.616
Tokenback
Token ID1891
Feature activation-1.53e-01

Pos logit contributions
retty+1.477
emouth+1.363
ergus+1.280
idth+1.257
edom+1.244
Neg logit contributions
 Ake-0.967
 Scand-0.916
ewski-0.845
do-0.825
arov-0.793
Token of
Token ID286
Feature activation-1.46e-01

Pos logit contributions
retty+0.124
emouth+0.111
ergus+0.106
idth+0.103
edom+0.101
Neg logit contributions
 Ake-0.109
 Scand-0.104
ewski-0.098
do-0.094
arov-0.092
Token Notre
Token ID23382
Feature activation-8.59e-01

Pos logit contributions
retty+0.115
emouth+0.103
ergus+0.097
idth+0.095
edom+0.093
Neg logit contributions
 Ake-0.106
 Scand-0.102
ewski-0.096
do-0.092
arov-0.090
Token Dame
Token ID20377
Feature activation-3.32e-01

Pos logit contributions
retty+0.560
emouth+0.491
ergus+0.454
idth+0.442
edom+0.430
Neg logit contributions
 Ake-0.745
 Scand-0.723
ewski-0.683
do-0.669
arov-0.648
Token,
Token ID11
Feature activation+3.80e-02

Pos logit contributions
retty+0.276
emouth+0.249
ergus+0.236
idth+0.231
edom+0.226
Neg logit contributions
 Ake-0.228
 Scand-0.218
ewski-0.204
do-0.196
arov-0.191
Token the
Token ID262
Feature activation-3.46e-01

Pos logit contributions
retty+0.114
emouth+0.103
ergus+0.097
idth+0.095
edom+0.093
Neg logit contributions
 Ake-0.094
 Scand-0.090
ewski-0.084
do-0.081
arov-0.079
Token director
Token ID3437
Feature activation-5.77e-01

Pos logit contributions
retty+0.273
emouth+0.245
ergus+0.232
idth+0.225
edom+0.221
Neg logit contributions
 Ake-0.252
 Scand-0.242
ewski-0.228
do-0.219
arov-0.213
Token is
Token ID318
Feature activation+3.54e-02

Pos logit contributions
retty+0.476
emouth+0.431
ergus+0.408
idth+0.397
edom+0.390
Neg logit contributions
 Ake-0.397
 Scand-0.381
ewski-0.357
do-0.343
arov-0.333
Token eyeing
Token ID48847
Feature activation-2.71e-01

Pos logit contributions
 Ake+0.025
 Scand+0.024
ewski+0.022
do+0.022
arov+0.021
Neg logit contributions
retty-0.029
emouth-0.026
ergus-0.024
idth-0.024
edom-0.023
Token The
Token ID383
Feature activation-6.14e-01

Pos logit contributions
retty+0.220
emouth+0.198
ergus+0.188
idth+0.182
edom+0.179
Neg logit contributions
 Ake-0.191
 Scand-0.183
ewski-0.172
do-0.165
arov-0.160
Token New
Token ID968
Feature activation-1.53e+00

Pos logit contributions
retty+0.491
emouth+0.443
ergus+0.419
idth+0.406
edom+0.399
Neg logit contributions
 Ake-0.439
 Scand-0.423
ewski-0.397
do-0.383
arov-0.371
Token 52
Token ID6740
Feature activation-3.29e-01

Pos logit contributions
retty+1.247
emouth+1.111
ergus+1.058
idth+1.013
edom+1.010
Neg logit contributions
 Ake-1.089
 Scand-1.042
ewski-0.973
do-0.952
arov-0.914
Token for
Token ID329
Feature activation+5.94e-03

Pos logit contributions
retty+0.270
emouth+0.243
ergus+0.230
idth+0.224
edom+0.220
Neg logit contributions
 Ake-0.229
 Scand-0.219
ewski-0.206
do-0.198
arov-0.192
Token inspiration
Token ID12141
Feature activation-1.01e-01

Pos logit contributions
 Ake+0.004
 Scand+0.004
ewski+0.004
do+0.004
arov+0.004
Neg logit contributions
retty-0.005
emouth-0.004
ergus-0.004
idth-0.004
edom-0.004
Token and
Token ID290
Feature activation-2.32e-01

Pos logit contributions
retty+0.083
emouth+0.075
ergus+0.071
idth+0.069
edom+0.068
Neg logit contributions
 Ake-0.070
 Scand-0.067
ewski-0.063
do-0.061
arov-0.059
Token hoping
Token ID7725
Feature activation+1.62e-01

Pos logit contributions
retty+0.188
emouth+0.170
ergus+0.161
idth+0.156
edom+0.154
Neg logit contributions
 Ake-0.163
 Scand-0.157
ewski-0.147
do-0.141
arov-0.137
Token Big
Token ID4403
Feature activation-7.29e-01

Pos logit contributions
retty+0.442
emouth+0.399
ergus+0.377
idth+0.368
edom+0.361
Neg logit contributions
 Ake-0.385
 Scand-0.370
ewski-0.345
do-0.333
arov-0.323
Token Bang
Token ID9801
Feature activation+1.67e-01

Pos logit contributions
retty+0.480
emouth+0.424
ergus+0.395
idth+0.382
edom+0.375
Neg logit contributions
 Ake-0.624
 Scand-0.602
ewski-0.572
do-0.557
arov-0.541
Token Theory
Token ID17003
Feature activation+1.70e-01

Pos logit contributions
 Ake+0.069
 Scand+0.064
ewski+0.057
do+0.053
arov+0.050
Neg logit contributions
retty-0.184
emouth-0.171
ergus-0.164
idth-0.161
edom-0.159
Token CBS
Token ID11133
Feature activation-2.44e-02

Pos logit contributions
 Ake+0.113
 Scand+0.108
ewski+0.101
do+0.097
arov+0.094
Neg logit contributions
retty-0.144
emouth-0.130
ergus-0.124
idth-0.121
edom-0.118
Token Amy
Token ID14235
Feature activation-1.09e-01

Pos logit contributions
retty+0.020
emouth+0.018
ergus+0.017
idth+0.017
edom+0.016
Neg logit contributions
 Ake-0.017
 Scand-0.016
ewski-0.015
do-0.015
arov-0.014
Token Poe
Token ID34815
Feature activation-2.48e+00

Pos logit contributions
retty+0.085
emouth+0.076
ergus+0.072
idth+0.070
edom+0.069
Neg logit contributions
 Ake-0.081
 Scand-0.078
ewski-0.073
do-0.070
arov-0.069
Tokenhler
Token ID49737
Feature activation+2.96e-02

Pos logit contributions
retty+1.746
emouth+1.582
ergus+1.453
idth+1.398
edom+1.380
Neg logit contributions
 Ake-2.044
 Scand-1.964
ewski-1.850
do-1.791
der-1.772
Token Parks
Token ID20604
Feature activation-3.43e-01

Pos logit contributions
 Ake+0.020
 Scand+0.020
ewski+0.018
do+0.018
arov+0.017
Neg logit contributions
retty-0.024
emouth-0.022
ergus-0.021
idth-0.020
edom-0.020
Token and
Token ID290
Feature activation-1.14e+00

Pos logit contributions
retty+0.284
emouth+0.257
ergus+0.243
idth+0.237
edom+0.233
Neg logit contributions
 Ake-0.236
 Scand-0.226
ewski-0.212
do-0.203
arov-0.197
Token Recreation
Token ID34285
Feature activation+7.19e-02

Pos logit contributions
retty+0.889
emouth+0.794
ergus+0.752
idth+0.739
edom+0.718
Neg logit contributions
 Ake-0.849
 Scand-0.822
ewski-0.764
do-0.737
arov-0.724
Token NBC
Token ID9716
Feature activation+3.55e-02

Pos logit contributions
 Ake+0.047
 Scand+0.045
ewski+0.042
do+0.040
arov+0.039
Neg logit contributions
retty-0.062
emouth-0.056
ergus-0.053
idth-0.052
edom-0.051