TOP ACTIVATIONS
MAX = 1.364

d 1 . Old gift be arer setting box underneath
object system . draw ing . bit map ($ SR .
( 7 ) T I –– This swim
and convicted in the past , including on assault charges ,
1 d 1 . Old gift be arer setting box
Tuesday , a second trailer for Sn atched was officially released
but it is containing everything and beyond the universe of the
and obesity combined ( B MI 25 kg / m
PF Bentley / Civil Beat Good win
millionaires , Ms . Ole ch owski said .
= [ system . windows . forms . text rend erer
- based Anat ol iy D erk ach , the owner
life , in her latest movie , Sn atched , Schumer
Johannes Brah ms : Life and Letters , MacDonald learned that
, was a distinguished veteran ," Stra ub said . "...
[ system . draw ing . String Al ignment ] ::
Russia s goal since the creation of NATO .
} at least one blank character (< Space > or <
PF Bentley / Civil Beat C ald
10 or more to help us continue to write about the

MIN ACTIVATIONS
MIN = -1.620

RI ER 11 a 11 . Weapon person loaded
Week end T ear V oid Ray J KS Le en
- a - det ailed - review The ability
42 3 355 ; mart in rand all . com ),
AK NOW LED G ED NET CALL UPDATE : 05 42
AK NOW LED G ED NET CALL UPDATE : 05 43
takeover of V enez ue ... From Vox :
move on 11 a 11 . Weapon person loaded
activist had received th rea ... From : A
{ pub fn load < ' a > ( & self
AK NOW LED G ED NET CALL UPDATE : 05 50
Diego . Sit ' Em I don
{ ... } impl < ' a , T > Copy
2006 Kevin James 2006 Charlie Sheen 2007 Ricky
AK NOW LED G ED NET CALL UPDATE : 05 41
There are knit - a ... <|endoftext|> Buy Photo F SU
FOR M EST OP V B 5 92 4 78 NET
Power = 20 dB m Ret ry short limit : 7
T AT 1 a 1 . Sw immer means
ACK H AT , rect K ernel ) 17 18 19

INTERVAL 0.618 - 1.364
CONTAINS 0.248%

. V ac ation Time Cat
8 to 7 8
While finding a " fail ure mode " affected the air
а а с т у
а м н и к о�

INTERVAL -0.128 - 0.618
CONTAINS 73.806%

in a computer malfunction , and released them Tuesday .
as Ma ureen Dow d recounted in the New York Times
ph ases added ]," r aves the Los Angeles Times .
only the room where the monkey is currently in is illuminated
items . The rationale for the policy change given

INTERVAL -0.874 - -0.128
CONTAINS 25.931%

, this line just keeps working .) There was some #
blogger , who made a video of himself playing Pokemon Go
On 10 October 1941 those fronts were merged into the Western
re going to have to leave .
it but I sent it in and J BL sent me

INTERVAL -1.620 - -0.874
CONTAINS 0.015%

9 - to - 5 Working Women Education Fund : ...
to create values and give these values names was
42 3 355 ; mart in rand all . com ),
becoming the 24 th player to do so . We provide
hardware virtual ization for CPUs and memory ( VT - x
Tokend
Token ID67
Feature activation-7.16e-01

Pos logit contributions
heit+1.959
agher+1.951
 Strat+1.897
ega+1.868
llah+1.857
Neg logit contributions
 CoC-2.020
\--2.011
hran-2.006
Mem-1.936
 sandy-1.932
Token 1
Token ID352
Feature activation-6.64e-02

Pos logit contributions
\-+5.122
hran+5.003
 CoC+5.000
Mem+4.879
 sandy+4.803
Neg logit contributions
heit-6.021
agher-5.893
 Strat-5.685
llah-5.644
ega-5.614
Token.
Token ID13
Feature activation+2.62e-01

Pos logit contributions
\-+0.496
 CoC+0.488
hran+0.478
Mem+0.470
 sandy+0.460
Neg logit contributions
heit-0.566
agher-0.560
inav-0.542
 Strat-0.541
llah-0.535
Token Old
Token ID5706
Feature activation-3.68e-01

Pos logit contributions
heit+2.202
agher+2.191
 Strat+2.175
inav+2.110
ega+2.097
Neg logit contributions
\--1.922
hran-1.910
 CoC-1.899
Mem-1.827
 sandy-1.813
Token gift
Token ID6979
Feature activation+1.15e+00

Pos logit contributions
\-+2.289
 CoC+2.265
hran+2.233
Mem+2.172
 sandy+2.159
Neg logit contributions
heit-3.546
agher-3.497
 Strat-3.429
inav-3.394
llah-3.385
Token
Token ID1906
Feature activation+1.36e+00

Pos logit contributions
heit+5.960
 Strat+5.749
agher+5.670
ega+5.497
inav+5.335
Neg logit contributions
 CoC-11.175
hran-11.156
\--10.871
Mem-10.711
}}}-10.662
Tokenbe
Token ID1350
Feature activation+7.41e-01

Pos logit contributions
heit+7.879
agher+7.731
ega+7.583
rail+7.232
inav+7.090
Neg logit contributions
 CoC-12.247
hran-11.902
���-11.576
\--11.552
 Fior-11.546
Tokenarer
Token ID11258
Feature activation+9.83e-01

Pos logit contributions
agher+1.804
heit+1.619
inav+1.377
ega+1.362
 Strat+1.329
Neg logit contributions
 CoC-9.939
\--9.775
hran-9.700
Mem-9.678
 sandy-9.665
Token setting
Token ID4634
Feature activation+6.20e-01

Pos logit contributions
 Strat+4.439
heit+4.176
agher+4.152
ega+3.719
inav+3.697
Neg logit contributions
hran-10.671
\--10.612
 CoC-10.468
Mem-10.404
Pir-10.249
Token box
Token ID3091
Feature activation+6.01e-01

Pos logit contributions
heit+1.407
 Strat+1.378
agher+1.351
ega+1.275
llah+1.208
Neg logit contributions
hran-8.167
\--8.115
 CoC-8.101
Mem-8.040
Serv-8.000
Token underneath
Token ID14638
Feature activation+5.45e-01

Pos logit contributions
heit+4.406
agher+4.372
llah+4.209
 Strat+4.182
ega+4.162
Neg logit contributions
\--4.994
hran-4.991
 CoC-4.978
Mem-4.827
Serv-4.748
Tokenobject
Token ID15252
Feature activation+9.25e-01

Pos logit contributions
heit+4.970
agher+4.880
ega+4.767
 Strat+4.760
inav+4.714
Neg logit contributions
hran-4.936
 CoC-4.914
 sandy-4.713
\--4.701
Mem-4.507
Token system
Token ID1080
Feature activation+9.23e-02

Pos logit contributions
 Strat+5.583
heit+5.358
ega+5.253
inav+5.066
agher+5.062
Neg logit contributions
hran-8.489
 CoC-8.226
\--8.180
Mem-8.048
Serv-7.918
Token.
Token ID13
Feature activation+5.34e-01

Pos logit contributions
heit+0.730
agher+0.718
 Strat+0.703
inav+0.692
ega+0.688
Neg logit contributions
\--0.734
 CoC-0.733
hran-0.731
 sandy-0.703
Mem-0.701
Tokendraw
Token ID19334
Feature activation+1.29e-01

Pos logit contributions
heit+2.832
agher+2.729
ega+2.680
 Strat+2.636
llah+2.629
Neg logit contributions
 CoC-5.517
hran-5.396
 sandy-5.372
\--5.358
 Lex-5.206
Tokening
Token ID278
Feature activation+6.64e-01

Pos logit contributions
heit+1.054
agher+1.042
 Strat+1.018
inav+1.005
llah+0.998
Neg logit contributions
\--0.996
 CoC-0.982
hran-0.979
Mem-0.947
 sandy-0.937
Token.
Token ID13
Feature activation+1.32e+00

Pos logit contributions
heit+4.299
 Strat+4.150
agher+4.082
ega+3.972
llah+3.958
Neg logit contributions
hran-6.024
 CoC-5.906
���-5.879
 sandy-5.820
\--5.729
Tokenbit
Token ID2545
Feature activation+3.50e-01

Pos logit contributions
heit+8.964
ega+8.626
agher+8.508
 Strat+8.298
llah+8.289
Neg logit contributions
 CoC-10.087
hran-9.649
 sandy-9.603
 Fior-9.580
 Lex-9.360
Tokenmap
Token ID8899
Feature activation+4.95e-01

Pos logit contributions
heit+3.218
agher+3.152
 Strat+3.090
inav+3.077
ega+3.059
Neg logit contributions
 CoC-2.319
hran-2.293
\--2.290
 sandy-2.196
Mem-2.169
Token($
Token ID16763
Feature activation-1.28e-01

Pos logit contributions
heit+3.333
 Strat+3.333
agher+3.241
ega+3.132
inav+3.126
Neg logit contributions
hran-4.382
 CoC-4.318
\--4.301
 sandy-4.135
Mem-4.124
TokenSR
Token ID12562
Feature activation-1.85e-01

Pos logit contributions
\-+1.037
 CoC+1.014
hran+1.011
Mem+0.989
 sandy+0.969
Neg logit contributions
heit-1.002
agher-0.990
 Strat-0.966
inav-0.954
llah-0.942
Token.
Token ID13
Feature activation+2.69e-01

Pos logit contributions
\-+1.368
 CoC+1.355
hran+1.348
Mem+1.301
 sandy+1.291
Neg logit contributions
heit-1.580
agher-1.560
 Strat-1.525
inav-1.509
llah-1.495
Token (
Token ID357
Feature activation+4.79e-02

Pos logit contributions
heit+2.377
agher+2.342
 Strat+2.298
inav+2.260
ega+2.241
Neg logit contributions
\--2.662
 CoC-2.632
hran-2.623
Mem-2.511
 sandy-2.508
Token7
Token ID22
Feature activation+1.32e-01

Pos logit contributions
heit+0.458
agher+0.453
 Strat+0.445
inav+0.440
ega+0.437
Neg logit contributions
\--0.305
 CoC-0.300
hran-0.300
Mem-0.288
 sandy-0.283
Token)
Token ID8
Feature activation+7.26e-01

Pos logit contributions
heit+1.152
agher+1.138
 Strat+1.115
inav+1.096
llah+1.092
Neg logit contributions
\--0.942
 CoC-0.937
hran-0.935
Mem-0.894
 sandy-0.893
Token
Token ID784
Feature activation+7.89e-01

Pos logit contributions
heit+4.444
 Strat+4.406
agher+4.374
ega+4.177
inav+4.126
Neg logit contributions
\--6.811
hran-6.800
 CoC-6.716
Mem-6.449
 sandy-6.415
Token
Token ID1906
Feature activation+8.91e-01

Pos logit contributions
heit+3.559
 Strat+3.465
agher+3.453
ega+3.243
inav+3.237
Neg logit contributions
hran-8.588
 CoC-8.561
\--8.411
 sandy-8.244
Mem-8.107
TokenT
Token ID51
Feature activation+1.25e+00

Pos logit contributions
 Strat+5.369
heit+5.356
agher+5.247
ega+4.989
inav+4.951
Neg logit contributions
hran-8.129
\--7.977
 CoC-7.960
 sandy-7.668
]}-7.491
Token
Token ID1906
Feature activation+9.75e-01

Pos logit contributions
 Strat+7.236
agher+7.169
heit+7.129
inav+6.908
ega+6.777
Neg logit contributions
hran-10.861
 CoC-10.789
\--10.643
 sandy-10.371
]}-10.211
TokenI
Token ID40
Feature activation+4.47e-01

Pos logit contributions
 Strat+6.798
heit+6.792
agher+6.681
inav+6.401
ega+6.391
Neg logit contributions
hran-8.011
 CoC-7.800
\--7.789
 sandy-7.483
Mem-7.361
Token––
Token ID25608
Feature activation+6.05e-01

Pos logit contributions
heit+3.452
agher+3.384
 Strat+3.342
inav+3.285
llah+3.254
Neg logit contributions
\--3.584
hran-3.578
 CoC-3.576
Mem-3.435
 sandy-3.425
Token This
Token ID770
Feature activation-7.78e-02

Pos logit contributions
heit+3.645
 Strat+3.525
agher+3.521
inav+3.378
llah+3.366
Neg logit contributions
hran-5.789
 CoC-5.766
\--5.742
 sandy-5.571
Mem-5.509
Token swim
Token ID9422
Feature activation+1.00e-01

Pos logit contributions
\-+0.600
 CoC+0.592
hran+0.588
Mem+0.572
 sandy+0.567
Neg logit contributions
heit-0.636
agher-0.629
 Strat-0.612
inav-0.610
ega-0.603
Token and
Token ID290
Feature activation+2.15e-01

Pos logit contributions
heit+0.939
agher+0.926
 Strat+0.904
inav+0.897
llah+0.887
Neg logit contributions
\--0.843
 CoC-0.836
hran-0.830
Mem-0.802
 sandy-0.799
Token convicted
Token ID9118
Feature activation+7.32e-02

Pos logit contributions
heit+1.630
agher+1.602
 Strat+1.576
inav+1.537
llah+1.535
Neg logit contributions
\--1.785
 CoC-1.770
hran-1.769
Mem-1.705
 sandy-1.692
Token in
Token ID287
Feature activation+3.52e-01

Pos logit contributions
heit+0.604
agher+0.596
 Strat+0.582
inav+0.576
llah+0.571
Neg logit contributions
\--0.560
 CoC-0.556
hran-0.553
Mem-0.534
 sandy-0.531
Token the
Token ID262
Feature activation+2.04e-01

Pos logit contributions
heit+2.822
agher+2.790
 Strat+2.762
inav+2.684
llah+2.675
Neg logit contributions
\--2.762
 CoC-2.721
hran-2.717
Mem-2.612
 sandy-2.583
Token past
Token ID1613
Feature activation+4.69e-02

Pos logit contributions
heit+1.776
agher+1.756
 Strat+1.723
inav+1.701
llah+1.688
Neg logit contributions
\--1.459
 CoC-1.443
hran-1.440
Mem-1.383
 sandy-1.373
Token,
Token ID11
Feature activation+1.19e+00

Pos logit contributions
heit+0.387
agher+0.382
 Strat+0.373
inav+0.369
llah+0.365
Neg logit contributions
\--0.360
 CoC-0.357
hran-0.355
Mem-0.343
 sandy-0.341
Token including
Token ID1390
Feature activation-3.96e-02

Pos logit contributions
 Strat+9.177
agher+8.680
heit+8.386
llah+8.262
ega+8.150
Neg logit contributions
hran-8.873
\--8.614
 CoC-8.602
Mem-8.381
lems-8.146
Token on
Token ID319
Feature activation+4.14e-01

Pos logit contributions
\-+0.285
 CoC+0.284
hran+0.281
 sandy+0.272
Mem+0.272
Neg logit contributions
heit-0.344
agher-0.340
inav-0.330
 Strat-0.327
llah-0.326
Token assault
Token ID4641
Feature activation-3.11e-01

Pos logit contributions
heit+3.200
agher+3.133
 Strat+3.115
llah+3.022
ega+3.019
Neg logit contributions
\--3.348
hran-3.329
 CoC-3.322
Mem-3.193
 sandy-3.155
Token charges
Token ID4530
Feature activation-3.40e-02

Pos logit contributions
\-+2.245
 CoC+2.203
hran+2.144
Mem+2.118
 sandy+2.100
Neg logit contributions
heit-2.717
agher-2.702
inav-2.618
 Strat-2.611
llah-2.550
Token,
Token ID11
Feature activation+7.45e-01

Pos logit contributions
\-+0.257
 CoC+0.254
hran+0.253
Mem+0.244
 sandy+0.243
Neg logit contributions
heit-0.286
agher-0.282
 Strat-0.274
inav-0.273
llah-0.269
Token1
Token ID16
Feature activation+2.53e-01

Pos logit contributions
\-+0.438
 CoC+0.427
hran+0.426
Mem+0.420
Serv+0.405
Neg logit contributions
heit-0.520
agher-0.511
 Strat-0.502
inav-0.494
ega-0.490
Tokend
Token ID67
Feature activation-7.16e-01

Pos logit contributions
heit+1.959
agher+1.951
 Strat+1.897
ega+1.868
llah+1.857
Neg logit contributions
 CoC-2.020
\--2.011
hran-2.006
Mem-1.936
 sandy-1.932
Token 1
Token ID352
Feature activation-6.64e-02

Pos logit contributions
\-+5.122
hran+5.003
 CoC+5.000
Mem+4.879
 sandy+4.803
Neg logit contributions
heit-6.021
agher-5.893
 Strat-5.685
llah-5.644
ega-5.614
Token.
Token ID13
Feature activation+2.62e-01

Pos logit contributions
\-+0.496
 CoC+0.488
hran+0.478
Mem+0.470
 sandy+0.460
Neg logit contributions
heit-0.566
agher-0.560
inav-0.542
 Strat-0.541
llah-0.535
Token Old
Token ID5706
Feature activation-3.68e-01

Pos logit contributions
heit+2.202
agher+2.191
 Strat+2.175
inav+2.110
ega+2.097
Neg logit contributions
\--1.922
hran-1.910
 CoC-1.899
Mem-1.827
 sandy-1.813
Token gift
Token ID6979
Feature activation+1.15e+00

Pos logit contributions
\-+2.289
 CoC+2.265
hran+2.233
Mem+2.172
 sandy+2.159
Neg logit contributions
heit-3.546
agher-3.497
 Strat-3.429
inav-3.394
llah-3.385
Token
Token ID1906
Feature activation+1.36e+00

Pos logit contributions
heit+5.960
 Strat+5.749
agher+5.670
ega+5.497
inav+5.335
Neg logit contributions
 CoC-11.175
hran-11.156
\--10.871
Mem-10.711
}}}-10.662
Tokenbe
Token ID1350
Feature activation+7.41e-01

Pos logit contributions
heit+7.879
agher+7.731
ega+7.583
rail+7.232
inav+7.090
Neg logit contributions
 CoC-12.247
hran-11.902
���-11.576
\--11.552
 Fior-11.546
Tokenarer
Token ID11258
Feature activation+9.83e-01

Pos logit contributions
agher+1.804
heit+1.619
inav+1.377
ega+1.362
 Strat+1.329
Neg logit contributions
 CoC-9.939
\--9.775
hran-9.700
Mem-9.678
 sandy-9.665
Token setting
Token ID4634
Feature activation+6.20e-01

Pos logit contributions
 Strat+4.439
heit+4.176
agher+4.152
ega+3.719
inav+3.697
Neg logit contributions
hran-10.671
\--10.612
 CoC-10.468
Mem-10.404
Pir-10.249
Token box
Token ID3091
Feature activation+6.01e-01

Pos logit contributions
heit+1.407
 Strat+1.378
agher+1.351
ega+1.275
llah+1.208
Neg logit contributions
hran-8.167
\--8.115
 CoC-8.101
Mem-8.040
Serv-8.000
Token Tuesday
Token ID3431
Feature activation+1.54e-02

Pos logit contributions
heit+3.833
agher+3.780
 Strat+3.772
ega+3.611
llah+3.601
Neg logit contributions
\--3.863
hran-3.855
 CoC-3.829
Mem-3.642
 sandy-3.611
Token,
Token ID11
Feature activation+3.64e-01

Pos logit contributions
heit+0.128
agher+0.126
 Strat+0.123
inav+0.122
llah+0.121
Neg logit contributions
\--0.118
 CoC-0.117
hran-0.116
Mem-0.113
 sandy-0.112
Token a
Token ID257
Feature activation+3.68e-01

Pos logit contributions
heit+2.859
agher+2.832
 Strat+2.796
llah+2.709
inav+2.701
Neg logit contributions
\--2.915
 CoC-2.887
hran-2.878
Mem-2.760
 sandy-2.744
Token second
Token ID1218
Feature activation+2.63e-01

Pos logit contributions
heit+2.850
 Strat+2.834
agher+2.822
llah+2.730
inav+2.717
Neg logit contributions
\--2.956
hran-2.913
 CoC-2.906
Mem-2.788
 sandy-2.757
Token trailer
Token ID12268
Feature activation+7.51e-03

Pos logit contributions
heit+2.028
agher+1.999
 Strat+1.970
llah+1.924
inav+1.922
Neg logit contributions
\--2.143
hran-2.119
 CoC-2.113
Mem-2.039
 sandy-2.023
Token for
Token ID329
Feature activation+1.14e+00

Pos logit contributions
heit+0.065
agher+0.064
 Strat+0.062
inav+0.062
llah+0.061
Neg logit contributions
\--0.055
 CoC-0.054
hran-0.054
Mem-0.052
 sandy-0.052
Token Sn
Token ID5489
Feature activation+1.10e-01

Pos logit contributions
 Strat+7.534
heit+7.216
agher+7.196
ega+7.112
llah+6.903
Neg logit contributions
\--9.663
hran-9.370
 CoC-9.337
 sandy-8.804
lems-8.737
Tokenatched
Token ID14265
Feature activation+2.43e-01

Pos logit contributions
heit+0.630
agher+0.620
 Strat+0.595
inav+0.591
ega+0.582
Neg logit contributions
\--1.124
 CoC-1.118
hran-1.114
Mem-1.083
 sandy-1.082
Token was
Token ID373
Feature activation+8.76e-02

Pos logit contributions
heit+2.011
agher+1.975
 Strat+1.958
inav+1.909
ega+1.906
Neg logit contributions
\--1.839
hran-1.828
 CoC-1.826
Mem-1.752
 sandy-1.742
Token officially
Token ID8720
Feature activation-6.38e-03

Pos logit contributions
heit+0.655
agher+0.645
 Strat+0.629
inav+0.621
llah+0.615
Neg logit contributions
\--0.738
 CoC-0.733
hran-0.730
Mem-0.707
 sandy-0.703
Token released
Token ID2716
Feature activation+1.35e-02

Pos logit contributions
\-+0.052
 CoC+0.051
hran+0.051
Mem+0.049
 sandy+0.049
Neg logit contributions
heit-0.050
agher-0.049
 Strat-0.048
inav-0.048
llah-0.047
Token but
Token ID475
Feature activation+5.57e-02

Pos logit contributions
heit+1.164
agher+1.153
 Strat+1.134
inav+1.115
llah+1.106
Neg logit contributions
\--0.962
 CoC-0.959
hran-0.953
Mem-0.918
 sandy-0.907
Token it
Token ID340
Feature activation+3.71e-02

Pos logit contributions
heit+0.496
agher+0.490
 Strat+0.480
inav+0.474
llah+0.470
Neg logit contributions
\--0.391
 CoC-0.388
hran-0.386
Mem-0.371
 sandy-0.369
Token is
Token ID318
Feature activation+6.34e-01

Pos logit contributions
heit+0.308
agher+0.303
 Strat+0.296
inav+0.293
llah+0.291
Neg logit contributions
\--0.284
 CoC-0.281
hran-0.279
Mem-0.270
 sandy-0.269
Tokencontaining
Token ID38301
Feature activation+2.91e-01

Pos logit contributions
heit+3.176
agher+3.108
 Strat+3.082
ega+2.993
inav+2.901
Neg logit contributions
 CoC-6.745
\--6.596
hran-6.564
Mem-6.437
Serv-6.392
Token everything
Token ID2279
Feature activation+5.58e-01

Pos logit contributions
heit+2.184
agher+2.169
 Strat+2.123
inav+2.103
llah+2.093
Neg logit contributions
 CoC-2.406
hran-2.390
\--2.375
Mem-2.274
 sandy-2.260
Token and
Token ID290
Feature activation+1.13e+00

Pos logit contributions
heit+3.868
agher+3.853
 Strat+3.829
llah+3.784
inav+3.695
Neg logit contributions
hran-4.763
 CoC-4.682
\--4.594
Mem-4.483
 sandy-4.467
Token beyond
Token ID3675
Feature activation+4.85e-01

Pos logit contributions
 Strat+7.854
ega+7.676
heit+7.586
agher+7.434
inav+7.373
Neg logit contributions
Mem-8.929
Serv-8.893
Pir-8.850
 CoC-8.817
Magikarp-8.678
Token the
Token ID262
Feature activation+4.51e-01

Pos logit contributions
heit+3.748
 Strat+3.653
agher+3.638
llah+3.542
inav+3.527
Neg logit contributions
hran-3.886
 CoC-3.846
\--3.833
 sandy-3.706
Mem-3.663
Token universe
Token ID6881
Feature activation-2.39e-02

Pos logit contributions
heit+2.796
agher+2.760
 Strat+2.751
inav+2.630
ega+2.627
Neg logit contributions
hran-4.250
 CoC-4.238
\--4.200
Mem-4.099
 sandy-4.059
Token of
Token ID286
Feature activation+2.15e-02

Pos logit contributions
\-+0.183
 CoC+0.181
hran+0.180
Mem+0.174
 sandy+0.173
Neg logit contributions
heit-0.198
agher-0.195
 Strat-0.191
inav-0.189
llah-0.187
Token the
Token ID262
Feature activation+2.26e-01

Pos logit contributions
heit+0.189
agher+0.187
 Strat+0.182
inav+0.181
ega+0.179
Neg logit contributions
\--0.153
 CoC-0.152
hran-0.151
Mem-0.146
 sandy-0.144
Token and
Token ID290
Feature activation-2.75e-03

Pos logit contributions
\-+2.652
 CoC+2.605
hran+2.581
Mem+2.511
 sandy+2.503
Neg logit contributions
agher-2.785
heit-2.766
inav-2.664
 Strat-2.647
ega-2.639
Token obesity
Token ID13825
Feature activation+5.23e-02

Pos logit contributions
\-+0.023
 CoC+0.023
hran+0.023
Mem+0.022
 sandy+0.022
Neg logit contributions
heit-0.020
agher-0.020
 Strat-0.019
inav-0.019
ega-0.019
Token combined
Token ID5929
Feature activation-2.90e-02

Pos logit contributions
heit+0.414
agher+0.407
 Strat+0.399
inav+0.393
llah+0.390
Neg logit contributions
\--0.418
 CoC-0.414
hran-0.413
Mem-0.399
 sandy-0.397
Token (
Token ID357
Feature activation+3.23e-01

Pos logit contributions
\-+0.229
 CoC+0.227
hran+0.226
Mem+0.218
 sandy+0.217
Neg logit contributions
heit-0.231
agher-0.229
 Strat-0.223
inav-0.220
ega-0.220
TokenB
Token ID33
Feature activation+1.75e-01

Pos logit contributions
heit+2.460
agher+2.412
 Strat+2.358
inav+2.320
llah+2.310
Neg logit contributions
\--2.650
 CoC-2.642
hran-2.632
 sandy-2.549
Mem-2.530
TokenMI
Token ID8895
Feature activation+1.11e+00

Pos logit contributions
heit+1.087
agher+1.074
 Strat+1.041
inav+1.023
ega+1.012
Neg logit contributions
\--1.696
 CoC-1.683
hran-1.681
Mem-1.633
 sandy-1.621
Token
Token ID26870
Feature activation+6.80e-01

Pos logit contributions
 Strat+5.801
heit+5.734
agher+5.631
llah+5.421
ega+5.319
Neg logit contributions
hran-10.357
\--10.214
 CoC-10.107
 sandy-9.999
Mem-9.984
Token25
Token ID1495
Feature activation+3.50e-01

Pos logit contributions
heit+4.923
agher+4.845
 Strat+4.834
inav+4.700
llah+4.633
Neg logit contributions
hran-5.579
 CoC-5.509
\--5.415
 sandy-5.367
Mem-5.273
Token kg
Token ID14211
Feature activation-1.15e-01

Pos logit contributions
heit+2.601
agher+2.524
 Strat+2.484
llah+2.433
ega+2.406
Neg logit contributions
hran-2.917
 CoC-2.888
\--2.884
Mem-2.818
 sandy-2.795
Token/
Token ID14
Feature activation+6.30e-01

Pos logit contributions
\-+0.891
 CoC+0.883
hran+0.880
Mem+0.849
 sandy+0.844
Neg logit contributions
heit-0.939
agher-0.926
 Strat-0.905
inav-0.895
llah-0.886
Tokenm
Token ID76
Feature activation-1.46e-02

Pos logit contributions
heit+3.264
agher+3.183
llah+3.081
inav+3.064
 Strat+3.048
Neg logit contributions
 CoC-6.531
\--6.407
hran-6.388
 sandy-6.378
Mem-6.232
Token
Token ID198
Feature activation-5.18e-02

Pos logit contributions
\-+1.917
 CoC+1.894
hran+1.867
Mem+1.819
 sandy+1.791
Neg logit contributions
heit-2.257
agher-2.224
inav-2.174
 Strat-2.169
ega-2.126
Token
Token ID198
Feature activation-1.36e-01

Pos logit contributions
\-+0.384
 CoC+0.378
hran+0.374
Mem+0.366
 sandy+0.359
Neg logit contributions
heit-0.443
agher-0.438
 Strat-0.425
inav-0.423
llah-0.419
TokenPF
Token ID42668
Feature activation+1.04e-01

Pos logit contributions
\-+1.040
 CoC+1.009
Mem+1.009
hran+1.003
Serv+0.974
Neg logit contributions
heit-1.135
agher-1.119
 Strat-1.098
inav-1.092
ega-1.070
Token Bentley
Token ID38881
Feature activation+1.20e-01

Pos logit contributions
heit+0.827
agher+0.816
 Strat+0.797
inav+0.787
llah+0.780
Neg logit contributions
\--0.820
 CoC-0.813
hran-0.810
Mem-0.783
 sandy-0.778
Token/
Token ID14
Feature activation+2.03e-01

Pos logit contributions
heit+0.952
agher+0.936
 Strat+0.918
inav+0.901
ega+0.896
Neg logit contributions
\--0.950
hran-0.945
 CoC-0.945
Mem-0.909
 sandy-0.908
TokenCivil
Token ID32610
Feature activation+1.10e+00

Pos logit contributions
heit+1.807
agher+1.785
 Strat+1.749
inav+1.724
ega+1.715
Neg logit contributions
\--1.424
 CoC-1.412
hran-1.410
 sandy-1.350
Mem-1.344
Token Beat
Token ID12568
Feature activation+3.05e-01

Pos logit contributions
heit+4.057
 Strat+4.037
agher+3.424
ega+3.306
inav+3.215
Neg logit contributions
hran-12.857
\--12.603
���-12.433
 CoC-12.328
lems-12.214
Token
Token ID198
Feature activation+1.25e-01

Pos logit contributions
heit+2.330
agher+2.275
 Strat+2.204
llah+2.187
ega+2.176
Neg logit contributions
\--2.514
 CoC-2.475
hran-2.452
 sandy-2.393
Mem-2.390
Token
Token ID198
Feature activation-1.81e-01

Pos logit contributions
heit+1.004
agher+0.990
 Strat+0.971
inav+0.955
llah+0.948
Neg logit contributions
\--0.977
 CoC-0.973
hran-0.971
 sandy-0.932
Mem-0.932
TokenGood
Token ID10248
Feature activation+2.59e-02

Pos logit contributions
\-+1.379
Mem+1.341
 CoC+1.323
hran+1.314
Serv+1.292
Neg logit contributions
heit-1.528
agher-1.508
 Strat-1.483
inav-1.475
ega-1.439
Tokenwin
Token ID5404
Feature activation+1.16e-01

Pos logit contributions
heit+0.277
agher+0.274
 Strat+0.269
inav+0.267
llah+0.265
Neg logit contributions
\--0.136
 CoC-0.134
hran-0.133
Mem-0.126
 sandy-0.125
Token millionaires
Token ID48675
Feature activation-1.52e-01

Pos logit contributions
\-+1.129
 CoC+1.120
hran+1.106
 sandy+1.070
Mem+1.064
Neg logit contributions
heit-1.404
agher-1.377
inav-1.353
llah-1.342
 Strat-1.335
Token,
Token ID11
Feature activation+6.42e-01

Pos logit contributions
\-+1.160
 CoC+1.145
hran+1.138
Mem+1.101
 sandy+1.094
Neg logit contributions
heit-1.263
agher-1.241
 Strat-1.210
inav-1.200
llah-1.192
Token
Token ID447
Feature activation+1.32e-01

Pos logit contributions
 Strat+5.310
agher+5.307
heit+5.265
inav+5.000
ega+4.962
Neg logit contributions
hran-4.677
\--4.668
 CoC-4.593
Mem-4.408
 sandy-4.318
Token
Token ID251
Feature activation+5.21e-01

Pos logit contributions
heit+1.000
agher+0.975
 Strat+0.951
llah+0.943
inav+0.935
Neg logit contributions
\--1.090
 CoC-1.088
hran-1.081
Mem-1.051
 sandy-1.045
Token Ms
Token ID6997
Feature activation+9.61e-01

Pos logit contributions
heit+4.144
agher+4.104
 Strat+4.082
ega+3.893
inav+3.865
Neg logit contributions
\--4.016
hran-4.012
 CoC-3.986
Mem-3.827
 sandy-3.789
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
heit+6.109
agher+6.050
 Strat+5.999
inav+5.687
ega+5.679
Neg logit contributions
 CoC-8.488
hran-8.401
���-8.250
\--8.196
 sandy-8.168
Token Ole
Token ID30093
Feature activation-1.02e-01

Pos logit contributions
 Strat+6.656
agher+6.440
heit+6.437
ega+5.929
inav+5.901
Neg logit contributions
 CoC-9.462
hran-9.422
\--9.333
 sandy-9.043
Mem-9.040
Tokench
Token ID354
Feature activation-5.64e-02

Pos logit contributions
\-+0.567
hran+0.554
 CoC+0.539
Mem+0.520
 sandy+0.511
Neg logit contributions
heit-1.053
agher-1.042
 Strat-1.032
inav-1.018
llah-1.017
Tokenowski
Token ID12079
Feature activation-2.47e-01

Pos logit contributions
\-+0.427
 CoC+0.416
hran+0.416
Mem+0.399
 sandy+0.394
Neg logit contributions
heit-0.470
agher-0.467
 Strat-0.463
inav-0.450
ega-0.446
Token said
Token ID531
Feature activation-7.45e-02

Pos logit contributions
\-+1.880
 CoC+1.837
hran+1.833
Mem+1.773
 sandy+1.760
Neg logit contributions
heit-2.050
agher-2.029
inav-1.987
 Strat-1.967
llah-1.930
Token.
Token ID13
Feature activation-8.61e-02

Pos logit contributions
\-+0.582
 CoC+0.577
hran+0.575
Mem+0.555
 sandy+0.552
Neg logit contributions
heit-0.604
agher-0.596
 Strat-0.582
inav-0.575
llah-0.570
Token =
Token ID796
Feature activation+1.53e-01

Pos logit contributions
heit+0.807
agher+0.796
 Strat+0.778
inav+0.767
llah+0.761
Neg logit contributions
\--0.788
 CoC-0.783
hran-0.780
Mem-0.751
 sandy-0.751
Token [
Token ID685
Feature activation+1.18e-01

Pos logit contributions
heit+1.258
 Strat+1.247
agher+1.242
inav+1.209
ega+1.202
Neg logit contributions
\--1.156
hran-1.153
 CoC-1.144
Mem-1.095
 sandy-1.087
Tokensystem
Token ID10057
Feature activation+1.03e-01

Pos logit contributions
heit+0.872
agher+0.859
 Strat+0.837
inav+0.826
llah+0.818
Neg logit contributions
\--1.009
 CoC-1.002
hran-0.999
Mem-0.967
 sandy-0.962
Token.
Token ID13
Feature activation+6.01e-01

Pos logit contributions
heit+0.810
agher+0.797
 Strat+0.782
inav+0.770
ega+0.765
Neg logit contributions
\--0.817
 CoC-0.815
hran-0.813
 sandy-0.782
Mem-0.781
Tokenwindows
Token ID28457
Feature activation+1.79e-01

Pos logit contributions
heit+3.815
agher+3.665
ega+3.624
inav+3.595
llah+3.567
Neg logit contributions
 CoC-5.598
 sandy-5.396
hran-5.387
\--5.286
Mem-5.248
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
heit+1.371
agher+1.344
 Strat+1.322
inav+1.296
ega+1.289
Neg logit contributions
hran-1.462
 CoC-1.457
\--1.449
 sandy-1.404
Mem-1.394
Tokenforms
Token ID23914
Feature activation+1.97e-01

Pos logit contributions
heit+6.865
agher+6.582
ega+6.544
 Strat+6.490
ackets+6.422
Neg logit contributions
 CoC-9.128
 sandy-9.058
hran-8.841
 Lex-8.681
Mem-8.579
Token.
Token ID13
Feature activation+6.86e-02

Pos logit contributions
heit+1.516
agher+1.480
 Strat+1.452
inav+1.428
ega+1.424
Neg logit contributions
 CoC-1.601
hran-1.597
\--1.586
 sandy-1.543
Mem-1.530
Tokentext
Token ID5239
Feature activation+1.54e-02

Pos logit contributions
heit+0.654
agher+0.646
 Strat+0.633
inav+0.627
llah+0.622
Neg logit contributions
\--0.437
 CoC-0.434
hran-0.431
Mem-0.412
 sandy-0.410
Tokenrend
Token ID10920
Feature activation+1.99e-01

Pos logit contributions
heit+0.112
agher+0.111
 Strat+0.108
inav+0.106
llah+0.106
Neg logit contributions
\--0.134
 CoC-0.132
hran-0.132
Mem-0.128
 sandy-0.127
Tokenerer
Token ID11882
Feature activation+1.23e-01

Pos logit contributions
heit+1.354
agher+1.331
 Strat+1.287
inav+1.280
ega+1.262
Neg logit contributions
\--1.819
 CoC-1.811
hran-1.802
Mem-1.748
 sandy-1.745
Token-
Token ID12
Feature activation+2.75e-01

Pos logit contributions
heit+1.892
agher+1.859
 Strat+1.848
inav+1.803
llah+1.789
Neg logit contributions
hran-1.906
\--1.905
 CoC-1.903
Mem-1.826
 sandy-1.813
Tokenbased
Token ID3106
Feature activation+2.66e-01

Pos logit contributions
heit+1.984
agher+1.941
 Strat+1.915
inav+1.881
ega+1.859
Neg logit contributions
 CoC-2.373
\--2.368
hran-2.364
 sandy-2.271
Mem-2.263
Token Anat
Token ID28880
Feature activation-6.10e-02

Pos logit contributions
heit+2.168
agher+2.145
 Strat+2.134
inav+2.095
llah+2.061
Neg logit contributions
\--2.033
hran-2.025
 CoC-2.015
Mem-1.942
 sandy-1.923
Tokenol
Token ID349
Feature activation-2.24e-01

Pos logit contributions
\-+0.546
 CoC+0.541
hran+0.540
Mem+0.524
 sandy+0.521
Neg logit contributions
heit-0.424
agher-0.418
 Strat-0.407
inav-0.400
llah-0.397
Tokeniy
Token ID7745
Feature activation-7.65e-02

Pos logit contributions
\-+1.362
hran+1.343
 CoC+1.332
Mem+1.282
 sandy+1.267
Neg logit contributions
heit-2.195
agher-2.174
 Strat-2.129
inav-2.102
ega-2.090
Token D
Token ID360
Feature activation+1.08e+00

Pos logit contributions
\-+0.494
 CoC+0.489
hran+0.486
Mem+0.466
 sandy+0.463
Neg logit contributions
heit-0.723
agher-0.715
 Strat-0.702
inav-0.694
llah-0.689
Tokenerk
Token ID9587
Feature activation+8.51e-02

Pos logit contributions
agher+3.593
heit+3.191
inav+3.065
ega+2.967
 Strat+2.714
Neg logit contributions
 CoC-13.048
\--12.856
 sandy-12.830
hran-12.638
Mem-12.563
Tokenach
Token ID620
Feature activation+3.60e-01

Pos logit contributions
heit+0.680
agher+0.668
 Strat+0.658
inav+0.648
llah+0.645
Neg logit contributions
\--0.675
hran-0.667
 CoC-0.666
Mem-0.639
 sandy-0.637
Token,
Token ID11
Feature activation+1.28e-01

Pos logit contributions
heit+2.852
agher+2.781
 Strat+2.765
inav+2.729
llah+2.695
Neg logit contributions
hran-2.823
 CoC-2.816
\--2.806
Mem-2.699
 sandy-2.693
Token the
Token ID262
Feature activation+2.08e-01

Pos logit contributions
heit+1.044
agher+1.030
 Strat+1.008
inav+0.995
llah+0.986
Neg logit contributions
\--0.986
 CoC-0.977
hran-0.974
Mem-0.940
 sandy-0.934
Token owner
Token ID4870
Feature activation+1.53e-02

Pos logit contributions
heit+1.553
agher+1.530
 Strat+1.498
inav+1.476
llah+1.460
Neg logit contributions
\--1.760
 CoC-1.745
hran-1.742
Mem-1.684
 sandy-1.673
Token life
Token ID1204
Feature activation+3.28e-01

Pos logit contributions
\-+1.426
 CoC+1.420
hran+1.398
 sandy+1.383
Mem+1.362
Neg logit contributions
heit-1.288
agher-1.259
inav-1.245
ega-1.217
 Strat-1.208
Token,
Token ID11
Feature activation+1.65e-01

Pos logit contributions
heit+2.558
agher+2.549
 Strat+2.490
ega+2.438
inav+2.424
Neg logit contributions
\--2.643
 CoC-2.620
hran-2.597
Mem-2.512
 sandy-2.497
Token in
Token ID287
Feature activation+3.00e-01

Pos logit contributions
heit+1.328
agher+1.312
 Strat+1.284
inav+1.263
llah+1.253
Neg logit contributions
\--1.294
 CoC-1.280
hran-1.277
Mem-1.232
 sandy-1.223
Token her
Token ID607
Feature activation+2.72e-02

Pos logit contributions
heit+2.540
agher+2.517
 Strat+2.475
inav+2.410
ega+2.402
Neg logit contributions
\--2.224
 CoC-2.190
hran-2.185
Mem-2.096
 sandy-2.078
Token latest
Token ID3452
Feature activation+1.22e-01

Pos logit contributions
heit+0.217
agher+0.215
 Strat+0.207
inav+0.207
ega+0.205
Neg logit contributions
 CoC-0.214
\--0.214
hran-0.212
Mem-0.207
 sandy-0.206
Token movie
Token ID3807
Feature activation+1.07e+00

Pos logit contributions
heit+1.050
agher+1.036
 Strat+1.018
inav+1.002
ega+0.994
Neg logit contributions
\--0.896
 CoC-0.885
hran-0.883
Mem-0.847
 sandy-0.842
Token,
Token ID11
Feature activation+1.00e+00

Pos logit contributions
 Strat+7.584
heit+7.414
agher+7.135
llah+7.122
ega+7.052
Neg logit contributions
\--8.423
 CoC-8.350
hran-8.057
 sandy-7.950
}}}-7.756
Token Sn
Token ID5489
Feature activation+1.65e-01

Pos logit contributions
 Strat+6.728
heit+6.604
agher+6.455
llah+6.202
ega+6.095
Neg logit contributions
\--8.528
 CoC-8.404
hran-8.221
 sandy-7.880
]}-7.831
Tokenatched
Token ID14265
Feature activation+2.00e-01

Pos logit contributions
heit+1.392
agher+1.377
 Strat+1.340
inav+1.332
ega+1.321
Neg logit contributions
\--1.236
 CoC-1.227
hran-1.220
Mem-1.175
 sandy-1.173
Token,
Token ID11
Feature activation+1.58e-01

Pos logit contributions
heit+1.619
agher+1.597
 Strat+1.566
inav+1.538
ega+1.532
Neg logit contributions
\--1.565
 CoC-1.550
hran-1.543
Mem-1.481
 sandy-1.480
Token Schumer
Token ID26107
Feature activation+4.39e-01

Pos logit contributions
heit+1.279
agher+1.263
 Strat+1.238
inav+1.213
llah+1.208
Neg logit contributions
\--1.243
 CoC-1.230
hran-1.225
Mem-1.180
 sandy-1.173
Token Johannes
Token ID38579
Feature activation-1.11e-01

Pos logit contributions
heit+0.768
agher+0.758
 Strat+0.741
inav+0.733
llah+0.727
Neg logit contributions
\--0.666
 CoC-0.660
hran-0.657
Mem-0.633
 sandy-0.629
Token Brah
Token ID36415
Feature activation-1.36e-01

Pos logit contributions
\-+0.894
 CoC+0.887
hran+0.884
Mem+0.855
 sandy+0.851
Neg logit contributions
heit-0.858
agher-0.856
 Strat-0.828
inav-0.824
llah-0.816
Tokenms
Token ID907
Feature activation-1.21e-01

Pos logit contributions
\-+0.544
 CoC+0.534
hran+0.531
Mem+0.495
 sandy+0.489
Neg logit contributions
heit-1.622
agher-1.608
 Strat-1.583
inav-1.570
llah-1.561
Token:
Token ID25
Feature activation+3.63e-01

Pos logit contributions
\-+0.894
 CoC+0.893
hran+0.884
Mem+0.859
 sandy+0.845
Neg logit contributions
heit-1.023
agher-1.014
inav-0.989
 Strat-0.983
ega-0.978
Token Life
Token ID5155
Feature activation+2.92e-02

Pos logit contributions
heit+3.235
agher+3.193
 Strat+3.173
inav+3.084
llah+3.060
Neg logit contributions
\--2.526
hran-2.479
 CoC-2.467
 sandy-2.354
Mem-2.348
Token and
Token ID290
Feature activation+1.06e+00

Pos logit contributions
heit+0.243
agher+0.240
 Strat+0.234
inav+0.231
llah+0.229
Neg logit contributions
\--0.222
 CoC-0.220
hran-0.219
Mem-0.211
 sandy-0.210
Token Letters
Token ID24501
Feature activation+1.48e-01

Pos logit contributions
 Strat+8.535
heit+8.115
agher+7.952
ega+7.868
inav+7.746
Neg logit contributions
\--7.883
hran-7.346
lems-7.194
 CoC-7.126
 sandy-7.100
Token,
Token ID11
Feature activation+7.93e-03

Pos logit contributions
heit+1.199
agher+1.186
 Strat+1.160
inav+1.137
ega+1.130
Neg logit contributions
\--1.154
 CoC-1.146
hran-1.139
Mem-1.098
 sandy-1.096
Token MacDonald
Token ID37131
Feature activation+1.30e-01

Pos logit contributions
heit+0.068
agher+0.067
 Strat+0.065
inav+0.065
ega+0.064
Neg logit contributions
\--0.058
 CoC-0.058
hran-0.058
Mem-0.056
 sandy-0.055
Token learned
Token ID4499
Feature activation+3.28e-01

Pos logit contributions
heit+0.997
agher+0.981
 Strat+0.957
inav+0.947
llah+0.937
Neg logit contributions
\--1.077
 CoC-1.067
hran-1.063
Mem-1.028
 sandy-1.023
Token that
Token ID326
Feature activation+1.33e-01

Pos logit contributions
heit+2.740
agher+2.694
 Strat+2.665
inav+2.585
llah+2.571
Neg logit contributions
\--2.465
hran-2.448
 CoC-2.447
Mem-2.352
 sandy-2.302
Token,
Token ID11
Feature activation+4.26e-01

Pos logit contributions
heit+2.484
agher+2.450
 Strat+2.406
inav+2.385
llah+2.353
Neg logit contributions
\--2.498
 CoC-2.465
hran-2.456
Mem-2.357
 sandy-2.342
Token was
Token ID373
Feature activation+3.60e-02

Pos logit contributions
heit+3.284
agher+3.267
 Strat+3.237
ega+3.139
inav+3.139
Neg logit contributions
hran-3.398
\--3.358
 CoC-3.349
Mem-3.198
lems-3.166
Token a
Token ID257
Feature activation+2.88e-03

Pos logit contributions
heit+0.295
agher+0.291
 Strat+0.283
inav+0.281
llah+0.278
Neg logit contributions
\--0.279
 CoC-0.277
hran-0.275
Mem-0.266
 sandy-0.265
Token distinguished
Token ID18876
Feature activation+7.34e-02

Pos logit contributions
heit+0.023
agher+0.023
inav+0.022
 Strat+0.022
llah+0.022
Neg logit contributions
\--0.022
 CoC-0.022
hran-0.022
Mem-0.022
 sandy-0.022
Token veteran
Token ID9298
Feature activation-1.17e-01

Pos logit contributions
heit+0.577
agher+0.569
 Strat+0.554
inav+0.548
llah+0.543
Neg logit contributions
\--0.591
 CoC-0.587
hran-0.583
Mem-0.566
 sandy-0.563
Token,"
Token ID553
Feature activation+1.05e+00

Pos logit contributions
\-+0.853
 CoC+0.848
hran+0.833
Mem+0.817
 sandy+0.817
Neg logit contributions
heit-1.008
agher-0.992
 Strat-0.966
inav-0.956
llah-0.953
Token Stra
Token ID15195
Feature activation+4.86e-01

Pos logit contributions
 Strat+6.662
heit+6.294
agher+6.253
ega+5.985
llah+5.916
Neg logit contributions
\--9.448
hran-9.419
 CoC-9.320
Mem-8.977
lems-8.895
Tokenub
Token ID549
Feature activation+9.29e-02

Pos logit contributions
heit+3.285
agher+3.276
 Strat+3.144
inav+3.123
ega+3.098
Neg logit contributions
 CoC-4.396
hran-4.371
\--4.358
 sandy-4.250
Mem-4.207
Token said
Token ID531
Feature activation+2.95e-01

Pos logit contributions
heit+0.719
agher+0.708
 Strat+0.694
inav+0.683
llah+0.678
Neg logit contributions
\--0.756
 CoC-0.754
hran-0.750
Mem-0.724
 sandy-0.721
Token.
Token ID13
Feature activation-3.58e-03

Pos logit contributions
heit+2.260
agher+2.225
 Strat+2.188
ega+2.142
inav+2.126
Neg logit contributions
 CoC-2.419
hran-2.406
\--2.402
Mem-2.314
 sandy-2.280
Token "...
Token ID27896
Feature activation+7.28e-02

Pos logit contributions
\-+0.028
 CoC+0.027
hran+0.027
Mem+0.026
 sandy+0.026
Neg logit contributions
heit-0.029
agher-0.029
 Strat-0.028
inav-0.028
llah-0.028
Token [
Token ID685
Feature activation+1.69e-02

Pos logit contributions
\-+0.676
 CoC+0.669
hran+0.666
Mem+0.641
 sandy+0.637
Neg logit contributions
heit-0.844
agher-0.834
 Strat-0.816
inav-0.807
llah-0.801
Tokensystem
Token ID10057
Feature activation-1.16e-01

Pos logit contributions
heit+0.124
agher+0.122
 Strat+0.119
inav+0.117
llah+0.116
Neg logit contributions
\--0.145
 CoC-0.144
hran-0.143
Mem-0.139
 sandy-0.138
Token.
Token ID13
Feature activation-5.52e-03

Pos logit contributions
\-+0.876
 CoC+0.856
hran+0.849
Mem+0.832
 sandy+0.810
Neg logit contributions
heit-0.977
agher-0.971
 Strat-0.942
inav-0.937
llah-0.925
Tokendraw
Token ID19334
Feature activation-6.97e-02

Pos logit contributions
\-+0.060
 CoC+0.059
hran+0.059
Mem+0.058
 sandy+0.057
Neg logit contributions
heit-0.028
agher-0.028
 Strat-0.027
inav-0.026
llah-0.026
Tokening
Token ID278
Feature activation+2.27e-01

Pos logit contributions
\-+0.515
hran+0.495
 CoC+0.494
Mem+0.484
 sandy+0.468
Neg logit contributions
heit-0.598
agher-0.596
 Strat-0.582
inav-0.575
llah-0.573
Token.
Token ID13
Feature activation+1.05e+00

Pos logit contributions
heit+1.717
agher+1.676
 Strat+1.662
inav+1.612
llah+1.610
Neg logit contributions
hran-1.880
 CoC-1.868
\--1.854
 sandy-1.813
Mem-1.779
TokenString
Token ID10100
Feature activation+5.11e-01

Pos logit contributions
heit+5.819
 Strat+5.733
agher+5.612
ega+5.328
llah+5.183
Neg logit contributions
hran-9.779
 CoC-9.763
 sandy-9.623
\--9.318
 Fior-9.283
TokenAl
Token ID2348
Feature activation-9.09e-02

Pos logit contributions
heit+3.145
agher+3.051
 Strat+3.042
ega+2.895
llah+2.850
Neg logit contributions
hran-4.850
 CoC-4.814
\--4.744
 sandy-4.736
lems-4.527
Tokenignment
Token ID16747
Feature activation+5.83e-02

Pos logit contributions
\-+0.915
hran+0.898
 CoC+0.895
Mem+0.873
 sandy+0.861
Neg logit contributions
heit-0.528
agher-0.520
 Strat-0.511
ega-0.496
llah-0.496
Token]
Token ID60
Feature activation+2.96e-01

Pos logit contributions
heit+0.445
agher+0.434
 Strat+0.429
inav+0.419
ega+0.419
Neg logit contributions
hran-0.480
\--0.478
 CoC-0.478
 sandy-0.459
Mem-0.456
Token::
Token ID3712
Feature activation+5.83e-01

Pos logit contributions
heit+2.627
agher+2.578
 Strat+2.567
ega+2.498
inav+2.491
Neg logit contributions
hran-2.064
 CoC-2.034
\--2.021
 sandy-1.956
Mem-1.929
Token Russia
Token ID3284
Feature activation+4.03e-03

Pos logit contributions
heit+1.959
agher+1.933
 Strat+1.891
inav+1.866
llah+1.850
Neg logit contributions
\--1.860
 CoC-1.844
hran-1.834
Mem-1.772
 sandy-1.762
Token
Token ID447
Feature activation+3.27e-02

Pos logit contributions
heit+0.036
agher+0.035
 Strat+0.034
inav+0.034
ega+0.034
Neg logit contributions
\--0.029
 CoC-0.028
hran-0.028
Mem-0.027
 sandy-0.027
Token
Token ID247
Feature activation-5.88e-02

Pos logit contributions
heit+0.231
agher+0.229
 Strat+0.223
inav+0.219
ega+0.217
Neg logit contributions
\--0.290
 CoC-0.287
hran-0.286
Mem-0.278
 sandy-0.276
Tokens
Token ID82
Feature activation-2.02e-01

Pos logit contributions
\-+0.497
hran+0.489
 CoC+0.487
Mem+0.470
 sandy+0.465
Neg logit contributions
heit-0.439
agher-0.434
 Strat-0.423
inav-0.419
llah-0.415
Token goal
Token ID3061
Feature activation+2.31e-01

Pos logit contributions
 CoC+1.636
hran+1.619
\-+1.618
Mem+1.564
 sandy+1.564
Neg logit contributions
heit-1.573
agher-1.554
ega-1.487
llah-1.484
 Strat-1.476
Token since
Token ID1201
Feature activation+1.05e+00

Pos logit contributions
heit+1.841
agher+1.819
 Strat+1.778
inav+1.755
llah+1.741
Neg logit contributions
\--1.833
 CoC-1.821
hran-1.812
Mem-1.753
 sandy-1.741
Token the
Token ID262
Feature activation+7.10e-01

Pos logit contributions
 Strat+7.622
heit+7.428
agher+7.415
llah+7.199
inav+7.129
Neg logit contributions
\--8.302
 CoC-7.978
hran-7.970
Mem-7.627
 sandy-7.605
Token creation
Token ID6282
Feature activation+2.89e-01

Pos logit contributions
 Strat+5.104
agher+4.951
heit+4.881
llah+4.814
inav+4.784
Neg logit contributions
\--5.992
hran-5.875
 CoC-5.770
Mem-5.559
Serv-5.530
Token of
Token ID286
Feature activation+3.69e-01

Pos logit contributions
heit+2.142
agher+2.121
 Strat+2.106
llah+2.050
inav+2.049
Neg logit contributions
 CoC-2.386
\--2.377
hran-2.355
Mem-2.278
 sandy-2.267
Token NATO
Token ID11332
Feature activation+5.04e-02

Pos logit contributions
heit+2.912
 Strat+2.893
agher+2.893
inav+2.796
llah+2.760
Neg logit contributions
\--2.910
hran-2.850
 CoC-2.841
Mem-2.727
 sandy-2.711
Token.
Token ID13
Feature activation-9.10e-03

Pos logit contributions
heit+0.411
agher+0.406
 Strat+0.398
inav+0.392
llah+0.388
Neg logit contributions
\--0.391
 CoC-0.388
hran-0.386
Mem-0.373
 sandy-0.371
Token}
Token ID92
Feature activation+4.05e-01

Pos logit contributions
\-+0.968
 CoC+0.952
hran+0.943
Mem+0.900
 sandy+0.893
Neg logit contributions
heit-1.820
agher-1.802
 Strat-1.770
inav-1.756
llah-1.743
Token at
Token ID379
Feature activation+7.39e-02

Pos logit contributions
heit+3.408
agher+3.367
 Strat+3.347
inav+3.269
ega+3.238
Neg logit contributions
hran-2.944
\--2.895
 CoC-2.891
Mem-2.789
 sandy-2.757
Token least
Token ID1551
Feature activation+1.76e-03

Pos logit contributions
heit+0.589
agher+0.581
 Strat+0.566
inav+0.561
llah+0.555
Neg logit contributions
\--0.587
 CoC-0.582
hran-0.579
Mem-0.560
 sandy-0.558
Token one
Token ID530
Feature activation+1.81e-01

Pos logit contributions
heit+0.015
agher+0.015
 Strat+0.014
inav+0.014
llah+0.014
Neg logit contributions
\--0.013
 CoC-0.013
hran-0.013
Mem-0.012
 sandy-0.012
Token blank
Token ID9178
Feature activation+3.83e-02

Pos logit contributions
heit+1.091
agher+1.069
 Strat+1.050
inav+1.014
llah+1.012
Neg logit contributions
\--1.773
hran-1.768
 CoC-1.763
Mem-1.713
 sandy-1.695
Token character
Token ID2095
Feature activation+1.04e+00

Pos logit contributions
heit+0.380
agher+0.376
 Strat+0.370
inav+0.365
ega+0.363
Neg logit contributions
\--0.228
 CoC-0.226
hran-0.226
Mem-0.215
 sandy-0.213
Token (<
Token ID38155
Feature activation+6.92e-01

Pos logit contributions
 Strat+7.106
heit+7.015
agher+6.875
ega+6.761
inav+6.716
Neg logit contributions
hran-8.471
 CoC-8.019
\--8.000
 sandy-7.825
Mem-7.784
TokenSpace
Token ID14106
Feature activation+2.36e-01

Pos logit contributions
heit+3.013
 Strat+2.930
agher+2.872
ega+2.768
inav+2.737
Neg logit contributions
hran-7.617
 CoC-7.576
 sandy-7.505
\--7.378
lems-7.186
Token>
Token ID29
Feature activation+2.47e-01

Pos logit contributions
heit+1.397
agher+1.368
 Strat+1.343
ega+1.298
inav+1.297
Neg logit contributions
hran-2.344
 CoC-2.332
\--2.331
Mem-2.263
 sandy-2.260
Token or
Token ID393
Feature activation-4.31e-02

Pos logit contributions
heit+1.733
agher+1.690
 Strat+1.672
ega+1.628
inav+1.620
Neg logit contributions
hran-2.175
 CoC-2.159
\--2.152
 sandy-2.084
Mem-2.083
Token <
Token ID1279
Feature activation+9.51e-01

Pos logit contributions
\-+0.474
 CoC+0.471
hran+0.466
Mem+0.456
 sandy+0.454
Neg logit contributions
heit-0.215
agher-0.210
inav-0.199
 Strat-0.198
llah-0.196
Token
Token ID198
Feature activation+4.96e-02

Pos logit contributions
heit+0.276
agher+0.273
 Strat+0.267
inav+0.264
llah+0.262
Neg logit contributions
\--0.252
 CoC-0.250
hran-0.249
Mem-0.240
 sandy-0.239
Token
Token ID198
Feature activation-7.47e-02

Pos logit contributions
heit+0.412
agher+0.407
 Strat+0.396
inav+0.393
llah+0.389
Neg logit contributions
\--0.379
 CoC-0.374
hran-0.372
Mem-0.361
 sandy-0.357
TokenPF
Token ID42668
Feature activation+1.90e-01

Pos logit contributions
\-+0.577
 CoC+0.564
hran+0.559
Mem+0.555
Serv+0.538
Neg logit contributions
heit-0.619
agher-0.611
 Strat-0.598
inav-0.593
ega-0.582
Token Bentley
Token ID38881
Feature activation+2.28e-01

Pos logit contributions
heit+1.491
agher+1.475
 Strat+1.444
inav+1.414
ega+1.407
Neg logit contributions
\--1.531
hran-1.519
 CoC-1.516
Mem-1.467
 sandy-1.456
Token/
Token ID14
Feature activation+1.04e-01

Pos logit contributions
heit+1.753
agher+1.714
 Strat+1.695
inav+1.645
ega+1.644
Neg logit contributions
hran-1.860
\--1.847
 CoC-1.844
 sandy-1.786
Mem-1.772
TokenCivil
Token ID32610
Feature activation+1.04e+00

Pos logit contributions
heit+0.944
agher+0.933
 Strat+0.913
inav+0.905
llah+0.897
Neg logit contributions
\--0.708
 CoC-0.701
hran-0.696
Mem-0.672
 sandy-0.663
Token Beat
Token ID12568
Feature activation+3.07e-01

Pos logit contributions
 Strat+3.973
heit+3.969
agher+3.408
ega+3.296
inav+3.235
Neg logit contributions
hran-12.022
\--11.805
 CoC-11.574
���-11.524
Mem-11.471
Token
Token ID198
Feature activation+2.23e-01

Pos logit contributions
heit+2.332
agher+2.272
 Strat+2.208
llah+2.195
ega+2.182
Neg logit contributions
\--2.538
 CoC-2.498
hran-2.478
 sandy-2.422
Mem-2.417
Token
Token ID198
Feature activation-5.76e-02

Pos logit contributions
heit+1.728
agher+1.700
 Strat+1.678
inav+1.639
ega+1.628
Neg logit contributions
hran-1.795
 CoC-1.790
\--1.787
 sandy-1.725
Mem-1.707
TokenC
Token ID34
Feature activation-1.24e-01

Pos logit contributions
\-+0.440
 CoC+0.429
hran+0.425
Mem+0.423
Serv+0.410
Neg logit contributions
heit-0.482
agher-0.477
 Strat-0.467
inav-0.463
ega-0.454
Tokenald
Token ID1940
Feature activation-5.77e-02

Pos logit contributions
\-+1.197
hran+1.183
 CoC+1.180
Mem+1.152
 sandy+1.143
Neg logit contributions
heit-0.767
agher-0.757
 Strat-0.742
inav-0.726
llah-0.715
Token10
Token ID940
Feature activation+4.47e-01

Pos logit contributions
\-+0.617
 CoC+0.610
hran+0.608
Mem+0.586
 sandy+0.582
Neg logit contributions
heit-0.729
agher-0.720
 Strat-0.704
inav-0.697
llah-0.691
Token or
Token ID393
Feature activation-1.11e-01

Pos logit contributions
heit+2.968
agher+2.900
 Strat+2.862
ega+2.802
inav+2.769
Neg logit contributions
hran-4.088
 CoC-4.002
\--3.987
Mem-3.894
 sandy-3.853
Token more
Token ID517
Feature activation+4.05e-01

Pos logit contributions
\-+0.825
 CoC+0.810
hran+0.797
 sandy+0.778
Mem+0.773
Neg logit contributions
heit-0.947
agher-0.938
 Strat-0.912
inav-0.903
ega-0.896
Token to
Token ID284
Feature activation+3.70e-01

Pos logit contributions
heit+3.271
agher+3.212
 Strat+3.190
ega+3.101
llah+3.076
Neg logit contributions
hran-3.131
 CoC-3.066
\--3.049
 sandy-2.951
Mem-2.942
Token help
Token ID1037
Feature activation+8.61e-01

Pos logit contributions
heit+2.393
agher+2.345
 Strat+2.315
inav+2.282
ega+2.264
Neg logit contributions
hran-3.436
 CoC-3.429
\--3.423
Mem-3.308
 sandy-3.273
Token us
Token ID514
Feature activation+1.02e+00

Pos logit contributions
 Strat+5.697
agher+5.670
inav+5.624
heit+5.624
ega+5.564
Neg logit contributions
hran-7.376
 CoC-7.182
���-7.160
\--7.117
Mem-6.838
Token continue
Token ID2555
Feature activation+5.18e-01

Pos logit contributions
agher+6.207
 Strat+5.946
heit+5.732
inav+5.714
ega+5.633
Neg logit contributions
 CoC-9.426
hran-9.338
���-9.331
\--9.037
Mem-8.937
Token to
Token ID284
Feature activation+6.00e-02

Pos logit contributions
heit+4.040
agher+3.975
 Strat+3.955
ega+3.815
inav+3.788
Neg logit contributions
hran-4.126
 CoC-4.027
\--3.971
 sandy-3.874
Mem-3.832
Token write
Token ID3551
Feature activation+6.08e-01

Pos logit contributions
heit+0.410
agher+0.404
 Strat+0.393
inav+0.387
ega+0.383
Neg logit contributions
\--0.544
 CoC-0.541
hran-0.539
Mem-0.523
 sandy-0.520
Token about
Token ID546
Feature activation+2.19e-01

Pos logit contributions
heit+3.220
 Strat+3.148
agher+3.142
inav+2.996
ega+2.974
Neg logit contributions
\--6.179
hran-6.162
 CoC-6.156
 sandy-5.947
Mem-5.887
Token the
Token ID262
Feature activation+3.82e-01

Pos logit contributions
heit+1.808
agher+1.766
 Strat+1.758
inav+1.713
llah+1.702
Neg logit contributions
\--1.666
hran-1.664
 CoC-1.645
 sandy-1.585
Mem-1.581
TokenRI
Token ID7112
Feature activation+4.25e-01

Pos logit contributions
heit+2.384
agher+2.337
 Strat+2.293
inav+2.261
ega+2.250
Neg logit contributions
\--2.402
hran-2.387
 CoC-2.385
Mem-2.289
 sandy-2.284
TokenER
Token ID1137
Feature activation+1.32e-02

Pos logit contributions
heit+2.087
agher+2.026
ega+1.968
 Strat+1.966
inav+1.881
Neg logit contributions
hran-4.581
 CoC-4.567
\--4.566
 sandy-4.463
Mem-4.428
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
heit+0.109
agher+0.108
 Strat+0.105
inav+0.105
llah+0.103
Neg logit contributions
\--0.101
 CoC-0.100
hran-0.099
Mem-0.096
 sandy-0.095
Token
Token ID198
Feature activation+8.59e-02

Pos logit contributions
heit+1.161
agher+1.144
 Strat+1.125
inav+1.105
ega+1.096
Neg logit contributions
\--1.149
hran-1.146
 CoC-1.146
 sandy-1.099
Mem-1.097
Token11
Token ID1157
Feature activation+4.23e-02

Pos logit contributions
heit+0.756
agher+0.747
 Strat+0.731
inav+0.722
llah+0.717
Neg logit contributions
\--0.613
 CoC-0.605
hran-0.603
Mem-0.582
 sandy-0.575
Tokena
Token ID64
Feature activation-1.62e+00

Pos logit contributions
heit+0.337
agher+0.333
 Strat+0.325
inav+0.321
ega+0.318
Neg logit contributions
\--0.335
 CoC-0.333
hran-0.332
Mem-0.320
 sandy-0.319
Token 11
Token ID1367
Feature activation-7.96e-02

Pos logit contributions
\-+6.668
hran+6.578
 CoC+6.212
 sandy+6.159
Mem+6.094
Neg logit contributions
agher-15.957
heit-15.857
ulic-15.248
llah-15.118
 Strat-15.062
Token.
Token ID13
Feature activation+1.46e-01

Pos logit contributions
\-+0.595
 CoC+0.582
hran+0.573
Mem+0.565
 sandy+0.549
Neg logit contributions
heit-0.678
agher-0.671
 Strat-0.651
inav-0.651
llah-0.643
Token Weapon
Token ID13072
Feature activation+2.64e-01

Pos logit contributions
heit+1.244
agher+1.231
 Strat+1.213
inav+1.189
ega+1.179
Neg logit contributions
\--1.068
hran-1.059
 CoC-1.055
Mem-1.013
 sandy-1.008
Token person
Token ID1048
Feature activation+7.02e-01

Pos logit contributions
heit+2.046
agher+2.031
 Strat+1.985
inav+1.944
ega+1.935
Neg logit contributions
\--2.114
hran-2.106
 CoC-2.099
Mem-2.028
 sandy-2.007
Token loaded
Token ID9639
Feature activation+3.97e-01

Pos logit contributions
agher+5.251
heit+5.232
 Strat+5.131
llah+4.975
ega+4.950
Neg logit contributions
hran-5.605
\--5.525
 CoC-5.508
Mem-5.327
 sandy-5.219
TokenWeek
Token ID20916
Feature activation+2.29e-01

Pos logit contributions
heit+0.643
agher+0.634
 Strat+0.621
inav+0.613
ega+0.608
Neg logit contributions
\--0.598
 CoC-0.594
hran-0.592
 sandy-0.565
Mem-0.565
Tokenend
Token ID437
Feature activation+3.55e-01

Pos logit contributions
heit+1.468
agher+1.444
 Strat+1.400
inav+1.379
ega+1.366
Neg logit contributions
\--2.172
 CoC-2.158
hran-2.151
Mem-2.088
 sandy-2.080
TokenT
Token ID51
Feature activation+2.37e-01

Pos logit contributions
heit+2.739
agher+2.701
 Strat+2.660
inav+2.621
ega+2.598
Neg logit contributions
hran-2.855
\--2.846
 CoC-2.833
 sandy-2.686
Mem-2.648
Tokenear
Token ID451
Feature activation+1.19e-01

Pos logit contributions
heit+1.869
agher+1.842
 Strat+1.790
inav+1.776
ega+1.773
Neg logit contributions
\--1.893
 CoC-1.889
hran-1.873
Mem-1.808
 sandy-1.805
TokenV
Token ID53
Feature activation-4.21e-01

Pos logit contributions
heit+0.979
agher+0.970
 Strat+0.953
inav+0.944
ega+0.930
Neg logit contributions
\--0.906
hran-0.901
 CoC-0.900
 sandy-0.855
Mem-0.849
Tokenoid
Token ID1868
Feature activation-1.29e+00

Pos logit contributions
\-+2.432
hran+2.315
 CoC+2.267
Mem+2.235
 sandy+2.199
Neg logit contributions
heit-4.219
 Strat-4.121
agher-4.121
llah-4.007
 guiActiveUn-3.954
TokenRay
Token ID19591
Feature activation-5.82e-02

Pos logit contributions
\-+4.011
Mem+3.911
Serv+3.907
Pir+3.878
hran+3.796
Neg logit contributions
agher-14.995
inav-14.677
heit-14.651
llah-14.362
 Strat-14.316
TokenJ
Token ID41
Feature activation-2.61e-01

Pos logit contributions
\-+0.440
 CoC+0.437
hran+0.435
Mem+0.420
 sandy+0.417
Neg logit contributions
heit-0.485
agher-0.479
 Strat-0.468
inav-0.463
llah-0.459
TokenKS
Token ID27015
Feature activation+9.03e-03

Pos logit contributions
\-+1.441
hran+1.410
 CoC+1.408
Mem+1.350
 sandy+1.326
Neg logit contributions
heit-2.714
agher-2.665
 Strat-2.629
inav-2.608
llah-2.595
TokenLe
Token ID3123
Feature activation+1.17e-01

Pos logit contributions
heit+0.071
agher+0.070
 Strat+0.068
inav+0.068
llah+0.067
Neg logit contributions
\--0.073
 CoC-0.072
hran-0.072
Mem-0.069
 sandy-0.069
Tokenen
Token ID268
Feature activation-2.81e-01

Pos logit contributions
heit+0.558
agher+0.540
 Strat+0.525
inav+0.510
llah+0.503
Neg logit contributions
\--1.302
hran-1.293
 CoC-1.290
Mem-1.263
 sandy-1.255
Token-
Token ID12
Feature activation+3.16e-01

Pos logit contributions
heit+3.637
agher+3.545
inav+3.498
 Strat+3.488
ega+3.406
Neg logit contributions
hran-4.395
\--4.382
 CoC-4.363
Mem-4.208
 sandy-4.183
Tokena
Token ID64
Feature activation-1.11e-01

Pos logit contributions
heit+2.620
agher+2.583
 Strat+2.510
inav+2.507
ega+2.482
Neg logit contributions
\--2.391
 CoC-2.372
hran-2.364
 sandy-2.265
Mem-2.257
Token-
Token ID12
Feature activation-2.76e-01

Pos logit contributions
\-+0.883
 CoC+0.873
hran+0.871
Mem+0.845
 sandy+0.839
Neg logit contributions
heit-0.874
agher-0.865
 Strat-0.845
inav-0.830
llah-0.825
Tokendet
Token ID15255
Feature activation-9.98e-02

Pos logit contributions
\-+2.302
 CoC+2.290
hran+2.277
Mem+2.269
 sandy+2.214
Neg logit contributions
heit-2.040
agher-2.031
 Strat-1.988
inav-1.935
ega-1.910
Tokenailed
Token ID6255
Feature activation-4.97e-01

Pos logit contributions
\-+0.699
 CoC+0.694
hran+0.689
Mem+0.670
 sandy+0.652
Neg logit contributions
heit-0.889
agher-0.873
 Strat-0.865
inav-0.845
llah-0.841
Token-
Token ID12
Feature activation-1.23e+00

Pos logit contributions
\-+3.464
hran+3.337
 CoC+3.327
Mem+3.245
 sandy+3.221
Neg logit contributions
agher-4.356
heit-4.338
 Strat-4.253
ega-4.134
llah-4.120
Tokenreview
Token ID19023
Feature activation+1.51e-01

Pos logit contributions
hran+5.529
Mem+5.500
\-+5.411
cour+5.317
call+5.213
Neg logit contributions
 Strat-12.587
agher-12.490
heit-12.204
llah-12.062
 guiActiveUn-11.896
Token
Token ID198
Feature activation+6.68e-02

Pos logit contributions
heit+1.193
agher+1.176
 Strat+1.154
inav+1.139
ega+1.124
Neg logit contributions
\--1.209
 CoC-1.200
hran-1.200
Mem-1.151
 sandy-1.149
Token
Token ID198
Feature activation+2.48e-01

Pos logit contributions
heit+0.549
agher+0.541
 Strat+0.529
inav+0.523
llah+0.518
Neg logit contributions
\--0.514
 CoC-0.510
hran-0.508
Mem-0.490
 sandy-0.487
TokenThe
Token ID464
Feature activation+9.54e-02

Pos logit contributions
heit+2.042
agher+2.013
 Strat+1.967
inav+1.949
llah+1.930
Neg logit contributions
\--1.896
 CoC-1.887
hran-1.884
 sandy-1.806
Mem-1.792
Token ability
Token ID2694
Feature activation-1.15e-01

Pos logit contributions
heit+0.804
agher+0.795
 Strat+0.774
inav+0.766
llah+0.760
Neg logit contributions
\--0.714
 CoC-0.712
hran-0.706
Mem-0.682
 sandy-0.680
Token42
Token ID3682
Feature activation+2.23e-01

Pos logit contributions
\-+1.443
 CoC+1.411
hran+1.383
Mem+1.367
 sandy+1.338
Neg logit contributions
heit-1.355
agher-1.336
inav-1.290
llah-1.282
 Strat-1.273
Token 3
Token ID513
Feature activation-9.28e-02

Pos logit contributions
heit+1.661
agher+1.637
 Strat+1.615
inav+1.572
ega+1.565
Neg logit contributions
\--1.868
hran-1.861
 CoC-1.854
Mem-1.792
 sandy-1.784
Token355
Token ID28567
Feature activation+1.65e-01

Pos logit contributions
\-+0.726
 CoC+0.715
hran+0.707
Mem+0.690
 sandy+0.678
Neg logit contributions
heit-0.758
agher-0.745
 Strat-0.728
inav-0.722
llah-0.717
Token;
Token ID26
Feature activation-3.96e-01

Pos logit contributions
heit+1.338
agher+1.319
 Strat+1.296
inav+1.271
ega+1.265
Neg logit contributions
\--1.282
 CoC-1.272
hran-1.270
Mem-1.222
 sandy-1.212
Token mart
Token ID11277
Feature activation-2.91e-01

Pos logit contributions
hran+3.213
 sandy+3.204
\-+3.184
 CoC+3.149
Mem+3.083
Neg logit contributions
heit-2.996
agher-2.952
 Strat-2.886
llah-2.865
ega-2.827
Tokenin
Token ID259
Feature activation-1.18e+00

Pos logit contributions
hran+2.270
\-+2.239
 CoC+2.176
Mem+2.144
 sandy+2.134
Neg logit contributions
heit-2.314
 Strat-2.268
agher-2.246
llah-2.199
inav-2.161
Tokenrand
Token ID25192
Feature activation-9.68e-02

Pos logit contributions
\-+8.942
hran+8.862
lems+8.677
 sandy+8.530
cour+8.397
Neg logit contributions
 Strat-8.543
heit-8.098
agher-7.906
 guiActiveUn-7.894
ega-7.881
Tokenall
Token ID439
Feature activation-3.29e-01

Pos logit contributions
\-+0.707
hran+0.697
 CoC+0.694
Mem+0.669
 sandy+0.666
Neg logit contributions
heit-0.834
agher-0.818
 Strat-0.811
inav-0.795
llah-0.792
Token.
Token ID13
Feature activation-8.78e-02

Pos logit contributions
\-+2.541
hran+2.491
 CoC+2.451
 sandy+2.397
Mem+2.391
Neg logit contributions
heit-2.637
 Strat-2.608
agher-2.557
llah-2.523
ega-2.480
Tokencom
Token ID785
Feature activation-3.54e-01

Pos logit contributions
\-+0.636
hran+0.626
 CoC+0.626
Mem+0.602
 sandy+0.597
Neg logit contributions
heit-0.762
agher-0.749
 Strat-0.738
inav-0.727
llah-0.723
Token),
Token ID828
Feature activation-6.26e-02

Pos logit contributions
\-+2.408
 CoC+2.386
hran+2.365
Mem+2.274
 sandy+2.267
Neg logit contributions
heit-3.191
agher-3.143
 Strat-3.069
inav-3.063
llah-3.037
Token AK
Token ID15837
Feature activation-4.19e-01

Pos logit contributions
heit+1.173
agher+1.160
 Strat+1.145
inav+1.122
ega+1.115
Neg logit contributions
\--0.866
hran-0.859
 CoC-0.854
Mem-0.817
 sandy-0.815
TokenNOW
Token ID45669
Feature activation+1.22e-01

Pos logit contributions
\-+3.100
 CoC+3.084
hran+2.992
Mem+2.988
]}+2.885
Neg logit contributions
heit-3.529
agher-3.528
inav-3.404
llah-3.398
 Strat-3.367
TokenLED
Token ID30465
Feature activation+2.81e-01

Pos logit contributions
heit+1.089
agher+1.075
 Strat+1.053
inav+1.041
llah+1.033
Neg logit contributions
\--0.858
 CoC-0.851
hran-0.847
Mem-0.813
 sandy-0.810
TokenG
Token ID38
Feature activation-3.76e-02

Pos logit contributions
heit+2.128
 Strat+2.084
agher+2.062
ega+2.020
inav+2.005
Neg logit contributions
hran-2.306
\--2.270
 CoC-2.257
 sandy-2.209
Mem-2.143
TokenED
Token ID1961
Feature activation+1.48e-01

Pos logit contributions
\-+0.267
 CoC+0.264
hran+0.259
Mem+0.254
 sandy+0.250
Neg logit contributions
heit-0.330
agher-0.330
 Strat-0.320
inav-0.319
llah-0.315
Token NET
Token ID30502
Feature activation-1.18e+00

Pos logit contributions
heit+1.300
agher+1.282
 Strat+1.272
inav+1.242
llah+1.233
Neg logit contributions
\--1.037
hran-1.035
 CoC-1.022
Mem-0.982
 sandy-0.975
Token CALL
Token ID42815
Feature activation+1.18e-01

Pos logit contributions
 CoC+4.634
\-+4.281
Mem+3.994
 Lex+3.881
 Mem+3.833
Neg logit contributions
agher-13.726
heit-13.724
inav-13.409
ega-13.062
etheus-13.038
Token UPDATE
Token ID35717
Feature activation+1.98e-01

Pos logit contributions
heit+0.922
agher+0.910
 Strat+0.897
inav+0.876
llah+0.870
Neg logit contributions
\--0.945
hran-0.941
 CoC-0.935
Mem-0.901
 sandy-0.899
Token:
Token ID25
Feature activation-3.53e-01

Pos logit contributions
heit+1.409
agher+1.386
 Strat+1.372
llah+1.325
inav+1.325
Neg logit contributions
\--1.728
hran-1.726
 CoC-1.715
Mem-1.654
 sandy-1.647
Token 05
Token ID8870
Feature activation+7.81e-02

Pos logit contributions
 CoC+2.195
hran+2.176
\-+2.167
Mem+2.062
 sandy+2.029
Neg logit contributions
heit-3.396
agher-3.374
inav-3.287
 Strat-3.268
ega-3.249
Token42
Token ID3682
Feature activation-4.46e-01

Pos logit contributions
heit+0.507
agher+0.498
 Strat+0.481
inav+0.476
llah+0.472
Neg logit contributions
\--0.742
 CoC-0.735
hran-0.730
Mem-0.715
 sandy-0.704
Token AK
Token ID15837
Feature activation-3.59e-01

Pos logit contributions
heit+1.139
agher+1.126
 Strat+1.111
inav+1.089
llah+1.082
Neg logit contributions
\--0.891
hran-0.886
 CoC-0.877
Mem-0.842
 sandy-0.839
TokenNOW
Token ID45669
Feature activation+2.42e-01

Pos logit contributions
\-+2.458
 CoC+2.448
Mem+2.389
hran+2.331
]}+2.305
Neg logit contributions
heit-3.255
agher-3.249
llah-3.159
inav-3.142
 Strat-3.115
TokenLED
Token ID30465
Feature activation+2.63e-01

Pos logit contributions
heit+2.087
agher+2.035
 Strat+2.005
inav+1.982
llah+1.968
Neg logit contributions
\--1.748
 CoC-1.748
hran-1.747
 sandy-1.678
Mem-1.656
TokenG
Token ID38
Feature activation-7.85e-02

Pos logit contributions
heit+1.985
 Strat+1.944
agher+1.923
ega+1.887
inav+1.868
Neg logit contributions
hran-2.171
\--2.132
 CoC-2.124
 sandy-2.084
Mem-2.013
TokenED
Token ID1961
Feature activation+2.57e-01

Pos logit contributions
\-+0.555
 CoC+0.547
hran+0.536
Mem+0.526
 sandy+0.516
Neg logit contributions
heit-0.695
agher-0.694
 Strat-0.674
inav-0.671
llah-0.663
Token NET
Token ID30502
Feature activation-1.17e+00

Pos logit contributions
heit+2.232
 Strat+2.208
agher+2.193
inav+2.132
llah+2.115
Neg logit contributions
hran-1.832
\--1.818
 CoC-1.778
Mem-1.720
 sandy-1.705
Token CALL
Token ID42815
Feature activation+1.51e-01

Pos logit contributions
 CoC+4.505
\-+4.078
 Lex+3.818
Mem+3.745
 Mem+3.736
Neg logit contributions
agher-14.199
heit-14.057
inav-13.877
etheus-13.795
 guiActiveUn-13.552
Token UPDATE
Token ID35717
Feature activation+2.01e-01

Pos logit contributions
heit+1.122
agher+1.107
 Strat+1.095
inav+1.065
ega+1.057
Neg logit contributions
hran-1.263
\--1.261
 CoC-1.250
 sandy-1.207
Mem-1.206
Token:
Token ID25
Feature activation-3.76e-01

Pos logit contributions
heit+1.430
agher+1.403
 Strat+1.395
inav+1.346
llah+1.339
Neg logit contributions
hran-1.749
\--1.738
 CoC-1.728
 sandy-1.675
Mem-1.672
Token 05
Token ID8870
Feature activation-3.41e-03

Pos logit contributions
 CoC+2.316
hran+2.295
\-+2.279
Mem+2.167
 sandy+2.135
Neg logit contributions
heit-3.646
agher-3.616
inav-3.533
 Strat-3.512
ega-3.485
Token43
Token ID3559
Feature activation-3.74e-01

Pos logit contributions
\-+0.031
 CoC+0.030
hran+0.030
Mem+0.029
 sandy+0.029
Neg logit contributions
heit-0.024
agher-0.024
 Strat-0.023
inav-0.023
llah-0.023
Token takeover
Token ID27011
Feature activation-1.02e-02

Pos logit contributions
heit+0.511
agher+0.504
 Strat+0.493
inav+0.487
llah+0.482
Neg logit contributions
\--0.478
 CoC-0.474
hran-0.472
Mem-0.455
 sandy-0.453
Token of
Token ID286
Feature activation-2.29e-01

Pos logit contributions
\-+0.080
 CoC+0.079
hran+0.079
Mem+0.076
 sandy+0.075
Neg logit contributions
heit-0.083
agher-0.082
 Strat-0.080
inav-0.079
ega-0.078
Token V
Token ID569
Feature activation-1.74e-01

Pos logit contributions
 CoC+1.664
\-+1.658
hran+1.643
 sandy+1.590
Mem+1.589
Neg logit contributions
heit-1.990
agher-1.962
llah-1.889
inav-1.887
 Strat-1.882
Tokenenez
Token ID11437
Feature activation-4.78e-01

Pos logit contributions
\-+1.360
hran+1.342
 CoC+1.333
Mem+1.302
 sandy+1.279
Neg logit contributions
heit-1.414
agher-1.390
 Strat-1.363
inav-1.344
llah-1.344
Tokenue
Token ID518
Feature activation+3.70e-02

Pos logit contributions
\-+3.801
hran+3.722
 CoC+3.602
Mem+3.595
 sandy+3.540
Neg logit contributions
heit-3.798
agher-3.700
 Strat-3.639
llah-3.588
inav-3.544
Token...
Token ID986
Feature activation-1.15e+00

Pos logit contributions
heit+0.302
agher+0.298
 Strat+0.290
inav+0.287
llah+0.284
Neg logit contributions
\--0.288
 CoC-0.285
hran-0.285
Mem-0.275
 sandy-0.273
Token
Token ID198
Feature activation-4.92e-01

Pos logit contributions
\-+6.922
hran+6.904
 CoC+6.771
Mem+6.593
 sandy+6.426
Neg logit contributions
heit-10.098
agher-10.069
 Strat-9.761
ega-9.698
inav-9.671
Token
Token ID198
Feature activation-1.38e-01

Pos logit contributions
\-+3.159
Mem+3.009
 CoC+2.994
hran+2.913
]}+2.895
Neg logit contributions
heit-4.650
agher-4.626
 guiActiveUn-4.593
inav-4.476
llah-4.434
TokenFrom
Token ID4863
Feature activation+9.44e-02

Pos logit contributions
\-+1.024
 CoC+0.997
Mem+0.996
hran+0.992
Serv+0.960
Neg logit contributions
heit-1.179
agher-1.168
 Strat-1.141
inav-1.134
llah-1.119
Token Vox
Token ID28035
Feature activation+1.72e-01

Pos logit contributions
heit+0.692
agher+0.683
 Strat+0.668
inav+0.654
llah+0.649
Neg logit contributions
\--0.807
 CoC-0.802
hran-0.801
Mem-0.772
 sandy-0.768
Token:
Token ID25
Feature activation+9.22e-02

Pos logit contributions
heit+1.356
agher+1.333
 Strat+1.309
inav+1.285
llah+1.273
Neg logit contributions
\--1.378
 CoC-1.361
hran-1.359
Mem-1.306
 sandy-1.305
Token move
Token ID1445
Feature activation-2.76e-02

Pos logit contributions
heit+0.084
agher+0.083
 Strat+0.081
inav+0.080
llah+0.079
Neg logit contributions
\--0.072
 CoC-0.071
hran-0.071
Mem-0.069
 sandy-0.068
Token on
Token ID319
Feature activation+1.41e-01

Pos logit contributions
\-+0.205
 CoC+0.203
hran+0.202
Mem+0.195
 sandy+0.193
Neg logit contributions
heit-0.234
agher-0.232
 Strat-0.226
inav-0.224
llah-0.222
Token
Token ID198
Feature activation+9.56e-02

Pos logit contributions
heit+1.138
agher+1.123
 Strat+1.100
inav+1.083
ega+1.074
Neg logit contributions
\--1.100
 CoC-1.089
hran-1.088
Mem-1.048
 sandy-1.041
Token
Token ID198
Feature activation-1.97e-01

Pos logit contributions
heit+0.778
agher+0.768
 Strat+0.751
inav+0.741
llah+0.735
Neg logit contributions
\--0.741
 CoC-0.737
hran-0.734
Mem-0.707
 sandy-0.705
Token11
Token ID1157
Feature activation-6.36e-02

Pos logit contributions
\-+1.374
hran+1.340
 CoC+1.330
Mem+1.320
Pir+1.267
Neg logit contributions
heit-1.756
agher-1.737
 Strat-1.706
inav-1.681
llah-1.667
Tokena
Token ID64
Feature activation-1.13e+00

Pos logit contributions
\-+0.483
 CoC+0.477
hran+0.473
Mem+0.458
 sandy+0.455
Neg logit contributions
heit-0.533
agher-0.523
 Strat-0.509
inav-0.508
llah-0.502
Token 11
Token ID1367
Feature activation-4.59e-02

Pos logit contributions
\-+6.099
 CoC+5.874
hran+5.847
Mem+5.704
 sandy+5.693
Neg logit contributions
heit-10.931
agher-10.749
llah-10.398
inav-10.188
 guiActiveUn-10.151
Token.
Token ID13
Feature activation-2.84e-02

Pos logit contributions
\-+0.361
 CoC+0.358
hran+0.357
Mem+0.344
 sandy+0.343
Neg logit contributions
heit-0.369
agher-0.364
 Strat-0.356
inav-0.351
llah-0.348
Token Weapon
Token ID13072
Feature activation+2.09e-01

Pos logit contributions
\-+0.204
 CoC+0.202
hran+0.201
Mem+0.194
 sandy+0.193
Neg logit contributions
heit-0.248
agher-0.245
 Strat-0.239
inav-0.237
llah-0.235
Token person
Token ID1048
Feature activation+3.36e-01

Pos logit contributions
heit+1.712
agher+1.692
 Strat+1.659
inav+1.628
ega+1.619
Neg logit contributions
\--1.597
 CoC-1.584
hran-1.584
Mem-1.523
 sandy-1.516
Token loaded
Token ID9639
Feature activation+1.71e-01

Pos logit contributions
heit+2.448
agher+2.437
 Strat+2.372
inav+2.324
ega+2.319
Neg logit contributions
\--2.848
 CoC-2.839
hran-2.837
 sandy-2.741
Mem-2.734
Token activist
Token ID11276
Feature activation-7.15e-02

Pos logit contributions
heit+0.402
agher+0.396
 Strat+0.387
inav+0.381
ega+0.378
Neg logit contributions
\--0.451
 CoC-0.448
hran-0.446
Mem-0.432
 sandy-0.429
Token had
Token ID550
Feature activation-3.55e-01

Pos logit contributions
\-+0.527
 CoC+0.522
hran+0.519
Mem+0.500
 sandy+0.498
Neg logit contributions
heit-0.613
agher-0.604
inav-0.588
 Strat-0.587
llah-0.582
Token received
Token ID2722
Feature activation-1.29e-01

Pos logit contributions
\-+2.731
 CoC+2.709
hran+2.702
 sandy+2.639
Mem+2.569
Neg logit contributions
heit-2.881
agher-2.877
inav-2.789
 Strat-2.731
llah-2.721
Token th
Token ID294
Feature activation-1.74e-01

Pos logit contributions
\-+0.996
 CoC+0.993
hran+0.978
 sandy+0.952
Mem+0.947
Neg logit contributions
heit-1.060
agher-1.053
inav-1.016
 Strat-1.011
llah-0.995
Tokenrea
Token ID21468
Feature activation-2.54e-01

Pos logit contributions
\-+1.152
hran+1.134
 CoC+1.133
Mem+1.084
 sandy+1.075
Neg logit contributions
heit-1.607
agher-1.594
 Strat-1.562
inav-1.547
llah-1.521
Token...
Token ID986
Feature activation-1.13e+00

Pos logit contributions
\-+1.608
hran+1.598
 CoC+1.581
Mem+1.526
 sandy+1.513
Neg logit contributions
heit-2.399
agher-2.385
 Strat-2.355
inav-2.338
ega-2.304
Token
Token ID198
Feature activation-5.12e-01

Pos logit contributions
hran+7.021
\-+6.998
 CoC+6.915
Mem+6.694
 Lex+6.514
Neg logit contributions
heit-9.858
agher-9.756
inav-9.559
 Strat-9.449
ega-9.435
Token
Token ID198
Feature activation-1.84e-01

Pos logit contributions
\-+3.264
Mem+3.127
 CoC+3.106
hran+3.033
]}+3.006
Neg logit contributions
heit-4.845
agher-4.814
 guiActiveUn-4.780
inav-4.669
llah-4.614
TokenFrom
Token ID4863
Feature activation+1.19e-02

Pos logit contributions
\-+1.381
Mem+1.354
 CoC+1.342
hran+1.335
Serv+1.302
Neg logit contributions
heit-1.552
agher-1.534
 Strat-1.500
inav-1.496
llah-1.467
Token:
Token ID25
Feature activation-1.06e-01

Pos logit contributions
heit+0.103
agher+0.102
 Strat+0.100
inav+0.099
llah+0.098
Neg logit contributions
\--0.086
 CoC-0.086
hran-0.085
Mem-0.082
 sandy-0.081
Token A
Token ID317
Feature activation-8.96e-02

Pos logit contributions
\-+0.813
 CoC+0.806
hran+0.805
Mem+0.777
 sandy+0.774
Neg logit contributions
heit-0.871
agher-0.860
 Strat-0.839
inav-0.835
ega-0.825
Token {
Token ID1391
Feature activation-3.79e-03

Pos logit contributions
 CoC+4.224
Mem+4.156
\-+4.103
hran+4.014
 Lex+3.936
Neg logit contributions
heit-6.837
agher-6.810
inav-6.637
llah-6.372
 Strat-6.356
Token pub
Token ID2240
Feature activation+8.54e-02

Pos logit contributions
\-+0.025
 CoC+0.024
hran+0.024
Mem+0.023
 sandy+0.023
Neg logit contributions
heit-0.036
agher-0.035
 Strat-0.035
inav-0.034
ega-0.034
Token fn
Token ID24714
Feature activation-1.86e-01

Pos logit contributions
heit+0.776
agher+0.767
 Strat+0.764
inav+0.747
llah+0.742
Neg logit contributions
\--0.576
 CoC-0.567
hran-0.559
 sandy-0.536
Mem-0.533
Token load
Token ID3440
Feature activation+6.48e-02

Pos logit contributions
\-+1.403
 CoC+1.392
hran+1.390
Mem+1.349
 sandy+1.349
Neg logit contributions
heit-1.551
agher-1.534
inav-1.489
 Strat-1.472
llah-1.465
Token <
Token ID1279
Feature activation-5.92e-01

Pos logit contributions
heit+0.505
agher+0.499
 Strat+0.487
inav+0.481
llah+0.476
Neg logit contributions
\--0.526
 CoC-0.521
hran-0.519
Mem-0.501
 sandy-0.499
Token '
Token ID705
Feature activation-1.12e+00

Pos logit contributions
\-+3.935
 CoC+3.847
Mem+3.737
hran+3.728
 sandy+3.669
Neg logit contributions
agher-5.419
heit-5.367
inav-5.324
ega-5.138
llah-5.094
Tokena
Token ID64
Feature activation-1.01e-01

Pos logit contributions
\-+6.823
Mem+6.248
 CoC+6.233
hran+6.181
 Lex+5.949
Neg logit contributions
inav-10.476
heit-10.332
agher-10.213
 Strat-9.758
etheus-9.689
Token >
Token ID1875
Feature activation-4.56e-01

Pos logit contributions
\-+0.728
 CoC+0.721
hran+0.718
Mem+0.692
 sandy+0.687
Neg logit contributions
heit-0.878
agher-0.867
 Strat-0.848
inav-0.839
llah-0.832
Token (
Token ID357
Feature activation-5.66e-01

Pos logit contributions
\-+3.210
 CoC+3.202
hran+3.197
Mem+3.170
 sandy+3.060
Neg logit contributions
agher-3.922
heit-3.917
inav-3.802
 Strat-3.701
llah-3.684
Token &
Token ID1222
Feature activation-7.81e-01

Pos logit contributions
\-+3.616
 CoC+3.566
hran+3.550
Mem+3.496
 sandy+3.472
Neg logit contributions
heit-5.240
agher-5.196
inav-5.091
 Strat-5.010
llah-4.943
Token self
Token ID2116
Feature activation-5.18e-01

Pos logit contributions
hran+3.872
\-+3.846
 sandy+3.797
 CoC+3.793
Mem+3.745
Neg logit contributions
heit-8.246
agher-8.087
inav-7.980
ega-7.741
llah-7.670
Token AK
Token ID15837
Feature activation-2.77e-01

Pos logit contributions
heit+0.468
agher+0.463
 Strat+0.455
inav+0.448
llah+0.445
Neg logit contributions
\--0.363
hran-0.359
 CoC-0.358
Mem-0.343
 sandy-0.342
TokenNOW
Token ID45669
Feature activation+2.36e-01

Pos logit contributions
\-+1.927
 CoC+1.911
Mem+1.866
hran+1.835
Serv+1.799
Neg logit contributions
heit-2.487
agher-2.480
llah-2.406
inav-2.403
 Strat-2.392
TokenLED
Token ID30465
Feature activation+2.59e-01

Pos logit contributions
heit+2.045
agher+1.997
 Strat+1.964
inav+1.943
llah+1.931
Neg logit contributions
\--1.702
 CoC-1.702
hran-1.701
 sandy-1.634
Mem-1.615
TokenG
Token ID38
Feature activation-5.84e-02

Pos logit contributions
heit+1.959
 Strat+1.915
agher+1.900
ega+1.861
inav+1.844
Neg logit contributions
hran-2.127
\--2.090
 CoC-2.084
 sandy-2.044
Mem-1.975
TokenED
Token ID1961
Feature activation+2.60e-01

Pos logit contributions
\-+0.416
 CoC+0.410
hran+0.402
Mem+0.394
 sandy+0.387
Neg logit contributions
heit-0.515
agher-0.513
 Strat-0.499
inav-0.497
llah-0.491
Token NET
Token ID30502
Feature activation-1.11e+00

Pos logit contributions
heit+2.230
 Strat+2.203
agher+2.188
inav+2.125
llah+2.111
Neg logit contributions
hran-1.879
\--1.861
 CoC-1.821
Mem-1.762
 sandy-1.751
Token CALL
Token ID42815
Feature activation+1.34e-01

Pos logit contributions
 CoC+4.015
\-+3.657
 Lex+3.378
Mem+3.329
 Mem+3.286
Neg logit contributions
agher-13.695
heit-13.608
inav-13.412
etheus-13.277
 guiActiveUn-13.077
Token UPDATE
Token ID35717
Feature activation+2.18e-01

Pos logit contributions
heit+0.992
agher+0.978
 Strat+0.967
inav+0.941
ega+0.934
Neg logit contributions
hran-1.121
\--1.118
 CoC-1.108
 sandy-1.071
Mem-1.070
Token:
Token ID25
Feature activation-2.72e-01

Pos logit contributions
heit+1.543
agher+1.512
 Strat+1.505
inav+1.450
llah+1.443
Neg logit contributions
hran-1.912
\--1.896
 CoC-1.886
 sandy-1.833
Mem-1.824
Token 05
Token ID8870
Feature activation+4.63e-02

Pos logit contributions
 CoC+1.711
\-+1.701
hran+1.697
Mem+1.612
 sandy+1.598
Neg logit contributions
heit-2.603
agher-2.577
inav-2.513
 Strat-2.513
ega-2.482
Token50
Token ID1120
Feature activation-2.20e-01

Pos logit contributions
heit+0.305
agher+0.300
 Strat+0.291
inav+0.287
llah+0.284
Neg logit contributions
\--0.432
 CoC-0.429
hran-0.427
Mem-0.415
 sandy-0.413
Token Diego
Token ID9500
Feature activation+9.96e-02

Pos logit contributions
\-+0.931
 CoC+0.914
hran+0.907
Mem+0.885
 sandy+0.869
Neg logit contributions
heit-1.285
agher-1.263
 Strat-1.236
inav-1.231
ega-1.219
Token.
Token ID13
Feature activation-9.71e-03

Pos logit contributions
heit+0.815
agher+0.805
 Strat+0.790
inav+0.776
ega+0.771
Neg logit contributions
\--0.766
hran-0.761
 CoC-0.759
Mem-0.731
 sandy-0.725
Token
Token ID198
Feature activation-1.21e-01

Pos logit contributions
\-+0.074
 CoC+0.073
hran+0.073
Mem+0.070
 sandy+0.070
Neg logit contributions
heit-0.081
agher-0.080
 Strat-0.078
inav-0.077
llah-0.076
Token
Token ID198
Feature activation+2.15e-02

Pos logit contributions
\-+0.879
 CoC+0.859
hran+0.847
Mem+0.837
 sandy+0.814
Neg logit contributions
heit-1.054
agher-1.041
inav-1.006
 Strat-1.005
llah-0.998
TokenSit
Token ID46655
Feature activation+5.38e-02

Pos logit contributions
heit+0.179
agher+0.178
 Strat+0.173
inav+0.172
ega+0.170
Neg logit contributions
\--0.164
Mem-0.160
 CoC-0.160
hran-0.159
Pir-0.154
Token '
Token ID705
Feature activation-1.11e+00

Pos logit contributions
heit+0.533
agher+0.526
 Strat+0.516
inav+0.511
ega+0.507
Neg logit contributions
\--0.323
 CoC-0.320
hran-0.319
Mem-0.304
 sandy-0.302
TokenEm
Token ID10161
Feature activation-9.01e-02

Pos logit contributions
Mem+4.194
Serv+3.762
\-+3.391
Pir+3.330
lems+3.136
Neg logit contributions
heit-13.122
inav-12.846
agher-12.798
 guiActiveUn-12.667
llah-12.614
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
\-+0.668
 CoC+0.664
hran+0.658
Mem+0.644
 sandy+0.631
Neg logit contributions
heit-0.760
agher-0.750
inav-0.729
 Strat-0.728
llah-0.726
Token
Token ID198
Feature activation+3.64e-03

Pos logit contributions
heit+1.156
agher+1.140
 Strat+1.122
inav+1.100
ega+1.091
Neg logit contributions
hran-1.160
\--1.159
 CoC-1.158
 sandy-1.112
Mem-1.105
TokenI
Token ID40
Feature activation+3.57e-01

Pos logit contributions
heit+0.031
agher+0.030
 Strat+0.030
inav+0.029
ega+0.029
Neg logit contributions
\--0.028
 CoC-0.027
hran-0.027
Mem-0.027
Serv-0.026
Token don
Token ID836
Feature activation+4.08e-01

Pos logit contributions
heit+2.775
agher+2.695
 Strat+2.658
inav+2.633
ega+2.600
Neg logit contributions
\--2.904
 CoC-2.893
hran-2.866
Mem-2.762
 sandy-2.760
Token {
Token ID1391
Feature activation-4.11e-01

Pos logit contributions
 CoC+4.332
\-+4.252
Mem+4.212
 Lex+4.136
hran+4.037
Neg logit contributions
heit-7.731
agher-7.701
ega-7.409
inav-7.408
etheus-7.260
Token...
Token ID2644
Feature activation-8.11e-01

Pos logit contributions
\-+2.295
 CoC+2.289
hran+2.278
Mem+2.215
 sandy+2.173
Neg logit contributions
heit-4.188
agher-4.162
 Strat-4.045
inav-4.038
llah-4.011
Token }
Token ID1782
Feature activation-1.59e-01

Pos logit contributions
hran+3.408
\-+3.367
 CoC+3.344
Mem+3.325
 Lex+3.205
Neg logit contributions
heit-9.178
agher-9.022
inav-8.799
 Strat-8.745
llah-8.691
Token impl
Token ID4114
Feature activation+2.08e-01

Pos logit contributions
\-+1.239
 CoC+1.232
hran+1.223
Mem+1.186
 sandy+1.178
Neg logit contributions
heit-1.290
agher-1.272
 Strat-1.237
inav-1.228
llah-1.216
Token <
Token ID1279
Feature activation-5.57e-01

Pos logit contributions
heit+0.830
 Strat+0.810
agher+0.802
inav+0.759
ega+0.744
Neg logit contributions
\--2.474
 CoC-2.429
hran-2.416
 sandy-2.358
lems-2.341
Token '
Token ID705
Feature activation-1.09e+00

Pos logit contributions
 CoC+3.746
\-+3.740
hran+3.641
Mem+3.617
 Lex+3.543
Neg logit contributions
heit-5.007
agher-4.988
inav-4.855
llah-4.783
ega-4.743
Tokena
Token ID64
Feature activation+4.66e-03

Pos logit contributions
\-+6.830
 CoC+6.321
hran+6.307
Mem+6.183
 Lex+5.966
Neg logit contributions
inav-9.830
heit-9.732
agher-9.642
 Strat-9.355
 guiActiveUn-9.191
Token,
Token ID837
Feature activation-2.12e-01

Pos logit contributions
heit+0.038
agher+0.038
 Strat+0.037
llah+0.036
inav+0.036
Neg logit contributions
\--0.036
 CoC-0.036
hran-0.035
Mem-0.034
 sandy-0.034
Token T
Token ID309
Feature activation-3.82e-01

Pos logit contributions
\-+1.647
 CoC+1.636
hran+1.622
Mem+1.574
 sandy+1.562
Neg logit contributions
heit-1.734
agher-1.714
 Strat-1.660
inav-1.653
llah-1.641
Token >
Token ID1875
Feature activation-3.50e-01

Pos logit contributions
\-+3.927
 CoC+3.921
hran+3.897
Mem+3.809
 sandy+3.773
Neg logit contributions
heit-2.134
agher-2.072
inav-1.984
 Strat-1.970
llah-1.929
Token Copy
Token ID17393
Feature activation-1.43e-01

Pos logit contributions
 CoC+1.840
\-+1.828
hran+1.791
Mem+1.752
 sandy+1.704
Neg logit contributions
heit-3.722
agher-3.695
inav-3.575
llah-3.573
 Strat-3.551
Token
Token ID198
Feature activation-9.11e-01

Pos logit contributions
heit+1.319
agher+1.299
 Strat+1.283
inav+1.252
ega+1.243
Neg logit contributions
hran-1.357
 CoC-1.356
\--1.353
 sandy-1.304
Mem-1.293
Token2006
Token ID13330
Feature activation+2.74e-01

Pos logit contributions
Mem+3.872
\-+3.598
Pir+3.526
Serv+3.427
hran+3.358
Neg logit contributions
agher-10.423
inav-10.259
 Strat-10.151
ega-10.146
heit-10.081
Token Kevin
Token ID7939
Feature activation+8.01e-02

Pos logit contributions
heit+2.204
 Strat+2.174
agher+2.173
ega+2.094
llah+2.089
Neg logit contributions
\--2.125
hran-2.112
 CoC-2.103
Mem-2.015
 sandy-1.994
Token James
Token ID3700
Feature activation-2.49e-02

Pos logit contributions
heit+0.697
 Strat+0.691
agher+0.690
inav+0.664
llah+0.657
Neg logit contributions
\--0.571
 CoC-0.567
hran-0.563
Mem-0.540
 sandy-0.537
Token
Token ID198
Feature activation-6.59e-02

Pos logit contributions
\-+0.193
 CoC+0.191
hran+0.190
Mem+0.183
 sandy+0.182
Neg logit contributions
heit-0.204
agher-0.201
 Strat-0.197
inav-0.194
llah-0.192
Token
Token ID198
Feature activation-1.09e+00

Pos logit contributions
\-+0.493
 CoC+0.485
hran+0.481
Mem+0.469
 sandy+0.461
Neg logit contributions
heit-0.558
agher-0.551
 Strat-0.535
inav-0.533
llah-0.529
Token2006
Token ID13330
Feature activation+6.01e-03

Pos logit contributions
Mem+4.443
Pir+4.035
\-+3.986
Serv+3.917
hran+3.789
Neg logit contributions
agher-12.409
inav-12.281
ega-12.151
 Strat-12.124
heit-11.946
Token Charlie
Token ID11526
Feature activation+3.38e-01

Pos logit contributions
heit+0.051
agher+0.050
 Strat+0.049
inav+0.048
llah+0.048
Neg logit contributions
\--0.045
 CoC-0.045
hran-0.044
Mem-0.043
 sandy-0.043
Token Sheen
Token ID50189
Feature activation-2.69e-01

Pos logit contributions
 Strat+2.625
heit+2.571
agher+2.558
inav+2.443
ega+2.441
Neg logit contributions
\--2.728
hran-2.720
 CoC-2.669
Mem-2.593
 sandy-2.546
Token 2007
Token ID4343
Feature activation-3.18e-01

Pos logit contributions
\-+2.035
 CoC+2.017
hran+2.009
Mem+1.939
 sandy+1.927
Neg logit contributions
heit-2.233
agher-2.206
 Strat-2.155
inav-2.132
llah-2.113
Token Ricky
Token ID31668
Feature activation+1.96e-01

Pos logit contributions
\-+2.302
 CoC+2.296
hran+2.254
 Lex+2.217
Mem+2.213
Neg logit contributions
heit-2.729
agher-2.695
inav-2.637
llah-2.577
ega-2.564
Token AK
Token ID15837
Feature activation+7.11e-03

Pos logit contributions
heit+0.878
agher+0.867
 Strat+0.852
inav+0.838
llah+0.833
Neg logit contributions
\--0.681
hran-0.675
 CoC-0.674
Mem-0.647
 sandy-0.643
TokenNOW
Token ID45669
Feature activation+3.70e-01

Pos logit contributions
heit+0.058
agher+0.057
 Strat+0.056
inav+0.055
ega+0.055
Neg logit contributions
\--0.055
 CoC-0.055
hran-0.055
Mem-0.053
 sandy-0.052
TokenLED
Token ID30465
Feature activation+3.54e-01

Pos logit contributions
heit+3.104
agher+2.990
 Strat+2.962
inav+2.920
llah+2.907
Neg logit contributions
 CoC-2.753
hran-2.743
\--2.742
 sandy-2.648
Mem-2.588
TokenG
Token ID38
Feature activation+1.86e-01

Pos logit contributions
heit+2.644
 Strat+2.582
agher+2.541
ega+2.501
inav+2.475
Neg logit contributions
hran-2.939
\--2.887
 CoC-2.884
 sandy-2.827
Mem-2.728
TokenED
Token ID1961
Feature activation+2.12e-01

Pos logit contributions
heit+1.568
agher+1.539
 Strat+1.510
inav+1.489
llah+1.478
Neg logit contributions
\--1.397
hran-1.391
 CoC-1.388
Mem-1.330
 sandy-1.329
Token NET
Token ID30502
Feature activation-1.08e+00

Pos logit contributions
heit+1.860
 Strat+1.829
agher+1.829
inav+1.773
llah+1.761
Neg logit contributions
hran-1.491
\--1.487
 CoC-1.457
Mem-1.408
 sandy-1.396
Token CALL
Token ID42815
Feature activation+1.38e-01

Pos logit contributions
 CoC+4.911
\-+4.627
Mem+4.337
 Lex+4.203
 Mem+4.172
Neg logit contributions
heit-11.913
agher-11.882
inav-11.586
ega-11.299
etheus-11.209
Token UPDATE
Token ID35717
Feature activation+1.70e-01

Pos logit contributions
heit+1.142
agher+1.127
 Strat+1.112
inav+1.088
llah+1.080
Neg logit contributions
\--1.039
hran-1.033
 CoC-1.027
Mem-0.988
 sandy-0.985
Token:
Token ID25
Feature activation-3.47e-01

Pos logit contributions
heit+1.222
agher+1.202
 Strat+1.187
inav+1.150
llah+1.149
Neg logit contributions
\--1.472
hran-1.467
 CoC-1.460
Mem-1.409
 sandy-1.403
Token 05
Token ID8870
Feature activation+2.22e-01

Pos logit contributions
 CoC+2.187
hran+2.167
\-+2.164
Mem+2.060
 sandy+2.024
Neg logit contributions
heit-3.312
agher-3.288
inav-3.203
 Strat-3.182
ega-3.166
Token41
Token ID3901
Feature activation-4.02e-01

Pos logit contributions
heit+1.301
agher+1.275
 Strat+1.242
inav+1.216
ega+1.201
Neg logit contributions
\--2.210
 CoC-2.202
hran-2.199
 sandy-2.136
Mem-2.126
Token There
Token ID1318
Feature activation-2.68e-01

Pos logit contributions
\-+0.402
 CoC+0.400
hran+0.394
Mem+0.383
 sandy+0.378
Neg logit contributions
heit-0.521
agher-0.515
inav-0.500
 Strat-0.498
llah-0.496
Token are
Token ID389
Feature activation+1.98e-01

Pos logit contributions
\-+1.895
hran+1.873
 CoC+1.857
Mem+1.803
 sandy+1.777
Neg logit contributions
heit-2.340
agher-2.318
inav-2.267
 Strat-2.263
ega-2.223
Token knit
Token ID30495
Feature activation-2.05e-01

Pos logit contributions
heit+1.593
agher+1.569
 Strat+1.545
inav+1.507
llah+1.502
Neg logit contributions
\--1.552
 CoC-1.528
hran-1.527
Mem-1.470
 sandy-1.455
Token-
Token ID12
Feature activation-2.62e-01

Pos logit contributions
\-+1.350
 CoC+1.326
hran+1.319
Mem+1.282
 sandy+1.264
Neg logit contributions
heit-1.907
agher-1.890
 Strat-1.845
llah-1.826
ega-1.825
Tokena
Token ID64
Feature activation+5.40e-03

Pos logit contributions
\-+2.031
 CoC+1.987
hran+1.985
Mem+1.936
 sandy+1.899
Neg logit contributions
heit-2.118
agher-2.082
 Strat-2.063
llah-2.024
inav-2.015
Token...
Token ID986
Feature activation-1.07e+00

Pos logit contributions
heit+0.044
agher+0.043
 Strat+0.043
inav+0.042
llah+0.042
Neg logit contributions
\--0.042
 CoC-0.042
hran-0.041
Mem-0.040
 sandy-0.040
Token<|endoftext|>
Token ID50256
Feature activation-7.66e-02

Pos logit contributions
\-+6.623
hran+6.600
 CoC+6.586
Mem+6.381
 sandy+6.279
Neg logit contributions
heit-9.304
agher-9.275
inav-9.032
ega-9.014
 Strat-8.985
TokenBuy
Token ID14518
Feature activation+4.17e-01

Pos logit contributions
\-+0.581
 CoC+0.567
hran+0.567
Mem+0.559
Serv+0.541
Neg logit contributions
heit-0.641
agher-0.634
 Strat-0.620
inav-0.614
llah-0.607
Token Photo
Token ID5555
Feature activation-3.18e-01

Pos logit contributions
heit+4.508
agher+4.436
 Strat+4.426
ega+4.310
inav+4.302
Neg logit contributions
\--2.069
hran-2.045
 CoC-1.990
Mem-1.910
 sandy-1.851
Token F
Token ID376
Feature activation-1.31e-02

Pos logit contributions
\-+2.344
 CoC+2.343
hran+2.295
Mem+2.253
 sandy+2.224
Neg logit contributions
heit-2.703
agher-2.671
inav-2.595
llah-2.563
ega-2.543
TokenSU
Token ID12564
Feature activation+9.52e-03

Pos logit contributions
\-+0.116
hran+0.114
 CoC+0.114
Mem+0.111
 sandy+0.110
Neg logit contributions
heit-0.093
agher-0.091
 Strat-0.089
inav-0.088
llah-0.087
Token FOR
Token ID7473
Feature activation-9.70e-02

Pos logit contributions
\-+1.511
 CoC+1.507
hran+1.468
Mem+1.445
 sandy+1.427
Neg logit contributions
heit-1.817
agher-1.801
inav-1.747
 Strat-1.729
llah-1.722
Token M
Token ID337
Feature activation-5.73e-02

Pos logit contributions
\-+0.679
 CoC+0.675
hran+0.657
Mem+0.647
 sandy+0.636
Neg logit contributions
heit-0.868
agher-0.857
inav-0.833
 Strat-0.830
llah-0.827
TokenEST
Token ID6465
Feature activation-1.59e-01

Pos logit contributions
\-+0.504
 CoC+0.499
hran+0.490
Mem+0.484
 sandy+0.475
Neg logit contributions
heit-0.413
agher-0.405
 Strat-0.393
inav-0.390
llah-0.387
Token OP
Token ID13349
Feature activation-1.76e-01

Pos logit contributions
\-+1.157
 CoC+1.147
hran+1.126
Mem+1.098
 sandy+1.087
Neg logit contributions
heit-1.387
agher-1.375
inav-1.330
 Strat-1.322
llah-1.319
Token V
Token ID569
Feature activation-6.10e-02

Pos logit contributions
\-+1.371
 CoC+1.360
hran+1.321
Mem+1.301
 sandy+1.283
Neg logit contributions
heit-1.442
agher-1.436
llah-1.375
inav-1.375
 Strat-1.365
TokenB
Token ID33
Feature activation-1.07e+00

Pos logit contributions
\-+0.700
 CoC+0.695
hran+0.689
Mem+0.675
 sandy+0.669
Neg logit contributions
heit-0.274
agher-0.272
 Strat-0.255
inav-0.253
llah-0.247
Token 5
Token ID642
Feature activation-2.90e-01

Pos logit contributions
 CoC+7.834
\-+7.806
Mem+7.251
 Lex+7.236
hran+7.138
Neg logit contributions
agher-8.506
heit-8.384
inav-8.264
llah-7.927
essee-7.860
Token92
Token ID5892
Feature activation-4.53e-01

Pos logit contributions
\-+2.056
 CoC+2.041
hran+2.000
Mem+1.954
 sandy+1.890
Neg logit contributions
heit-2.557
agher-2.535
inav-2.458
 Strat-2.445
llah-2.430
Token 4
Token ID604
Feature activation+1.74e-01

Pos logit contributions
\-+3.637
 CoC+3.606
hran+3.465
Mem+3.448
 sandy+3.414
Neg logit contributions
heit-3.542
agher-3.511
inav-3.414
 Strat-3.322
llah-3.315
Token78
Token ID3695
Feature activation-1.05e-01

Pos logit contributions
heit+1.101
agher+1.084
 Strat+1.060
inav+1.036
ega+1.028
Neg logit contributions
\--1.647
hran-1.640
 CoC-1.634
 sandy-1.586
Mem-1.584
Token NET
Token ID30502
Feature activation-1.73e-01

Pos logit contributions
\-+0.786
 CoC+0.780
hran+0.767
Mem+0.748
 sandy+0.742
Neg logit contributions
heit-0.888
agher-0.880
inav-0.851
 Strat-0.849
llah-0.839
TokenPower
Token ID13434
Feature activation+6.77e-01

Pos logit contributions
\-+1.025
 CoC+0.992
Mem+0.986
hran+0.977
Serv+0.952
Neg logit contributions
heit-1.754
agher-1.753
 Strat-1.698
inav-1.696
llah-1.683
Token=
Token ID28
Feature activation+3.76e-01

Pos logit contributions
heit+4.488
 Strat+4.357
agher+4.198
inav+4.145
llah+4.135
Neg logit contributions
hran-6.069
 CoC-5.895
 sandy-5.858
\--5.809
Mem-5.640
Token20
Token ID1238
Feature activation+7.01e-01

Pos logit contributions
heit+2.863
agher+2.804
 Strat+2.739
ega+2.696
llah+2.691
Neg logit contributions
 CoC-3.067
hran-3.052
\--3.016
 sandy-2.967
Mem-2.909
Token dB
Token ID30221
Feature activation+2.55e-01

Pos logit contributions
heit+4.439
 Strat+4.186
agher+4.115
llah+4.048
ega+4.003
Neg logit contributions
hran-6.560
\--6.518
 CoC-6.341
Mem-6.282
 sandy-6.265
Tokenm
Token ID76
Feature activation+2.99e-02

Pos logit contributions
heit+1.486
agher+1.455
 Strat+1.405
inav+1.392
ega+1.377
Neg logit contributions
 CoC-2.544
\--2.540
hran-2.529
 sandy-2.467
Mem-2.438
Token Ret
Token ID4990
Feature activation-1.06e+00

Pos logit contributions
heit+0.284
agher+0.280
 Strat+0.277
inav+0.272
ega+0.270
Neg logit contributions
\--0.192
hran-0.189
 CoC-0.188
Mem-0.179
 sandy-0.179
Tokenry
Token ID563
Feature activation+8.09e-02

Pos logit contributions
\-+3.526
hran+3.252
Mem+3.177
Serv+3.114
lems+3.068
Neg logit contributions
 guiActiveUn-12.542
 Strat-12.506
agher-12.298
heit-12.235
inav-11.988
Token short
Token ID1790
Feature activation-6.22e-01

Pos logit contributions
heit+0.712
agher+0.697
 Strat+0.689
llah+0.675
inav+0.671
Neg logit contributions
\--0.573
hran-0.570
 CoC-0.570
Mem-0.542
 sandy-0.535
Token limit
Token ID4179
Feature activation+3.70e-01

Pos logit contributions
\-+3.550
 CoC+3.463
Mem+3.315
 sandy+3.281
hran+3.217
Neg logit contributions
heit-6.281
agher-6.240
inav-6.027
 Strat-6.019
llah-5.953
Token:
Token ID25
Feature activation+7.34e-02

Pos logit contributions
heit+2.497
agher+2.431
 Strat+2.420
inav+2.330
ega+2.317
Neg logit contributions
hran-3.358
 CoC-3.305
\--3.265
 sandy-3.222
Mem-3.173
Token7
Token ID22
Feature activation-1.17e-01

Pos logit contributions
heit+0.688
agher+0.679
 Strat+0.667
inav+0.660
llah+0.655
Neg logit contributions
\--0.479
 CoC-0.475
hran-0.473
 sandy-0.452
Mem-0.452
Token T
Token ID309
Feature activation+2.87e-01

Pos logit contributions
\-+2.221
 CoC+2.212
hran+2.135
Mem+2.103
 sandy+2.096
Neg logit contributions
heit-2.481
agher-2.477
inav-2.371
llah-2.354
 Strat-2.346
TokenAT
Token ID1404
Feature activation+1.09e-01

Pos logit contributions
heit+1.997
agher+1.961
 Strat+1.935
inav+1.892
ega+1.889
Neg logit contributions
\--2.515
 CoC-2.510
hran-2.507
 sandy-2.438
Mem-2.412
Token
Token ID198
Feature activation+9.44e-02

Pos logit contributions
heit+0.895
agher+0.883
 Strat+0.862
inav+0.853
llah+0.845
Neg logit contributions
\--0.846
 CoC-0.839
hran-0.835
Mem-0.807
 sandy-0.801
Token
Token ID198
Feature activation+1.08e-02

Pos logit contributions
heit+0.767
agher+0.757
 Strat+0.741
inav+0.731
llah+0.724
Neg logit contributions
\--0.733
 CoC-0.728
hran-0.726
Mem-0.699
 sandy-0.697
Token1
Token ID16
Feature activation+1.30e-02

Pos logit contributions
heit+0.089
agher+0.087
 Strat+0.086
inav+0.084
llah+0.084
Neg logit contributions
\--0.084
 CoC-0.082
hran-0.082
Mem-0.081
 sandy-0.079
Tokena
Token ID64
Feature activation-1.06e+00

Pos logit contributions
heit+0.096
agher+0.094
 Strat+0.092
inav+0.091
llah+0.090
Neg logit contributions
\--0.110
 CoC-0.110
hran-0.109
Mem-0.106
 sandy-0.105
Token 1
Token ID352
Feature activation+5.43e-02

Pos logit contributions
\-+7.038
 CoC+6.765
hran+6.673
 Lex+6.640
Mem+6.561
Neg logit contributions
heit-8.903
agher-8.801
inav-8.423
llah-8.370
ega-8.287
Token.
Token ID13
Feature activation+7.41e-02

Pos logit contributions
heit+0.443
agher+0.437
 Strat+0.426
inav+0.422
llah+0.418
Neg logit contributions
\--0.423
 CoC-0.418
hran-0.416
Mem-0.402
 sandy-0.400
Token Sw
Token ID2451
Feature activation+1.39e-01

Pos logit contributions
heit+0.630
agher+0.622
 Strat+0.609
inav+0.601
llah+0.596
Neg logit contributions
\--0.549
 CoC-0.544
hran-0.542
Mem-0.522
 sandy-0.519
Tokenimmer
Token ID10957
Feature activation+3.91e-01

Pos logit contributions
heit+0.982
agher+0.972
 Strat+0.939
inav+0.935
ega+0.924
Neg logit contributions
\--1.234
 CoC-1.229
hran-1.215
Mem-1.182
 sandy-1.182
Token means
Token ID1724
Feature activation+3.40e-01

Pos logit contributions
heit+3.153
agher+3.132
 Strat+3.060
inav+3.005
ega+2.984
Neg logit contributions
\--3.007
hran-2.989
 CoC-2.983
Mem-2.868
 sandy-2.845
TokenACK
Token ID8120
Feature activation+5.88e-01

Pos logit contributions
heit+3.017
 Strat+2.917
agher+2.854
ega+2.752
inav+2.746
Neg logit contributions
hran-4.432
\--4.360
 CoC-4.293
 sandy-4.244
Mem-4.148
TokenH
Token ID39
Feature activation+1.75e-01

Pos logit contributions
heit+4.256
 Strat+4.041
agher+3.972
llah+3.791
inav+3.732
Neg logit contributions
hran-5.057
\--4.939
 CoC-4.905
 sandy-4.775
Serv-4.719
TokenAT
Token ID1404
Feature activation+2.93e-01

Pos logit contributions
heit+1.264
agher+1.230
 Strat+1.216
ega+1.182
inav+1.181
Neg logit contributions
hran-1.517
\--1.509
 CoC-1.503
 sandy-1.452
Mem-1.438
Token,
Token ID11
Feature activation+8.44e-02

Pos logit contributions
heit+2.466
agher+2.378
 Strat+2.372
inav+2.290
llah+2.281
Neg logit contributions
hran-2.212
\--2.165
 CoC-2.143
 sandy-2.085
Mem-2.052
Token rect
Token ID13621
Feature activation-3.67e-01

Pos logit contributions
heit+0.670
agher+0.662
 Strat+0.646
inav+0.638
llah+0.633
Neg logit contributions
\--0.672
 CoC-0.667
hran-0.664
Mem-0.642
 sandy-0.638
TokenK
Token ID42
Feature activation-1.06e+00

Pos logit contributions
\-+2.246
 CoC+2.197
hran+2.177
Mem+2.135
 sandy+2.053
Neg logit contributions
heit-3.581
agher-3.556
 Strat-3.494
inav-3.445
llah-3.413
Tokenernel
Token ID7948
Feature activation+1.10e-01

Pos logit contributions
\-+3.583
Mem+3.436
hran+3.103
 CoC+2.959
Serv+2.942
Neg logit contributions
 Strat-12.589
agher-12.505
heit-12.306
 guiActiveUn-12.150
inav-11.854
Token)
Token ID8
Feature activation+6.95e-02

Pos logit contributions
heit+0.926
agher+0.907
 Strat+0.894
inav+0.875
ega+0.874
Neg logit contributions
\--0.820
hran-0.817
 CoC-0.814
 sandy-0.781
Mem-0.776
Token 17
Token ID1596
Feature activation-3.38e-01

Pos logit contributions
heit+0.587
agher+0.578
 Strat+0.569
inav+0.559
ega+0.554
Neg logit contributions
\--0.518
hran-0.513
 CoC-0.511
Mem-0.492
 sandy-0.487
Token 18
Token ID1248
Feature activation-3.80e-01

Pos logit contributions
 CoC+2.527
\-+2.514
hran+2.469
Mem+2.455
 sandy+2.436
Neg logit contributions
heit-2.792
agher-2.765
inav-2.709
 Strat-2.643
llah-2.611
Token 19
Token ID678
Feature activation-2.06e-01

Pos logit contributions
 CoC+3.147
\-+3.123
hran+3.107
Mem+3.045
 sandy+3.025
Neg logit contributions
heit-2.869
agher-2.811
inav-2.754
ega-2.712
llah-2.708
Token.
Token ID13
Feature activation+1.76e-01

Pos logit contributions
heit+0.543
agher+0.535
 Strat+0.523
inav+0.517
llah+0.512
Neg logit contributions
\--0.547
 CoC-0.543
hran-0.540
Mem-0.522
 sandy-0.519
Token
Token ID447
Feature activation+2.26e-01

Pos logit contributions
heit+1.488
agher+1.468
 Strat+1.449
inav+1.425
llah+1.411
Neg logit contributions
\--1.297
hran-1.290
 CoC-1.280
Mem-1.233
 sandy-1.232
Token
Token ID251
Feature activation+1.36e-01

Pos logit contributions
heit+1.846
agher+1.809
 Strat+1.778
llah+1.760
inav+1.751
Neg logit contributions
\--1.720
 CoC-1.716
hran-1.709
Mem-1.651
 sandy-1.651
Token
Token ID198
Feature activation-2.70e-02

Pos logit contributions
heit+1.149
agher+1.135
 Strat+1.111
inav+1.097
llah+1.088
Neg logit contributions
\--1.010
 CoC-1.000
hran-0.998
Mem-0.960
 sandy-0.956
Token
Token ID198
Feature activation+2.17e-01

Pos logit contributions
\-+0.203
 CoC+0.200
hran+0.198
Mem+0.194
 sandy+0.190
Neg logit contributions
heit-0.229
agher-0.226
 Strat-0.219
inav-0.218
llah-0.216
TokenV
Token ID53
Feature activation+6.71e-01

Pos logit contributions
heit+1.848
agher+1.824
 Strat+1.790
inav+1.765
ega+1.749
Neg logit contributions
\--1.590
hran-1.588
 CoC-1.583
 sandy-1.522
Mem-1.495
Tokenac
Token ID330
Feature activation-8.75e-02

Pos logit contributions
heit+4.813
agher+4.756
ega+4.672
 Strat+4.619
inav+4.588
Neg logit contributions
\--5.677
 CoC-5.647
hran-5.609
 sandy-5.484
Mem-5.396
Tokenation
Token ID341
Feature activation+4.92e-01

Pos logit contributions
\-+0.786
 CoC+0.781
hran+0.773
Mem+0.757
 sandy+0.750
Neg logit contributions
heit-0.606
agher-0.596
 Strat-0.578
inav-0.572
llah-0.567
Token Time
Token ID3862
Feature activation+5.05e-01

Pos logit contributions
heit+4.178
 Strat+4.120
agher+4.084
inav+3.984
ega+3.974
Neg logit contributions
hran-3.549
\--3.529
 CoC-3.479
 sandy-3.341
Mem-3.319
Token
Token ID784
Feature activation+1.02e-01

Pos logit contributions
heit+4.011
 Strat+3.918
agher+3.889
inav+3.745
ega+3.738
Neg logit contributions
hran-3.936
\--3.909
 CoC-3.847
 sandy-3.753
Mem-3.675
Token Cat
Token ID5181
Feature activation+3.28e-01

Pos logit contributions
heit+0.904
agher+0.892
 Strat+0.879
inav+0.866
llah+0.858
Neg logit contributions
\--0.723
hran-0.716
 CoC-0.713
Mem-0.685
 sandy-0.682
Token
Token ID447
Feature activation-8.22e-02

Pos logit contributions
heit+4.670
 Strat+4.553
agher+4.535
ega+4.381
llah+4.335
Neg logit contributions
hran-5.134
 CoC-5.100
\--5.035
Mem-4.925
 sandy-4.833
Token
Token ID247
Feature activation+1.60e-01

Pos logit contributions
\-+0.663
hran+0.653
 CoC+0.652
Mem+0.626
 sandy+0.624
Neg logit contributions
heit-0.648
agher-0.644
 Strat-0.625
inav-0.621
ega-0.610
Token8
Token ID23
Feature activation+3.66e-01

Pos logit contributions
heit+1.387
agher+1.371
 Strat+1.340
inav+1.328
llah+1.315
Neg logit contributions
\--1.156
 CoC-1.142
hran-1.137
Mem-1.097
 sandy-1.091
Token
Token ID447
Feature activation-1.53e-02

Pos logit contributions
heit+3.019
agher+2.990
 Strat+2.920
inav+2.866
llah+2.858
Neg logit contributions
 CoC-2.753
\--2.751
hran-2.736
Mem-2.633
 sandy-2.609
Token
Token ID251
Feature activation+2.55e-01

Pos logit contributions
\-+0.123
hran+0.122
 CoC+0.121
Mem+0.117
 sandy+0.116
Neg logit contributions
heit-0.121
agher-0.120
 Strat-0.117
inav-0.116
ega-0.114
Token to
Token ID284
Feature activation+6.56e-01

Pos logit contributions
heit+2.212
agher+2.185
 Strat+2.140
inav+2.111
llah+2.094
Neg logit contributions
\--1.843
 CoC-1.832
hran-1.825
Mem-1.751
 sandy-1.739
Token 7
Token ID767
Feature activation+3.46e-01

Pos logit contributions
heit+4.470
 Strat+4.446
agher+4.412
inav+4.257
llah+4.225
Neg logit contributions
hran-5.665
\--5.625
 CoC-5.563
Mem-5.458
Serv-5.340
Token
Token ID447
Feature activation-7.07e-02

Pos logit contributions
heit+2.079
agher+2.047
 Strat+1.990
llah+1.952
inav+1.941
Neg logit contributions
 CoC-3.364
\--3.342
hran-3.331
 sandy-3.240
Mem-3.236
Token
Token ID247
Feature activation+2.68e-01

Pos logit contributions
\-+0.579
hran+0.569
 CoC+0.567
Mem+0.543
 sandy+0.541
Neg logit contributions
heit-0.552
agher-0.549
 Strat-0.534
inav-0.534
ega-0.518
Token8
Token ID23
Feature activation+4.88e-01

Pos logit contributions
heit+2.353
agher+2.326
 Strat+2.277
inav+2.252
llah+2.233
Neg logit contributions
\--1.889
 CoC-1.884
hran-1.872
Mem-1.797
 sandy-1.795
Token
Token ID447
Feature activation-6.11e-02

Pos logit contributions
heit+3.241
agher+3.208
 Strat+3.127
llah+3.061
inav+3.043
Neg logit contributions
 CoC-4.383
\--4.344
hran-4.327
Mem-4.211
 sandy-4.190
Token While
Token ID2893
Feature activation+1.06e-03

Pos logit contributions
\-+0.463
 CoC+0.461
hran+0.456
Mem+0.440
 sandy+0.435
Neg logit contributions
heit-0.641
agher-0.634
inav-0.616
 Strat-0.614
ega-0.610
Token finding
Token ID4917
Feature activation+6.92e-02

Pos logit contributions
heit+0.009
agher+0.009
 Strat+0.009
inav+0.009
llah+0.009
Neg logit contributions
\--0.008
 CoC-0.008
hran-0.008
Mem-0.007
 sandy-0.007
Token a
Token ID257
Feature activation+3.60e-02

Pos logit contributions
heit+0.601
agher+0.594
 Strat+0.583
inav+0.574
llah+0.570
Neg logit contributions
\--0.501
 CoC-0.495
hran-0.493
Mem-0.475
 sandy-0.470
Token "
Token ID366
Feature activation+5.85e-02

Pos logit contributions
heit+0.286
agher+0.282
 Strat+0.276
inav+0.272
llah+0.270
Neg logit contributions
\--0.286
 CoC-0.284
hran-0.283
Mem-0.273
 sandy-0.272
Tokenfail
Token ID32165
Feature activation+9.06e-01

Pos logit contributions
heit+0.503
agher+0.497
 Strat+0.486
inav+0.480
llah+0.476
Neg logit contributions
\--0.429
 CoC-0.425
hran-0.423
Mem-0.408
 sandy-0.405
Tokenure
Token ID495
Feature activation+6.86e-01

Pos logit contributions
heit+4.101
agher+3.855
 Strat+3.778
ega+3.649
inav+3.541
Neg logit contributions
hran-9.778
\--9.670
 CoC-9.611
Serv-9.435
lems-9.335
Token mode
Token ID4235
Feature activation+3.15e-01

Pos logit contributions
heit+4.849
 Strat+4.648
agher+4.625
ega+4.462
llah+4.419
Neg logit contributions
\--5.870
hran-5.822
 CoC-5.748
Serv-5.590
lems-5.526
Token"
Token ID1
Feature activation-1.84e-01

Pos logit contributions
heit+1.789
agher+1.741
 Strat+1.718
ega+1.643
inav+1.636
Neg logit contributions
\--3.182
hran-3.167
 CoC-3.140
Mem-3.043
 sandy-3.010
Token affected
Token ID5676
Feature activation-1.19e-02

Pos logit contributions
 CoC+1.358
\-+1.356
hran+1.337
 sandy+1.299
Mem+1.295
Neg logit contributions
heit-1.555
agher-1.545
inav-1.502
 Strat-1.495
llah-1.486
Token the
Token ID262
Feature activation-3.24e-01

Pos logit contributions
\-+0.086
 CoC+0.086
hran+0.085
Mem+0.082
 sandy+0.081
Neg logit contributions
heit-0.103
agher-0.102
 Strat-0.100
inav-0.099
llah-0.098
Token air
Token ID1633
Feature activation-1.38e-01

Pos logit contributions
 CoC+2.467
\-+2.400
hran+2.400
 sandy+2.345
Mem+2.306
Neg logit contributions
agher-2.664
heit-2.658
inav-2.589
ega-2.560
llah-2.534
Token
Token ID12466
Feature activation+2.77e-01

Pos logit contributions
heit+0.839
agher+0.828
 Strat+0.810
inav+0.799
llah+0.793
Neg logit contributions
\--0.765
 CoC-0.759
hran-0.755
Mem-0.728
 sandy-0.724
Token
Token ID115
Feature activation+2.11e-01

Pos logit contributions
heit+1.692
agher+1.658
 Strat+1.611
inav+1.584
llah+1.575
Neg logit contributions
\--2.702
 CoC-2.681
hran-2.673
Mem-2.604
 sandy-2.592
Tokenа
Token ID16142
Feature activation+2.34e-01

Pos logit contributions
heit+1.550
agher+1.527
 Strat+1.488
inav+1.468
llah+1.453
Neg logit contributions
\--1.809
 CoC-1.795
hran-1.789
Mem-1.733
 sandy-1.724
Token
Token ID141
Feature activation+2.72e-01

Pos logit contributions
heit+1.928
agher+1.902
 Strat+1.874
inav+1.836
llah+1.829
Neg logit contributions
\--1.770
 CoC-1.756
hran-1.750
Mem-1.680
 sandy-1.679
Token
Token ID229
Feature activation+1.40e-01

Pos logit contributions
heit+2.177
agher+2.145
 Strat+2.106
inav+2.070
llah+2.061
Neg logit contributions
\--2.123
hran-2.109
 CoC-2.107
Mem-2.030
 sandy-2.019
Tokenа
Token ID16142
Feature activation+6.75e-01

Pos logit contributions
heit+1.167
agher+1.154
 Strat+1.127
inav+1.114
llah+1.105
Neg logit contributions
\--1.057
 CoC-1.049
hran-1.045
Mem-1.008
 sandy-1.003
Tokenс
Token ID21727
Feature activation+5.12e-01

Pos logit contributions
heit+5.405
agher+5.287
 Strat+5.205
llah+5.148
ega+5.093
Neg logit contributions
 CoC-4.999
hran-4.995
\--4.959
Mem-4.811
 sandy-4.785
Tokenт
Token ID20375
Feature activation+3.09e-01

Pos logit contributions
heit+4.004
agher+3.833
 Strat+3.820
llah+3.765
inav+3.703
Neg logit contributions
\--4.088
 CoC-4.080
hran-4.023
Mem-3.910
 sandy-3.894
Tokenу
Token ID35072
Feature activation+2.78e-01

Pos logit contributions
heit+2.276
agher+2.227
 Strat+2.186
inav+2.140
llah+2.132
Neg logit contributions
\--2.618
hran-2.600
 CoC-2.588
Mem-2.514
 sandy-2.506
Token
Token ID141
Feature activation+1.62e-01

Pos logit contributions
heit+2.360
agher+2.310
 Strat+2.276
inav+2.234
llah+2.227
Neg logit contributions
\--2.062
hran-2.041
 CoC-2.031
Mem-1.959
 sandy-1.947
Token
Token ID236
Feature activation+5.35e-01

Pos logit contributions
heit+1.152
agher+1.136
 Strat+1.105
inav+1.091
llah+1.079
Neg logit contributions
\--1.427
 CoC-1.416
hran-1.410
Mem-1.368
 sandy-1.361
Token
Token ID227
Feature activation-2.49e-01

Pos logit contributions
\-+0.400
 CoC+0.392
hran+0.385
Mem+0.379
 sandy+0.376
Neg logit contributions
heit-0.340
agher-0.336
inav-0.325
 Strat-0.322
llah-0.318
Token
Token ID12466
Feature activation+1.89e-03

Pos logit contributions
\-+1.765
 CoC+1.752
hran+1.717
Mem+1.669
 sandy+1.661
Neg logit contributions
heit-2.177
agher-2.174
inav-2.100
 Strat-2.078
ega-2.072
Token
Token ID121
Feature activation+7.12e-02

Pos logit contributions
heit+0.012
agher+0.012
 Strat+0.011
inav+0.011
ega+0.011
Neg logit contributions
\--0.018
 CoC-0.018
hran-0.018
Mem-0.018
 sandy-0.018
Tokenа
Token ID16142
Feature activation-2.38e-01

Pos logit contributions
heit+0.568
agher+0.561
 Strat+0.547
inav+0.540
llah+0.535
Neg logit contributions
\--0.566
 CoC-0.561
hran-0.559
Mem-0.540
 sandy-0.537
Token
Token ID141
Feature activation+1.87e-01

Pos logit contributions
\-+1.758
 CoC+1.743
hran+1.724
Mem+1.680
 sandy+1.660
Neg logit contributions
heit-2.030
agher-2.000
 Strat-1.930
inav-1.926
llah-1.915
Token
Token ID239
Feature activation+8.75e-01

Pos logit contributions
heit+1.428
agher+1.409
 Strat+1.377
inav+1.357
ega+1.350
Neg logit contributions
\--1.532
hran-1.521
 CoC-1.519
Mem-1.468
 sandy-1.461
Tokenм
Token ID43108
Feature activation+2.13e-01

Pos logit contributions
heit+5.741
agher+5.622
 Strat+5.589
llah+5.371
inav+5.338
Neg logit contributions
\--7.553
hran-7.532
 CoC-7.493
 sandy-7.221
Mem-7.158
Tokenн
Token ID22177
Feature activation+2.24e-01

Pos logit contributions
heit+1.906
agher+1.871
 Strat+1.849
inav+1.813
ega+1.809
Neg logit contributions
\--1.458
hran-1.458
 CoC-1.448
Mem-1.388
 sandy-1.377
Tokenи
Token ID18849
Feature activation+2.29e-01

Pos logit contributions
heit+1.939
agher+1.910
 Strat+1.874
inav+1.838
llah+1.837
Neg logit contributions
hran-1.601
\--1.599
 CoC-1.596
 sandy-1.520
Mem-1.519
Tokenк
Token ID31583
Feature activation+2.64e-01

Pos logit contributions
heit+1.864
agher+1.841
 Strat+1.824
ega+1.776
inav+1.772
Neg logit contributions
\--1.741
hran-1.720
 CoC-1.716
Mem-1.659
 sandy-1.645
Tokenо�
Token ID25443
Feature activation-1.20e-01

Pos logit contributions
heit+1.967
agher+1.918
 Strat+1.894
inav+1.849
ega+1.839
Neg logit contributions
\--2.210
hran-2.207
 CoC-2.206
Mem-2.129
 sandy-2.112
Token in
Token ID287
Feature activation-5.31e-02

Pos logit contributions
\-+0.551
 CoC+0.542
hran+0.539
Mem+0.523
 sandy+0.521
Neg logit contributions
heit-0.675
agher-0.674
inav-0.654
 Strat-0.648
llah-0.643
Token a
Token ID257
Feature activation+2.64e-02

Pos logit contributions
\-+0.374
 CoC+0.373
hran+0.366
 sandy+0.357
Mem+0.357
Neg logit contributions
heit-0.470
agher-0.464
inav-0.456
llah-0.448
 Strat-0.445
Token computer
Token ID3644
Feature activation-1.45e-01

Pos logit contributions
heit+0.214
agher+0.211
 Strat+0.203
inav+0.203
llah+0.202
Neg logit contributions
\--0.208
 CoC-0.207
hran-0.205
Mem-0.199
 sandy-0.198
Token malfunction
Token ID35654
Feature activation-1.66e-01

Pos logit contributions
\-+1.068
 CoC+1.054
hran+1.048
 sandy+1.015
Mem+1.014
Neg logit contributions
heit-1.254
agher-1.234
inav-1.192
llah-1.188
 Strat-1.188
Token,
Token ID11
Feature activation-8.30e-02

Pos logit contributions
\-+1.199
 CoC+1.180
hran+1.175
Mem+1.136
 sandy+1.128
Neg logit contributions
heit-1.449
agher-1.427
inav-1.389
 Strat-1.386
llah-1.374
Token and
Token ID290
Feature activation-9.86e-03

Pos logit contributions
\-+0.592
 CoC+0.585
hran+0.580
Mem+0.561
 sandy+0.559
Neg logit contributions
heit-0.731
agher-0.718
inav-0.705
 Strat-0.699
ega-0.694
Token released
Token ID2716
Feature activation-3.65e-01

Pos logit contributions
\-+0.072
 CoC+0.072
hran+0.071
Mem+0.069
 sandy+0.068
Neg logit contributions
heit-0.085
agher-0.084
inav-0.082
 Strat-0.081
ega-0.081
Token them
Token ID606
Feature activation-4.78e-01

Pos logit contributions
\-+2.494
 CoC+2.470
hran+2.392
Mem+2.369
 sandy+2.359
Neg logit contributions
agher-3.265
heit-3.257
inav-3.219
ega-3.141
llah-3.102
Token Tuesday
Token ID3431
Feature activation-3.51e-01

Pos logit contributions
\-+3.365
 CoC+3.270
hran+3.202
Mem+3.180
 sandy+3.139
Neg logit contributions
heit-4.146
agher-4.130
inav-4.102
llah-3.972
ega-3.941
Token.
Token ID13
Feature activation-1.40e-01

Pos logit contributions
\-+2.513
 CoC+2.437
hran+2.417
Mem+2.383
 sandy+2.364
Neg logit contributions
heit-3.030
agher-2.988
inav-2.974
llah-2.911
 Strat-2.907
Token
Token ID198
Feature activation-6.50e-02

Pos logit contributions
\-+1.008
 CoC+0.996
hran+0.983
Mem+0.957
 sandy+0.938
Neg logit contributions
heit-1.227
agher-1.214
inav-1.183
 Strat-1.170
ega-1.167
Token as
Token ID355
Feature activation+5.90e-03

Pos logit contributions
\-+1.051
 CoC+1.036
hran+1.028
 sandy+0.995
Mem+0.994
Neg logit contributions
heit-1.208
agher-1.198
 Strat-1.158
inav-1.153
ega-1.142
Token Ma
Token ID6669
Feature activation+4.23e-03

Pos logit contributions
heit+0.050
agher+0.049
 Strat+0.048
inav+0.048
ega+0.047
Neg logit contributions
\--0.044
 CoC-0.044
hran-0.044
Mem-0.042
 sandy-0.042
Tokenureen
Token ID49851
Feature activation+4.38e-01

Pos logit contributions
heit+0.029
agher+0.028
 Strat+0.027
inav+0.027
llah+0.027
Neg logit contributions
\--0.039
hran-0.038
 CoC-0.038
Mem-0.037
 sandy-0.037
Token Dow
Token ID21842
Feature activation-7.06e-02

Pos logit contributions
heit+3.666
agher+3.621
 Strat+3.619
inav+3.484
ega+3.443
Neg logit contributions
\--3.233
 CoC-3.209
hran-3.174
Mem-3.083
 sandy-3.046
Tokend
Token ID67
Feature activation-9.38e-02

Pos logit contributions
\-+0.599
 CoC+0.592
hran+0.591
Mem+0.572
 sandy+0.570
Neg logit contributions
heit-0.526
agher-0.516
 Strat-0.504
inav-0.499
llah-0.493
Token recounted
Token ID34187
Feature activation-1.73e-03

Pos logit contributions
\-+0.715
hran+0.704
 CoC+0.701
Mem+0.679
 sandy+0.675
Neg logit contributions
heit-0.773
agher-0.766
 Strat-0.747
inav-0.744
llah-0.733
Token in
Token ID287
Feature activation+6.27e-02

Pos logit contributions
\-+0.013
 CoC+0.013
hran+0.013
Mem+0.012
 sandy+0.012
Neg logit contributions
heit-0.015
agher-0.014
 Strat-0.014
inav-0.014
llah-0.014
Token the
Token ID262
Feature activation+1.00e-01

Pos logit contributions
heit+0.544
agher+0.538
 Strat+0.526
inav+0.520
llah+0.516
Neg logit contributions
\--0.453
 CoC-0.449
hran-0.447
Mem-0.431
 sandy-0.428
Token New
Token ID968
Feature activation+2.10e-02

Pos logit contributions
heit+0.831
agher+0.822
 Strat+0.806
inav+0.794
llah+0.787
Neg logit contributions
\--0.763
 CoC-0.756
hran-0.754
Mem-0.726
 sandy-0.721
Token York
Token ID1971
Feature activation+3.10e-01

Pos logit contributions
heit+0.231
agher+0.229
 Strat+0.225
inav+0.223
ega+0.221
Neg logit contributions
\--0.104
 CoC-0.103
hran-0.101
Mem-0.096
 sandy-0.095
Token Times
Token ID3782
Feature activation+2.00e-01

Pos logit contributions
agher+1.636
heit+1.634
 Strat+1.600
inav+1.533
llah+1.513
Neg logit contributions
\--3.237
 CoC-3.224
hran-3.223
Mem-3.123
 sandy-3.113
Tokenph
Token ID746
Feature activation-6.80e-02

Pos logit contributions
heit+0.202
agher+0.199
 Strat+0.194
inav+0.192
llah+0.190
Neg logit contributions
\--0.189
hran-0.187
 CoC-0.186
Mem-0.181
 sandy-0.178
Tokenases
Token ID1386
Feature activation-5.31e-02

Pos logit contributions
\-+0.521
hran+0.514
 CoC+0.512
Mem+0.497
 sandy+0.492
Neg logit contributions
heit-0.560
agher-0.554
 Strat-0.539
inav-0.535
llah-0.531
Token added
Token ID2087
Feature activation-2.45e-01

Pos logit contributions
\-+0.406
 CoC+0.399
hran+0.398
 sandy+0.385
Mem+0.385
Neg logit contributions
heit-0.443
agher-0.438
 Strat-0.424
inav-0.424
llah-0.418
Token],"
Token ID17241
Feature activation+2.80e-03

Pos logit contributions
\-+1.785
 CoC+1.727
hran+1.726
Mem+1.679
 sandy+1.669
Neg logit contributions
heit-2.121
agher-2.106
inav-2.039
 Strat-2.031
llah-2.023
Token r
Token ID374
Feature activation+1.90e-02

Pos logit contributions
heit+0.023
agher+0.023
 Strat+0.022
inav+0.022
llah+0.022
Neg logit contributions
\--0.021
 CoC-0.021
hran-0.021
Mem-0.020
 sandy-0.020
Tokenaves
Token ID3080
Feature activation+4.13e-01

Pos logit contributions
heit+0.188
agher+0.186
 Strat+0.183
inav+0.181
llah+0.180
Neg logit contributions
\--0.113
hran-0.112
 CoC-0.112
Mem-0.107
 sandy-0.106
Token the
Token ID262
Feature activation+2.32e-01

Pos logit contributions
heit+3.530
agher+3.511
 Strat+3.449
inav+3.380
ega+3.364
Neg logit contributions
\--2.997
 CoC-2.936
hran-2.917
Mem-2.817
 sandy-2.784
Token Los
Token ID5401
Feature activation-3.53e-01

Pos logit contributions
heit+1.947
agher+1.923
 Strat+1.888
inav+1.861
llah+1.844
Neg logit contributions
\--1.744
 CoC-1.723
hran-1.718
Mem-1.653
 sandy-1.641
Token Angeles
Token ID5652
Feature activation+3.95e-01

Pos logit contributions
\-+2.076
hran+2.071
 CoC+2.034
Mem+1.967
 sandy+1.942
Neg logit contributions
agher-3.481
heit-3.472
 Strat-3.344
inav-3.338
ega-3.313
Token Times
Token ID3782
Feature activation+4.51e-01

Pos logit contributions
heit+2.273
agher+2.221
 Strat+2.198
inav+2.122
llah+2.106
Neg logit contributions
\--3.941
hran-3.934
 CoC-3.921
Mem-3.806
 sandy-3.779
Token.
Token ID13
Feature activation+9.27e-02

Pos logit contributions
heit+3.522
agher+3.473
 Strat+3.402
inav+3.331
ega+3.308
Neg logit contributions
\--3.620
 CoC-3.573
hran-3.544
Mem-3.413
 sandy-3.408
Token only
Token ID691
Feature activation+3.62e-02

Pos logit contributions
heit+2.499
agher+2.461
 Strat+2.417
inav+2.365
llah+2.362
Neg logit contributions
\--2.318
 CoC-2.300
hran-2.296
Mem-2.222
 sandy-2.162
Token the
Token ID262
Feature activation-3.65e-01

Pos logit contributions
heit+0.302
agher+0.298
 Strat+0.291
inav+0.287
llah+0.285
Neg logit contributions
\--0.275
 CoC-0.272
hran-0.271
Mem-0.262
 sandy-0.260
Token room
Token ID2119
Feature activation-3.76e-01

Pos logit contributions
 CoC+2.810
\-+2.781
hran+2.728
 sandy+2.714
Mem+2.661
Neg logit contributions
heit-2.978
agher-2.957
 Strat-2.847
inav-2.847
ega-2.840
Token where
Token ID810
Feature activation-1.29e-01

Pos logit contributions
\-+2.584
 CoC+2.548
hran+2.525
 sandy+2.472
Mem+2.461
Neg logit contributions
agher-3.354
heit-3.324
inav-3.258
 Strat-3.232
ega-3.197
Token the
Token ID262
Feature activation-1.59e-01

Pos logit contributions
\-+0.924
 CoC+0.917
hran+0.911
Mem+0.880
 sandy+0.878
Neg logit contributions
heit-1.124
agher-1.114
 Strat-1.087
inav-1.080
llah-1.069
Token monkey
Token ID21657
Feature activation+1.76e-01

Pos logit contributions
\-+1.216
 CoC+1.214
hran+1.200
 sandy+1.167
Mem+1.166
Neg logit contributions
heit-1.314
agher-1.300
 Strat-1.259
inav-1.254
llah-1.243
Token is
Token ID318
Feature activation-1.90e-02

Pos logit contributions
heit+1.409
agher+1.389
 Strat+1.363
inav+1.340
ega+1.332
Neg logit contributions
\--1.384
 CoC-1.377
hran-1.377
Mem-1.317
 sandy-1.309
Token currently
Token ID3058
Feature activation-8.00e-02

Pos logit contributions
\-+0.154
 CoC+0.152
hran+0.152
Mem+0.147
 sandy+0.147
Neg logit contributions
heit-0.149
agher-0.147
 Strat-0.143
inav-0.142
llah-0.141
Token in
Token ID287
Feature activation-2.28e-01

Pos logit contributions
\-+0.602
 CoC+0.594
hran+0.591
 sandy+0.574
Mem+0.574
Neg logit contributions
heit-0.675
agher-0.665
 Strat-0.647
inav-0.646
llah-0.639
Token is
Token ID318
Feature activation+8.62e-02

Pos logit contributions
\-+1.689
 CoC+1.665
hran+1.653
Mem+1.606
 sandy+1.600
Neg logit contributions
heit-1.914
agher-1.911
 Strat-1.861
inav-1.847
ega-1.823
Token illuminated
Token ID35162
Feature activation-2.08e-01

Pos logit contributions
heit+0.688
agher+0.678
 Strat+0.663
inav+0.652
llah+0.648
Neg logit contributions
\--0.683
 CoC-0.677
hran-0.675
Mem-0.653
 sandy-0.646
Token items
Token ID3709
Feature activation+1.43e-01

Pos logit contributions
\-+0.056
 CoC+0.055
hran+0.055
Mem+0.054
 sandy+0.053
Neg logit contributions
heit-0.056
agher-0.055
 Strat-0.054
inav-0.053
ega-0.053
Token.
Token ID13
Feature activation+8.09e-02

Pos logit contributions
heit+1.189
agher+1.176
 Strat+1.150
inav+1.134
llah+1.127
Neg logit contributions
\--1.081
 CoC-1.073
hran-1.069
Mem-1.029
 sandy-1.021
Token
Token ID198
Feature activation+1.38e-01

Pos logit contributions
heit+0.676
agher+0.668
 Strat+0.653
inav+0.645
llah+0.640
Neg logit contributions
\--0.611
 CoC-0.606
hran-0.604
Mem-0.582
 sandy-0.579
Token
Token ID198
Feature activation+4.22e-02

Pos logit contributions
heit+1.096
agher+1.080
 Strat+1.062
inav+1.043
llah+1.034
Neg logit contributions
\--1.085
 CoC-1.082
hran-1.082
 sandy-1.039
Mem-1.035
TokenThe
Token ID464
Feature activation+2.11e-01

Pos logit contributions
heit+0.355
agher+0.352
 Strat+0.343
inav+0.339
ega+0.336
Neg logit contributions
\--0.319
 CoC-0.313
hran-0.311
Mem-0.307
Serv-0.297
Token rationale
Token ID25738
Feature activation-1.06e-01

Pos logit contributions
heit+1.593
agher+1.569
 Strat+1.534
inav+1.513
llah+1.499
Neg logit contributions
\--1.759
 CoC-1.742
hran-1.738
Mem-1.681
 sandy-1.670
Token for
Token ID329
Feature activation+4.08e-02

Pos logit contributions
\-+0.790
 CoC+0.782
hran+0.776
Mem+0.749
 sandy+0.746
Neg logit contributions
heit-0.900
agher-0.890
 Strat-0.866
inav-0.863
ega-0.851
Token the
Token ID262
Feature activation+1.04e-01

Pos logit contributions
heit+0.355
agher+0.349
 Strat+0.340
inav+0.338
ega+0.335
Neg logit contributions
 CoC-0.296
\--0.295
hran-0.292
 sandy-0.282
Mem-0.282
Token policy
Token ID2450
Feature activation-2.10e-02

Pos logit contributions
heit+0.798
agher+0.787
 Strat+0.763
inav+0.755
ega+0.751
Neg logit contributions
\--0.860
 CoC-0.858
hran-0.852
Mem-0.825
 sandy-0.824
Token change
Token ID1487
Feature activation-2.30e-01

Pos logit contributions
\-+0.161
 CoC+0.159
hran+0.159
Mem+0.153
 sandy+0.152
Neg logit contributions
heit-0.174
agher-0.172
 Strat-0.168
inav-0.166
llah-0.165
Token given
Token ID1813
Feature activation-4.67e-01

Pos logit contributions
\-+1.715
hran+1.683
 CoC+1.682
Mem+1.619
 sandy+1.607
Neg logit contributions
heit-1.943
agher-1.927
 Strat-1.874
inav-1.859
llah-1.843
Token,
Token ID11
Feature activation+1.47e-01

Pos logit contributions
heit+2.036
agher+1.995
 Strat+1.972
inav+1.922
llah+1.916
Neg logit contributions
\--1.928
hran-1.920
 CoC-1.917
Mem-1.846
 sandy-1.832
Token this
Token ID428
Feature activation+2.80e-01

Pos logit contributions
heit+1.229
agher+1.221
 Strat+1.211
inav+1.181
llah+1.164
Neg logit contributions
\--1.093
hran-1.084
 CoC-1.070
Mem-1.040
 sandy-1.025
Token line
Token ID1627
Feature activation+2.44e-01

Pos logit contributions
heit+2.177
agher+2.161
 Strat+2.151
inav+2.084
ega+2.055
Neg logit contributions
\--2.220
hran-2.211
 CoC-2.203
Mem-2.124
 sandy-2.106
Token just
Token ID655
Feature activation+1.10e-01

Pos logit contributions
heit+1.917
agher+1.900
 Strat+1.855
inav+1.835
ega+1.820
Neg logit contributions
 CoC-1.932
hran-1.926
\--1.923
Mem-1.850
 sandy-1.845
Token keeps
Token ID7622
Feature activation+7.86e-02

Pos logit contributions
heit+0.916
agher+0.904
 Strat+0.883
inav+0.874
llah+0.866
Neg logit contributions
\--0.830
 CoC-0.823
hran-0.819
Mem-0.791
 sandy-0.786
Token working
Token ID1762
Feature activation-4.06e-01

Pos logit contributions
heit+0.647
agher+0.637
 Strat+0.621
inav+0.616
llah+0.610
Neg logit contributions
\--0.606
 CoC-0.600
hran-0.597
Mem-0.577
 sandy-0.574
Token.)
Token ID2014
Feature activation+1.99e-01

Pos logit contributions
\-+2.611
 CoC+2.591
hran+2.550
Mem+2.502
 sandy+2.469
Neg logit contributions
heit-3.771
agher-3.717
inav-3.648
 Strat-3.629
ega-3.566
Token There
Token ID1318
Feature activation+6.18e-02

Pos logit contributions
heit+1.725
agher+1.710
 Strat+1.710
inav+1.659
ega+1.642
Neg logit contributions
\--1.418
hran-1.413
 CoC-1.392
 sandy-1.348
Mem-1.344
Token was
Token ID373
Feature activation+7.45e-02

Pos logit contributions
heit+0.505
agher+0.499
 Strat+0.487
inav+0.481
llah+0.477
Neg logit contributions
\--0.477
 CoC-0.474
hran-0.471
Mem-0.455
 sandy-0.453
Token some
Token ID617
Feature activation+2.41e-01

Pos logit contributions
heit+0.645
agher+0.637
 Strat+0.623
inav+0.616
llah+0.611
Neg logit contributions
\--0.541
 CoC-0.536
hran-0.534
Mem-0.514
 sandy-0.511
Token #
Token ID1303
Feature activation+2.77e-01

Pos logit contributions
heit+1.882
agher+1.870
 Strat+1.849
inav+1.809
ega+1.786
Neg logit contributions
\--1.934
hran-1.911
 CoC-1.894
Mem-1.842
 sandy-1.805
Token blogger
Token ID23530
Feature activation+2.08e-01

Pos logit contributions
heit+2.578
agher+2.561
 Strat+2.526
inav+2.459
llah+2.456
Neg logit contributions
\--2.577
hran-2.537
 CoC-2.520
Mem-2.443
 sandy-2.418
Token,
Token ID11
Feature activation+4.22e-01

Pos logit contributions
heit+1.664
agher+1.648
 Strat+1.622
inav+1.584
llah+1.574
Neg logit contributions
\--1.631
 CoC-1.614
hran-1.610
Mem-1.554
 sandy-1.550
Token who
Token ID508
Feature activation-6.50e-02

Pos logit contributions
agher+3.320
heit+3.319
 Strat+3.304
inav+3.154
ega+3.153
Neg logit contributions
\--3.296
hran-3.270
 CoC-3.239
Mem-3.121
 sandy-3.115
Token made
Token ID925
Feature activation-5.59e-02

Pos logit contributions
\-+0.502
 CoC+0.495
hran+0.493
Mem+0.476
 sandy+0.472
Neg logit contributions
heit-0.536
agher-0.529
 Strat-0.514
inav-0.512
llah-0.505
Token a
Token ID257
Feature activation-3.07e-02

Pos logit contributions
\-+0.414
 CoC+0.412
hran+0.409
Mem+0.395
 sandy+0.393
Neg logit contributions
heit-0.476
agher-0.471
 Strat-0.455
inav-0.455
llah-0.450
Token video
Token ID2008
Feature activation-3.31e-01

Pos logit contributions
\-+0.235
 CoC+0.233
hran+0.232
Mem+0.224
 sandy+0.223
Neg logit contributions
heit-0.253
agher-0.250
 Strat-0.243
inav-0.241
llah-0.239
Token of
Token ID286
Feature activation-1.59e-01

Pos logit contributions
\-+2.441
 CoC+2.417
hran+2.412
Mem+2.349
 sandy+2.302
Neg logit contributions
heit-2.830
agher-2.766
inav-2.695
llah-2.671
 Strat-2.649
Token himself
Token ID2241
Feature activation+9.30e-02

Pos logit contributions
\-+1.104
 CoC+1.102
hran+1.088
Mem+1.053
 sandy+1.049
Neg logit contributions
heit-1.433
agher-1.405
inav-1.375
ega-1.353
llah-1.352
Token playing
Token ID2712
Feature activation+1.86e-01

Pos logit contributions
heit+0.756
agher+0.746
 Strat+0.729
inav+0.721
llah+0.714
Neg logit contributions
\--0.723
 CoC-0.717
hran-0.714
Mem-0.690
 sandy-0.686
Token Pokemon
Token ID14878
Feature activation-1.23e-02

Pos logit contributions
heit+1.528
agher+1.502
 Strat+1.494
inav+1.451
llah+1.444
Neg logit contributions
\--1.427
hran-1.407
 CoC-1.405
Mem-1.355
 sandy-1.347
Token Go
Token ID1514
Feature activation-2.32e-01

Pos logit contributions
\-+0.079
 CoC+0.078
hran+0.077
Mem+0.074
 sandy+0.074
Neg logit contributions
heit-0.117
agher-0.116
 Strat-0.113
inav-0.113
llah-0.112
Token On
Token ID1550
Feature activation-3.94e-02

Pos logit contributions
\-+2.314
 CoC+2.288
hran+2.241
Mem+2.227
 Lex+2.170
Neg logit contributions
heit-3.009
agher-2.979
inav-2.869
llah-2.864
ega-2.842
Token 10
Token ID838
Feature activation-2.37e-01

Pos logit contributions
\-+0.322
 CoC+0.320
hran+0.316
Mem+0.309
 sandy+0.308
Neg logit contributions
heit-0.307
agher-0.301
inav-0.290
 Strat-0.289
llah-0.289
Token October
Token ID3267
Feature activation-3.14e-01

Pos logit contributions
\-+1.915
hran+1.882
 CoC+1.870
 sandy+1.820
Mem+1.809
Neg logit contributions
heit-1.856
agher-1.834
inav-1.774
 Strat-1.755
llah-1.751
Token 1941
Token ID23234
Feature activation+9.69e-02

Pos logit contributions
\-+2.024
hran+1.991
 CoC+1.985
 sandy+1.930
Mem+1.915
Neg logit contributions
agher-2.941
heit-2.940
inav-2.832
llah-2.817
ega-2.815
Token those
Token ID883
Feature activation-2.22e-01

Pos logit contributions
heit+0.665
agher+0.654
 Strat+0.639
inav+0.627
llah+0.621
Neg logit contributions
\--0.877
 CoC-0.869
hran-0.867
Mem-0.840
 sandy-0.836
Token fronts
Token ID29324
Feature activation-2.00e-01

Pos logit contributions
\-+1.680
 CoC+1.673
hran+1.658
Mem+1.620
 sandy+1.615
Neg logit contributions
heit-1.867
agher-1.827
inav-1.759
llah-1.753
ega-1.746
Token were
Token ID547
Feature activation-2.86e-01

Pos logit contributions
\-+1.496
 CoC+1.475
hran+1.473
Mem+1.421
 sandy+1.417
Neg logit contributions
heit-1.686
agher-1.676
 Strat-1.616
inav-1.603
llah-1.595
Token merged
Token ID23791
Feature activation-4.29e-03

Pos logit contributions
\-+2.183
 CoC+2.145
hran+2.140
 sandy+2.083
Mem+2.057
Neg logit contributions
heit-2.377
agher-2.352
inav-2.284
llah-2.261
 Strat-2.254
Token into
Token ID656
Feature activation-2.39e-01

Pos logit contributions
\-+0.033
 CoC+0.033
hran+0.032
Mem+0.031
 sandy+0.031
Neg logit contributions
heit-0.035
agher-0.035
 Strat-0.034
inav-0.034
llah-0.033
Token the
Token ID262
Feature activation-2.29e-02

Pos logit contributions
 CoC+1.686
\-+1.674
hran+1.655
Mem+1.622
 sandy+1.618
Neg logit contributions
heit-2.101
agher-2.081
llah-1.999
ega-1.997
 Strat-1.985
Token Western
Token ID4885
Feature activation-5.85e-01

Pos logit contributions
\-+0.180
 CoC+0.180
hran+0.178
Mem+0.173
 sandy+0.172
Neg logit contributions
heit-0.183
agher-0.181
 Strat-0.176
inav-0.174
llah-0.173
Tokenre
Token ID260
Feature activation-4.12e-01

Pos logit contributions
heit+0.544
agher+0.536
 Strat+0.522
inav+0.515
llah+0.510
Neg logit contributions
\--0.638
 CoC-0.633
hran-0.630
Mem-0.611
 sandy-0.608
Token going
Token ID1016
Feature activation-1.59e-01

Pos logit contributions
\-+3.104
hran+3.008
 CoC+3.006
 sandy+2.913
Mem+2.883
Neg logit contributions
heit-3.433
agher-3.408
inav-3.408
 Strat-3.319
ega-3.259
Token to
Token ID284
Feature activation-3.58e-01

Pos logit contributions
\-+1.096
 CoC+1.064
hran+1.056
 sandy+1.025
Mem+1.022
Neg logit contributions
heit-1.438
agher-1.421
 Strat-1.386
inav-1.384
llah-1.364
Token have
Token ID423
Feature activation-1.16e-01

Pos logit contributions
\-+2.581
 CoC+2.525
hran+2.489
Mem+2.426
 sandy+2.422
Neg logit contributions
heit-3.131
agher-3.119
inav-3.029
 Strat-2.994
ega-2.954
Token to
Token ID284
Feature activation-3.37e-01

Pos logit contributions
\-+0.815
 CoC+0.810
hran+0.806
Mem+0.776
 sandy+0.769
Neg logit contributions
heit-1.024
agher-1.011
 Strat-0.990
inav-0.978
ega-0.971
Token leave
Token ID2666
Feature activation-4.45e-01

Pos logit contributions
\-+2.268
 CoC+2.221
hran+2.181
 sandy+2.107
Mem+2.096
Neg logit contributions
heit-3.117
agher-3.085
inav-2.998
 Strat-2.981
ega-2.941
Token.
Token ID13
Feature activation-7.55e-02

Pos logit contributions
\-+3.017
 CoC+2.973
hran+2.895
Mem+2.844
 sandy+2.830
Neg logit contributions
heit-4.000
agher-3.992
inav-3.884
 Strat-3.789
llah-3.775
Token
Token ID447
Feature activation-1.14e-01

Pos logit contributions
\-+0.612
 CoC+0.607
hran+0.599
Mem+0.585
 sandy+0.577
Neg logit contributions
heit-0.593
agher-0.586
 Strat-0.567
inav-0.566
ega-0.557
Token
Token ID251
Feature activation-1.10e-01

Pos logit contributions
\-+0.720
 CoC+0.713
hran+0.709
Mem+0.679
 sandy+0.674
Neg logit contributions
heit-1.090
agher-1.077
 Strat-1.056
inav-1.045
llah-1.038
Token
Token ID198
Feature activation-2.96e-01

Pos logit contributions
\-+0.846
 CoC+0.839
hran+0.836
Mem+0.806
 sandy+0.802
Neg logit contributions
heit-0.905
agher-0.893
 Strat-0.873
inav-0.862
llah-0.855
Token
Token ID198
Feature activation-3.73e-01

Pos logit contributions
\-+2.037
 CoC+1.962
Mem+1.933
hran+1.922
 Lex+1.860
Neg logit contributions
heit-2.702
agher-2.677
inav-2.592
 guiActiveUn-2.582
llah-2.560
Token it
Token ID340
Feature activation-9.14e-02

Pos logit contributions
heit+1.070
agher+1.058
 Strat+1.034
inav+1.024
llah+1.015
Neg logit contributions
\--0.847
 CoC-0.840
hran-0.835
Mem-0.804
 sandy-0.799
Token but
Token ID475
Feature activation+5.76e-02

Pos logit contributions
\-+0.677
 CoC+0.668
hran+0.661
Mem+0.642
 sandy+0.640
Neg logit contributions
heit-0.779
agher-0.771
inav-0.749
 Strat-0.747
llah-0.738
Token I
Token ID314
Feature activation+5.41e-02

Pos logit contributions
heit+0.477
agher+0.471
 Strat+0.459
inav+0.455
llah+0.451
Neg logit contributions
\--0.440
 CoC-0.436
hran-0.433
Mem-0.419
 sandy-0.418
Token sent
Token ID1908
Feature activation-3.41e-01

Pos logit contributions
heit+0.434
agher+0.428
 Strat+0.418
inav+0.413
llah+0.409
Neg logit contributions
\--0.427
 CoC-0.423
hran-0.421
Mem-0.407
 sandy-0.405
Token it
Token ID340
Feature activation-2.38e-01

Pos logit contributions
\-+2.208
 CoC+2.205
hran+2.170
 sandy+2.102
 Lex+2.099
Neg logit contributions
heit-3.166
agher-3.118
inav-3.049
llah-3.017
ega-3.004
Token in
Token ID287
Feature activation-1.82e-01

Pos logit contributions
\-+1.600
 CoC+1.560
hran+1.534
 sandy+1.502
Mem+1.499
Neg logit contributions
heit-2.185
agher-2.171
inav-2.116
llah-2.093
 Strat-2.085
Token and
Token ID290
Feature activation-4.18e-02

Pos logit contributions
\-+1.332
 CoC+1.318
hran+1.300
 sandy+1.277
Mem+1.267
Neg logit contributions
agher-1.551
heit-1.548
inav-1.503
 Strat-1.485
llah-1.483
Token J
Token ID449
Feature activation+1.89e-01

Pos logit contributions
\-+0.306
 CoC+0.304
hran+0.301
 sandy+0.291
Mem+0.291
Neg logit contributions
heit-0.358
agher-0.355
 Strat-0.344
inav-0.342
ega-0.340
TokenBL
Token ID9148
Feature activation+6.75e-02

Pos logit contributions
heit+1.474
agher+1.455
 Strat+1.420
inav+1.402
ega+1.389
Neg logit contributions
\--1.525
 CoC-1.513
hran-1.508
Mem-1.457
 sandy-1.449
Token sent
Token ID1908
Feature activation-2.12e-01

Pos logit contributions
heit+0.568
agher+0.562
inav+0.545
 Strat+0.545
llah+0.539
Neg logit contributions
\--0.506
 CoC-0.501
hran-0.498
Mem-0.483
 sandy-0.480
Token me
Token ID502
Feature activation-6.03e-02

Pos logit contributions
\-+1.477
 CoC+1.461
hran+1.456
 sandy+1.404
Mem+1.398
Neg logit contributions
heit-1.875
agher-1.860
inav-1.801
 Strat-1.800
ega-1.788
Token9
Token ID24
Feature activation-6.54e-02

Pos logit contributions
\-+0.052
 CoC+0.052
hran+0.052
 sandy+0.049
Mem+0.049
Neg logit contributions
heit-0.073
agher-0.072
 Strat-0.071
inav-0.070
llah-0.069
Token-
Token ID12
Feature activation+3.33e-02

Pos logit contributions
\-+0.517
 CoC+0.512
hran+0.509
Mem+0.493
 sandy+0.489
Neg logit contributions
heit-0.525
agher-0.519
 Strat-0.505
inav-0.500
llah-0.496
Tokento
Token ID1462
Feature activation+2.16e-01

Pos logit contributions
heit+0.308
agher+0.304
 Strat+0.298
inav+0.295
ega+0.293
Neg logit contributions
\--0.221
 CoC-0.220
hran-0.218
 sandy-0.209
Mem-0.208
Token-
Token ID12
Feature activation-3.12e-01

Pos logit contributions
heit+1.621
agher+1.590
 Strat+1.564
inav+1.535
ega+1.527
Neg logit contributions
hran-1.791
 CoC-1.789
\--1.782
 sandy-1.724
Mem-1.723
Token5
Token ID20
Feature activation+1.11e-01

Pos logit contributions
\-+2.058
 CoC+1.963
hran+1.943
Mem+1.911
Serv+1.862
Neg logit contributions
heit-2.977
agher-2.948
 Strat-2.867
llah-2.859
inav-2.848
Token Working
Token ID14594
Feature activation-9.07e-01

Pos logit contributions
heit+0.941
agher+0.931
 Strat+0.920
inav+0.903
ega+0.890
Neg logit contributions
\--0.808
hran-0.807
 CoC-0.801
Mem-0.769
 sandy-0.768
Token Women
Token ID6926
Feature activation+2.79e-01

Pos logit contributions
\-+6.667
 CoC+6.282
Mem+6.095
 Mem+6.009
 Lex+6.002
Neg logit contributions
agher-7.463
heit-7.350
 guiActiveUn-7.222
ega-7.179
inav-7.179
Token Education
Token ID7868
Feature activation+7.38e-02

Pos logit contributions
heit+1.826
agher+1.779
 Strat+1.774
inav+1.687
ega+1.681
Neg logit contributions
 CoC-2.572
\--2.568
hran-2.564
 sandy-2.493
Mem-2.492
Token Fund
Token ID7557
Feature activation-2.03e-01

Pos logit contributions
heit+0.631
agher+0.622
 Strat+0.615
inav+0.601
ega+0.597
Neg logit contributions
\--0.540
 CoC-0.536
hran-0.534
Mem-0.515
 sandy-0.513
Token:
Token ID25
Feature activation-1.67e-02

Pos logit contributions
\-+1.638
 CoC+1.631
hran+1.610
Mem+1.567
 sandy+1.550
Neg logit contributions
heit-1.595
agher-1.576
 Strat-1.523
inav-1.513
llah-1.509
Token...
Token ID2644
Feature activation-5.46e-01

Pos logit contributions
\-+0.110
 CoC+0.109
hran+0.109
Mem+0.105
 sandy+0.104
Neg logit contributions
heit-0.155
agher-0.153
 Strat-0.150
inav-0.148
llah-0.147
Token to
Token ID284
Feature activation-1.13e-01

Pos logit contributions
\-+0.725
 CoC+0.714
hran+0.712
Mem+0.691
 sandy+0.685
Neg logit contributions
heit-0.760
agher-0.750
 Strat-0.733
inav-0.725
llah-0.720
Token create
Token ID2251
Feature activation-1.83e-01

Pos logit contributions
\-+0.843
 CoC+0.835
hran+0.830
Mem+0.802
 sandy+0.797
Neg logit contributions
heit-0.956
agher-0.944
 Strat-0.920
inav-0.912
llah-0.904
Token values
Token ID3815
Feature activation-3.95e-01

Pos logit contributions
\-+1.460
 CoC+1.442
hran+1.422
Mem+1.391
 sandy+1.376
Neg logit contributions
heit-1.457
agher-1.435
 Strat-1.391
inav-1.383
llah-1.376
Token and
Token ID290
Feature activation-1.89e-01

Pos logit contributions
\-+2.957
 CoC+2.843
hran+2.824
Mem+2.751
 sandy+2.708
Neg logit contributions
heit-3.369
agher-3.322
inav-3.214
 Strat-3.198
llah-3.193
Token give
Token ID1577
Feature activation-5.23e-01

Pos logit contributions
\-+1.436
 CoC+1.425
hran+1.418
Mem+1.375
 sandy+1.363
Neg logit contributions
heit-1.557
agher-1.538
 Strat-1.498
inav-1.496
llah-1.478
Token these
Token ID777
Feature activation-9.40e-01

Pos logit contributions
 CoC+3.713
\-+3.698
hran+3.644
Mem+3.558
 sandy+3.549
Neg logit contributions
agher-4.472
heit-4.434
inav-4.312
llah-4.295
 Strat-4.269
Token values
Token ID3815
Feature activation-7.09e-01

Pos logit contributions
\-+5.289
 CoC+5.181
hran+5.023
 Lex+5.023
Mem+4.966
Neg logit contributions
heit-9.159
agher-8.899
llah-8.692
inav-8.616
 Strat-8.592
Token names
Token ID3891
Feature activation-6.02e-01

Pos logit contributions
\-+4.670
 CoC+4.552
hran+4.516
Mem+4.367
 sandy+4.367
Neg logit contributions
agher-6.344
heit-6.342
inav-6.095
llah-6.083
 Strat-6.036
Token
Token ID447
Feature activation+2.99e-02

Pos logit contributions
\-+4.344
hran+4.171
 CoC+4.043
Mem+4.034
 Lex+3.930
Neg logit contributions
heit-5.074
agher-5.011
 Strat-4.946
ega-4.847
inav-4.829
Token
Token ID247
Feature activation-3.97e-01

Pos logit contributions
heit+0.210
agher+0.208
 Strat+0.202
inav+0.200
ega+0.197
Neg logit contributions
\--0.266
 CoC-0.263
hran-0.262
Mem-0.254
 sandy-0.252
Token was
Token ID373
Feature activation-4.02e-01

Pos logit contributions
\-+2.928
 CoC+2.824
hran+2.824
Mem+2.751
 Lex+2.698
Neg logit contributions
heit-3.343
agher-3.309
 Strat-3.214
inav-3.198
llah-3.180
Token42
Token ID3682
Feature activation+2.23e-01

Pos logit contributions
\-+1.443
 CoC+1.411
hran+1.383
Mem+1.367
 sandy+1.338
Neg logit contributions
heit-1.355
agher-1.336
inav-1.290
llah-1.282
 Strat-1.273
Token 3
Token ID513
Feature activation-9.28e-02

Pos logit contributions
heit+1.661
agher+1.637
 Strat+1.615
inav+1.572
ega+1.565
Neg logit contributions
\--1.868
hran-1.861
 CoC-1.854
Mem-1.792
 sandy-1.784
Token355
Token ID28567
Feature activation+1.65e-01

Pos logit contributions
\-+0.726
 CoC+0.715
hran+0.707
Mem+0.690
 sandy+0.678
Neg logit contributions
heit-0.758
agher-0.745
 Strat-0.728
inav-0.722
llah-0.717
Token;
Token ID26
Feature activation-3.96e-01

Pos logit contributions
heit+1.338
agher+1.319
 Strat+1.296
inav+1.271
ega+1.265
Neg logit contributions
\--1.282
 CoC-1.272
hran-1.270
Mem-1.222
 sandy-1.212
Token mart
Token ID11277
Feature activation-2.91e-01

Pos logit contributions
hran+3.213
 sandy+3.204
\-+3.184
 CoC+3.149
Mem+3.083
Neg logit contributions
heit-2.996
agher-2.952
 Strat-2.886
llah-2.865
ega-2.827
Tokenin
Token ID259
Feature activation-1.18e+00

Pos logit contributions
hran+2.270
\-+2.239
 CoC+2.176
Mem+2.144
 sandy+2.134
Neg logit contributions
heit-2.314
 Strat-2.268
agher-2.246
llah-2.199
inav-2.161
Tokenrand
Token ID25192
Feature activation-9.68e-02

Pos logit contributions
\-+8.942
hran+8.862
lems+8.677
 sandy+8.530
cour+8.397
Neg logit contributions
 Strat-8.543
heit-8.098
agher-7.906
 guiActiveUn-7.894
ega-7.881
Tokenall
Token ID439
Feature activation-3.29e-01

Pos logit contributions
\-+0.707
hran+0.697
 CoC+0.694
Mem+0.669
 sandy+0.666
Neg logit contributions
heit-0.834
agher-0.818
 Strat-0.811
inav-0.795
llah-0.792
Token.
Token ID13
Feature activation-8.78e-02

Pos logit contributions
\-+2.541
hran+2.491
 CoC+2.451
 sandy+2.397
Mem+2.391
Neg logit contributions
heit-2.637
 Strat-2.608
agher-2.557
llah-2.523
ega-2.480
Tokencom
Token ID785
Feature activation-3.54e-01

Pos logit contributions
\-+0.636
hran+0.626
 CoC+0.626
Mem+0.602
 sandy+0.597
Neg logit contributions
heit-0.762
agher-0.749
 Strat-0.738
inav-0.727
llah-0.723
Token),
Token ID828
Feature activation-6.26e-02

Pos logit contributions
\-+2.408
 CoC+2.386
hran+2.365
Mem+2.274
 sandy+2.267
Neg logit contributions
heit-3.191
agher-3.143
 Strat-3.069
inav-3.063
llah-3.037
Token becoming
Token ID5033
Feature activation+2.48e-01

Pos logit contributions
\-+0.149
 CoC+0.147
hran+0.147
Mem+0.142
 sandy+0.142
Neg logit contributions
heit-0.177
agher-0.172
inav-0.169
 Strat-0.168
llah-0.168
Token the
Token ID262
Feature activation-8.12e-02

Pos logit contributions
heit+2.119
agher+2.099
 Strat+2.056
inav+2.021
ega+2.009
Neg logit contributions
\--1.825
 CoC-1.813
hran-1.802
Mem-1.733
 sandy-1.723
Token 24
Token ID1987
Feature activation-2.32e-02

Pos logit contributions
\-+0.644
 CoC+0.642
hran+0.634
Mem+0.620
 sandy+0.619
Neg logit contributions
heit-0.651
agher-0.635
inav-0.614
 Strat-0.610
llah-0.609
Tokenth
Token ID400
Feature activation-3.36e-01

Pos logit contributions
\-+0.211
 CoC+0.209
hran+0.207
Mem+0.202
 sandy+0.201
Neg logit contributions
heit-0.159
agher-0.156
 Strat-0.152
inav-0.151
llah-0.149
Token player
Token ID2137
Feature activation-5.24e-01

Pos logit contributions
 CoC+2.530
\-+2.495
hran+2.415
 sandy+2.405
Mem+2.392
Neg logit contributions
heit-2.829
agher-2.699
inav-2.676
llah-2.675
ega-2.645
Token to
Token ID284
Feature activation-9.41e-01

Pos logit contributions
\-+3.362
 CoC+3.338
hran+3.308
Mem+3.246
 sandy+3.217
Neg logit contributions
heit-4.796
llah-4.673
inav-4.671
agher-4.615
 Strat-4.524
Token do
Token ID466
Feature activation+3.07e-02

Pos logit contributions
 CoC+6.303
 batter+6.141
\-+6.140
hran+6.091
 sandy+6.052
Neg logit contributions
heit-7.969
llah-7.581
inav-7.547
agher-7.505
 guiActiveUn-7.393
Token so
Token ID523
Feature activation-5.73e-01

Pos logit contributions
heit+0.247
agher+0.243
 Strat+0.237
inav+0.235
llah+0.233
Neg logit contributions
\--0.243
 CoC-0.241
hran-0.240
Mem-0.232
 sandy-0.231
Token.
Token ID13
Feature activation-4.14e-02

Pos logit contributions
\-+3.824
 CoC+3.795
hran+3.743
Mem+3.658
 Lex+3.576
Neg logit contributions
heit-5.082
agher-4.910
llah-4.863
inav-4.823
 Strat-4.785
Token We
Token ID775
Feature activation-1.36e-02

Pos logit contributions
\-+0.306
 CoC+0.303
hran+0.300
Mem+0.292
 sandy+0.287
Neg logit contributions
heit-0.354
agher-0.348
 Strat-0.339
inav-0.338
llah-0.335
Token provide
Token ID2148
Feature activation+1.82e-01

Pos logit contributions
\-+0.105
hran+0.104
 CoC+0.103
Mem+0.100
 sandy+0.099
Neg logit contributions
heit-0.112
agher-0.111
 Strat-0.108
inav-0.106
llah-0.106
Token hardware
Token ID6890
Feature activation+2.53e-02

Pos logit contributions
 CoC+0.501
\-+0.500
hran+0.493
 sandy+0.479
Mem+0.478
Neg logit contributions
heit-0.574
agher-0.572
 Strat-0.549
inav-0.549
llah-0.545
Token virtual
Token ID7166
Feature activation+2.20e-01

Pos logit contributions
heit+0.141
agher+0.139
 Strat+0.133
inav+0.132
llah+0.130
Neg logit contributions
\--0.262
 CoC-0.262
hran-0.260
Mem-0.254
 sandy-0.253
Tokenization
Token ID1634
Feature activation+1.20e-01

Pos logit contributions
heit+1.458
agher+1.421
 Strat+1.399
inav+1.375
ega+1.369
Neg logit contributions
\--2.041
 CoC-2.026
hran-2.022
Mem-1.945
 sandy-1.939
Token for
Token ID329
Feature activation-2.48e-01

Pos logit contributions
heit+0.968
agher+0.954
 Strat+0.940
inav+0.921
ega+0.917
Neg logit contributions
\--0.937
hran-0.925
 CoC-0.925
Mem-0.890
 sandy-0.882
Token CPUs
Token ID32340
Feature activation-1.94e-01

Pos logit contributions
 CoC+1.638
\-+1.628
hran+1.607
Mem+1.568
 sandy+1.565
Neg logit contributions
heit-2.300
agher-2.296
inav-2.201
 Strat-2.198
llah-2.182
Token and
Token ID290
Feature activation-8.81e-01

Pos logit contributions
\-+1.440
 CoC+1.428
hran+1.418
Mem+1.374
 sandy+1.365
Neg logit contributions
heit-1.644
agher-1.626
 Strat-1.579
inav-1.572
llah-1.556
Token memory
Token ID4088
Feature activation-8.95e-02

Pos logit contributions
Mem+4.234
 CoC+4.234
\-+4.164
 sandy+4.103
hran+4.056
Neg logit contributions
agher-9.365
heit-9.292
inav-9.046
llah-8.851
 Strat-8.834
Token (
Token ID357
Feature activation-5.25e-01

Pos logit contributions
\-+0.701
 CoC+0.698
hran+0.693
Mem+0.673
 sandy+0.669
Neg logit contributions
heit-0.723
agher-0.714
 Strat-0.694
inav-0.688
llah-0.683
TokenVT
Token ID36392
Feature activation-1.91e-01

Pos logit contributions
\-+2.197
Mem+2.175
hran+2.164
 CoC+2.149
Pir+1.997
Neg logit contributions
heit-6.007
agher-5.961
 Strat-5.818
inav-5.767
llah-5.757
Token-
Token ID12
Feature activation-3.04e-01

Pos logit contributions
\-+1.484
 CoC+1.468
hran+1.459
Mem+1.424
 sandy+1.410
Neg logit contributions
heit-1.562
agher-1.543
llah-1.485
 Strat-1.482
inav-1.474
Tokenx
Token ID87
Feature activation+8.73e-02

Pos logit contributions
\-+1.593
 CoC+1.542
hran+1.525
Mem+1.513
Serv+1.444
Neg logit contributions
heit-3.245
agher-3.211
 Strat-3.131
llah-3.125
inav-3.124