TOP ACTIVATIONS
MAX = 9.268

. windows . forms ') | out - null # Draw
ing . im aging ') | out - null [ system
etheus Books , 2000 ), my biography of the great libertarian
type ) @ 144 Hz ( OD = Normal ) The
x . 79 10 65 110 x . x . x
3 s )} K d 6 { ( 47 s )}
Atomic < T > { pub fn load < ' a
") is an autos omal dominant ker at oder ma of
N . Roth bard ( Prom etheus Books , 2000 ),
x . 162 1 128 019 x . x . x
( 6 s )} Ng 6 { ( 7 s )}
x . 139 10 64 659 x . x . x
90 s )} N xc 7 { ( 5 s )}
x . 143 10 33 455 x . x . x
we follow the SH RM ( Str ategic Human Resource Management
pop / ret 's frame | [ address of system ]
feed by going here . But please note that my tweets
] :: All Sc reens | Where Primary | Select -
noted . <|endoftext|> T EL AV IV A clandestine Israeli
ona , Hawai i a me Hal ep ā

MIN ACTIVATIONS
MIN = -9.539

[ +( \ S + )\ s + " \ S
> {{ phone . sn ipp et }} p >
ap = arg parse . Arg ument Parser () ap .
d 3 . Count below one thousand is low ( 7
updates ? No more bad news pl s . Good updates
Element ( cv 2 . M OR PH _ RECT ,
a gimm icky , w ann abe hi - fi pret
: set dir = c \ :\ tmp : */ This
($ s z 1 . Height ), $ SR . Width
[ + \ S + \ s + "( \ S
Tiff in , Iowa . Hide Caption 5 of 15 Photos
at Sen . Jeff Flake ( R - Ari z .)
., Ross , S . W ., Is ava , D
set dir = c \ :\ tmp : */ This sets
. S ., Bates , J . E . ( 1997
P ., Pick ett , W ., H arel - F
gb ($ FC 1 [ 0 ], $ FC 1 [
le $ art ext . Count ; $ i ++) {
x . x . x . 167 101 320 6 x
= ($ text - split "\ r ") $

INTERVAL 4.566 - 9.268
CONTAINS 0.410%

", { 9 , 15 } -> " S ", {
kind of an out of body experience . <|endoftext|>
help center where Americans can lodge complaints against banks and financial
", { 10 , 15 } -> " S " |
( 418 s )} R xc 3 { ( 64 s

INTERVAL -0.135 - 4.566
CONTAINS 53.989%

that the volatility is a result of supply - and -
members of smaller ethnic groups like the Kal en jin and
progressing in terms of increasing performance ). In the end ,
Travels destinations , and explore the world with kindred spirits .
s obviously not impossible that this could happen again

INTERVAL -4.837 - -0.135
CONTAINS 45.398%

a way as may tend to the instruction of beginners .
After the initial euph oria wears off a bit ,
arp factor " number that is greater than 0 , and
items amid the j umble of images appearing on their screens
that in September 2014 the lake s surface area

INTERVAL -9.539 - -4.837
CONTAINS 0.202%

of the occupational deriv ational suffix - cin , but not
09 - 20 01 : 44 : 24 # 19 edit
th anniversary of Sultan Hassan al - B olk iah 's
Mor aga , California . Hide Caption 13 of 15 Photos
files ] WHERE path LIKE ' % project . cl j
Token.
Token ID13
Feature activation-1.11e+00

Pos logit contributions
ongyang+1.525
 sett+1.505
emis+1.502
 emanc+1.499
+1.494
Neg logit contributions
arnaev-1.632
 Grassley-1.516
 Explos-1.482
 Straw-1.472
Station-1.464
Tokenwindows
Token ID28457
Feature activation-1.16e+00

Pos logit contributions
arnaev+0.864
 Grassley+0.807
Station+0.790
 Explos+0.788
 Straw+0.786
Neg logit contributions
ongyang-0.806
 emanc-0.798
 sett-0.793
emis-0.791
-0.782
Token.
Token ID13
Feature activation-2.77e+00

Pos logit contributions
arnaev+0.862
 Grassley+0.802
Station+0.785
 Explos+0.782
 Straw+0.780
Neg logit contributions
ongyang-0.878
 emanc-0.868
 sett-0.864
emis-0.861
-0.852
Tokenforms
Token ID23914
Feature activation+1.91e-01

Pos logit contributions
arnaev+2.171
 Grassley+2.017
Station+2.005
 Explos+1.980
 Straw+1.974
Neg logit contributions
ongyang-1.968
 emanc-1.950
 sett-1.940
emis-1.919
-1.894
Token')
Token ID11537
Feature activation+1.90e+00

Pos logit contributions
ongyang+0.143
 emanc+0.142
 sett+0.141
emis+0.141
+0.139
Neg logit contributions
arnaev-0.143
 Grassley-0.134
 Explos-0.130
Station-0.130
 Straw-0.130
Token |
Token ID930
Feature activation+9.27e+00

Pos logit contributions
 emanc+1.105
ongyang+1.096
 sett+1.095
emis+1.086
+1.070
Neg logit contributions
arnaev-1.735
 Grassley-1.628
 Explos-1.590
 Straw-1.589
Station-1.587
Token out
Token ID503
Feature activation+3.48e-01

Pos logit contributions
 emanc+3.660
 sett+3.577
 sty+3.434
emis+3.424
+3.418
Neg logit contributions
arnaev-9.906
 Grassley-9.279
 Explos-9.042
Station-9.029
 Straw-8.966
Token-
Token ID12
Feature activation+3.10e+00

Pos logit contributions
ongyang+0.235
 emanc+0.233
 sett+0.232
emis+0.231
+0.230
Neg logit contributions
arnaev-0.286
 Grassley-0.267
 Explos-0.261
Station-0.261
 Straw-0.260
Tokennull
Token ID8423
Feature activation+2.55e+00

Pos logit contributions
ongyang+2.583
emis+2.564
 emanc+2.549
 sett+2.548
+2.546
Neg logit contributions
arnaev-2.032
 Grassley-1.869
 Explos-1.837
 Straw-1.823
Station-1.789
Token #
Token ID1303
Feature activation-3.56e-01

Pos logit contributions
 emanc+1.599
 sett+1.595
ongyang+1.580
emis+1.570
+1.564
Neg logit contributions
arnaev-2.201
 Grassley-2.055
Station-2.009
 Explos-2.001
 Straw-1.996
Token Draw
Token ID15315
Feature activation-1.04e-01

Pos logit contributions
arnaev+0.275
 Grassley+0.256
Station+0.250
 Explos+0.250
 Straw+0.249
Neg logit contributions
ongyang-0.259
 emanc-0.257
 sett-0.256
emis-0.255
-0.252
Tokening
Token ID278
Feature activation-4.72e-01

Pos logit contributions
arnaev+2.506
 Grassley+2.349
Station+2.342
 Straw+2.297
 Explos+2.293
Neg logit contributions
ongyang-2.153
 emanc-2.150
 sett-2.133
emis-2.117
-2.090
Token.
Token ID13
Feature activation-1.49e+00

Pos logit contributions
arnaev+0.356
 Grassley+0.332
 Explos+0.324
Station+0.323
 Straw+0.322
Neg logit contributions
ongyang-0.352
 emanc-0.348
 sett-0.346
emis-0.346
-0.341
Tokenim
Token ID320
Feature activation-7.83e-01

Pos logit contributions
arnaev+1.145
 Grassley+1.068
Station+1.051
 Explos+1.044
 Straw+1.042
Neg logit contributions
ongyang-1.083
 emanc-1.073
 sett-1.067
emis-1.061
-1.049
Tokenaging
Token ID3039
Feature activation+7.72e-01

Pos logit contributions
arnaev+0.644
 Grassley+0.604
Station+0.594
 Explos+0.591
 Straw+0.589
Neg logit contributions
ongyang-0.528
 emanc-0.522
 sett-0.519
emis-0.517
-0.511
Token')
Token ID11537
Feature activation+2.42e+00

Pos logit contributions
ongyang+0.571
 emanc+0.562
emis+0.562
 sett+0.560
+0.553
Neg logit contributions
arnaev-0.588
 Grassley-0.548
 Explos-0.535
 Straw-0.531
Station-0.527
Token |
Token ID930
Feature activation+9.22e+00

Pos logit contributions
 emanc+1.664
 sett+1.648
ongyang+1.642
emis+1.627
+1.613
Neg logit contributions
arnaev-1.970
 Grassley-1.831
 Explos-1.772
 Straw-1.767
Station-1.762
Token out
Token ID503
Feature activation-1.40e+00

Pos logit contributions
 emanc+6.008
 sett+5.892
 immersion+5.825
emis+5.817
+5.798
Neg logit contributions
arnaev-7.539
 Grassley-6.888
 Explos-6.566
Station-6.516
 AZ-6.497
Token-
Token ID12
Feature activation+2.01e+00

Pos logit contributions
arnaev+1.156
 Grassley+1.082
Station+1.057
 Explos+1.057
 Straw+1.054
Neg logit contributions
ongyang-0.941
 emanc-0.933
 sett-0.927
emis-0.923
-0.912
Tokennull
Token ID8423
Feature activation-9.06e-01

Pos logit contributions
 emanc+1.471
 sett+1.468
emis+1.456
ongyang+1.448
+1.443
Neg logit contributions
arnaev-1.547
 Grassley-1.429
 Straw-1.381
 Explos-1.379
Station-1.359
Token [
Token ID685
Feature activation+3.77e+00

Pos logit contributions
arnaev+0.731
 Grassley+0.684
Station+0.670
 Explos+0.668
 Straw+0.666
Neg logit contributions
ongyang-0.627
 emanc-0.621
 sett-0.617
emis-0.615
-0.608
Tokensystem
Token ID10057
Feature activation+3.44e+00

Pos logit contributions
+2.801
emis+2.798
 emanc+2.791
 sett+2.791
ongyang+2.791
Neg logit contributions
arnaev-2.784
 Grassley-2.581
 Explos-2.523
 Straw-2.463
 AZ-2.441
Tokenetheus
Token ID36916
Feature activation+5.77e+00

Pos logit contributions
emis+3.682
ongyang+3.587
 sett+3.546
 emanc+3.526
ixel+3.405
Neg logit contributions
arnaev-8.770
 Grassley-8.204
 Straw-8.174
 Explos-8.115
Station-8.030
Token Books
Token ID13661
Feature activation+7.15e+00

Pos logit contributions
 sett+4.260
emis+4.229
 immersion+4.137
 emanc+4.130
ongyang+4.102
Neg logit contributions
arnaev-4.454
 Grassley-4.035
 Straw-3.957
Station-3.898
 Explos-3.821
Token,
Token ID11
Feature activation+7.12e+00

Pos logit contributions
 sett+4.015
+4.000
 emanc+3.967
ongyang+3.948
emis+3.904
Neg logit contributions
arnaev-6.595
 Grassley-5.991
 Straw-5.945
Station-5.937
 Explos-5.911
Token 2000
Token ID4751
Feature activation+3.85e+00

Pos logit contributions
+5.716
 sett+5.701
 emanc+5.624
emis+5.592
ongyang+5.515
Neg logit contributions
arnaev-4.811
 Grassley-4.300
Station-4.295
ufact-4.233
 Explos-4.214
Token),
Token ID828
Feature activation+5.04e+00

Pos logit contributions
ongyang+2.407
 sett+2.397
+2.346
 emanc+2.341
emis+2.297
Neg logit contributions
arnaev-3.391
 Grassley-3.140
Station-3.124
 Explos-3.094
 Straw-3.075
Token my
Token ID616
Feature activation+8.76e+00

Pos logit contributions
ongyang+3.690
 emanc+3.677
 sett+3.661
emis+3.639
+3.605
Neg logit contributions
arnaev-3.848
 Grassley-3.535
Station-3.506
 Straw-3.427
 Explos-3.415
Token biography
Token ID26444
Feature activation+6.61e+00

Pos logit contributions
 sett+4.323
ongyang+4.192
emis+4.188
+4.067
 emanc+4.045
Neg logit contributions
arnaev-8.534
Station-7.912
 Explos-7.835
 IPM-7.796
ilial-7.746
Token of
Token ID286
Feature activation+6.51e+00

Pos logit contributions
 sett+3.798
 emanc+3.746
emis+3.684
 immersion+3.678
 torped+3.626
Neg logit contributions
arnaev-5.819
Station-5.557
 Grassley-5.505
 Straw-5.361
ufact-5.352
Token the
Token ID262
Feature activation+7.39e+00

Pos logit contributions
 emanc+3.954
 sett+3.945
ongyang+3.877
+3.812
 immersion+3.756
Neg logit contributions
arnaev-5.831
Station-5.348
 Grassley-5.304
 Explos-5.239
 Straw-5.166
Token great
Token ID1049
Feature activation+5.72e+00

Pos logit contributions
 sett+3.114
 emanc+3.083
+2.760
ongyang+2.632
 bargain+2.614
Neg logit contributions
arnaev-8.042
 Grassley-7.729
 Explos-7.606
Station-7.605
 IPM-7.479
Token libertarian
Token ID19466
Feature activation+3.63e+00

Pos logit contributions
 emanc+3.869
 sett+3.825
ongyang+3.684
 immersion+3.643
emis+3.642
Neg logit contributions
arnaev-4.843
Station-4.419
 Grassley-4.408
 Explos-4.343
 Straw-4.304
Tokentype
Token ID4906
Feature activation+1.32e+00

Pos logit contributions
ongyang+2.656
emis+2.642
 sett+2.634
 emanc+2.609
+2.559
Neg logit contributions
arnaev-5.062
 Grassley-4.777
 Explos-4.740
 Straw-4.696
Station-4.601
Token)
Token ID8
Feature activation+6.85e-01

Pos logit contributions
ongyang+0.836
 sett+0.828
 emanc+0.826
emis+0.821
+0.815
Neg logit contributions
arnaev-1.135
 Grassley-1.056
 Explos-1.035
Station-1.033
 Straw-1.030
Token @
Token ID2488
Feature activation+6.24e+00

Pos logit contributions
ongyang+0.528
 emanc+0.522
 sett+0.520
emis+0.518
+0.513
Neg logit contributions
arnaev-0.499
 Grassley-0.464
Station-0.454
 Explos-0.452
 Straw-0.451
Token 144
Token ID20224
Feature activation+1.44e-01

Pos logit contributions
 sett+3.435
 emanc+3.427
ongyang+3.405
 immersion+3.400
emis+3.387
Neg logit contributions
arnaev-5.804
 Grassley-5.360
Station-5.280
 Explos-5.195
 Straw-5.181
TokenHz
Token ID7399
Feature activation+3.31e+00

Pos logit contributions
ongyang+0.106
 emanc+0.105
 sett+0.105
emis+0.104
+0.102
Neg logit contributions
arnaev-0.109
 Grassley-0.102
Station-0.101
 Explos-0.100
 Straw-0.099
Token (
Token ID357
Feature activation+8.68e+00

Pos logit contributions
ongyang+2.018
 sett+2.009
 emanc+1.995
+1.965
emis+1.964
Neg logit contributions
arnaev-2.944
 Grassley-2.715
Station-2.684
 Straw-2.650
 Explos-2.648
TokenOD
Token ID3727
Feature activation+8.67e-02

Pos logit contributions
+2.070
emis+1.789
ongyang+1.772
 sett+1.727
 emanc+1.637
Neg logit contributions
arnaev-10.906
 Grassley-10.145
ufact-10.132
 Explos-10.065
 Straw-10.028
Token =
Token ID796
Feature activation+4.04e+00

Pos logit contributions
ongyang+0.066
 emanc+0.065
 sett+0.065
emis+0.064
+0.064
Neg logit contributions
arnaev-0.064
 Grassley-0.060
Station-0.059
 Explos-0.058
 Straw-0.058
Token Normal
Token ID14435
Feature activation-4.50e-01

Pos logit contributions
 emanc+2.645
ongyang+2.637
 sett+2.632
emis+2.608
 immersion+2.585
Neg logit contributions
arnaev-3.400
 Grassley-3.141
Station-3.083
 Explos-3.054
 Straw-3.052
Token)
Token ID8
Feature activation+2.47e+00

Pos logit contributions
arnaev+0.368
 Grassley+0.345
Station+0.339
 Explos+0.338
 Straw+0.337
Neg logit contributions
ongyang-0.307
 emanc-0.303
 sett-0.301
emis-0.301
-0.296
Token The
Token ID383
Feature activation+7.75e-01

Pos logit contributions
ongyang+1.640
 emanc+1.613
 sett+1.607
emis+1.604
+1.589
Neg logit contributions
arnaev-2.060
 Grassley-1.919
Station-1.884
 Explos-1.871
 Straw-1.871
Tokenx
Token ID87
Feature activation+3.36e+00

Pos logit contributions
ongyang+1.022
 emanc+1.012
 sett+1.008
emis+1.005
+0.995
Neg logit contributions
arnaev-0.789
 Grassley-0.727
Station-0.709
 Explos-0.706
 Straw-0.704
Token.
Token ID13
Feature activation+3.06e+00

Pos logit contributions
 sett+2.336
ongyang+2.325
emis+2.319
+2.316
 emanc+2.305
Neg logit contributions
arnaev-2.690
 Grassley-2.442
 Explos-2.412
 Straw-2.385
Station-2.375
Token79
Token ID3720
Feature activation-7.60e-01

Pos logit contributions
ongyang+1.512
emis+1.494
 sett+1.492
 emanc+1.482
+1.445
Neg logit contributions
arnaev-3.070
 Grassley-2.906
 Explos-2.851
 Straw-2.826
Station-2.819
Token 10
Token ID838
Feature activation-1.10e+00

Pos logit contributions
arnaev+0.618
 Grassley+0.574
Station+0.564
 Explos+0.561
 Straw+0.559
Neg logit contributions
ongyang-0.520
 emanc-0.517
 sett-0.515
emis-0.511
-0.507
Token65
Token ID2996
Feature activation+1.17e+00

Pos logit contributions
arnaev+0.838
 Grassley+0.777
Station+0.760
 Explos+0.758
 Straw+0.756
Neg logit contributions
ongyang-0.815
 emanc-0.810
 sett-0.809
emis-0.804
-0.797
Token110
Token ID11442
Feature activation+8.64e+00

Pos logit contributions
 sett+0.841
 emanc+0.837
ongyang+0.836
emis+0.832
+0.830
Neg logit contributions
arnaev-0.908
 Grassley-0.837
Station-0.819
 Explos-0.816
 Straw-0.815
Token x
Token ID2124
Feature activation+3.10e+00

Pos logit contributions
 sett+5.311
 emanc+5.217
ixel+5.131
 ker+5.119
 fid+5.103
Neg logit contributions
arnaev-7.324
Station-6.573
 Grassley-6.544
 Explos-6.441
 Straw-6.391
Token.
Token ID13
Feature activation-6.26e-01

Pos logit contributions
ongyang+2.169
 sett+2.166
+2.163
 emanc+2.146
emis+2.143
Neg logit contributions
arnaev-2.451
 Grassley-2.247
 Explos-2.211
Station-2.193
 Straw-2.190
Tokenx
Token ID87
Feature activation-4.79e-01

Pos logit contributions
arnaev+0.415
 Grassley+0.383
Station+0.373
 Explos+0.372
 Straw+0.370
Neg logit contributions
ongyang-0.524
 emanc-0.518
 sett-0.516
emis-0.515
-0.510
Token.
Token ID13
Feature activation+1.48e+00

Pos logit contributions
arnaev+0.350
 Grassley+0.327
Station+0.320
 Explos+0.318
 Straw+0.317
Neg logit contributions
ongyang-0.369
 emanc-0.365
 sett-0.362
emis-0.361
-0.356
Tokenx
Token ID87
Feature activation+3.21e+00

Pos logit contributions
ongyang+1.212
 emanc+1.196
 sett+1.194
emis+1.192
+1.178
Neg logit contributions
arnaev-1.009
 Grassley-0.929
Station-0.905
 Explos-0.903
 Straw-0.897
Token3
Token ID18
Feature activation-7.94e-01

Pos logit contributions
arnaev+1.281
 Grassley+1.199
Station+1.177
 Explos+1.171
 Straw+1.167
Neg logit contributions
ongyang-1.183
 emanc-1.169
 sett-1.161
emis-1.158
-1.141
Tokens
Token ID82
Feature activation-7.34e-01

Pos logit contributions
arnaev+0.574
 Grassley+0.533
Station+0.521
 Explos+0.520
 Straw+0.518
Neg logit contributions
ongyang-0.616
 emanc-0.610
 sett-0.607
emis-0.605
-0.599
Token)}
Token ID38165
Feature activation+7.83e-01

Pos logit contributions
arnaev+0.425
 Grassley+0.391
Station+0.379
 Straw+0.377
 Explos+0.376
Neg logit contributions
ongyang-0.673
 emanc-0.669
 sett-0.664
emis-0.663
-0.656
Token K
Token ID509
Feature activation-5.92e-02

Pos logit contributions
ongyang+0.597
 emanc+0.596
 sett+0.593
emis+0.588
+0.583
Neg logit contributions
arnaev-0.578
 Grassley-0.531
Station-0.523
 Straw-0.517
 Explos-0.515
Tokend
Token ID67
Feature activation+3.50e+00

Pos logit contributions
arnaev+0.050
 Grassley+0.047
Station+0.046
 Explos+0.045
 Straw+0.045
Neg logit contributions
ongyang-0.039
 emanc-0.039
 sett-0.039
emis-0.038
-0.038
Token6
Token ID21
Feature activation+8.49e+00

Pos logit contributions
ongyang+2.521
 emanc+2.467
emis+2.464
+2.445
 sett+2.439
Neg logit contributions
arnaev-2.753
 Grassley-2.563
 Straw-2.505
Station-2.503
 Explos-2.483
Token {
Token ID1391
Feature activation+1.20e+00

Pos logit contributions
+3.409
 emanc+3.406
 sett+3.339
ongyang+3.318
emis+3.281
Neg logit contributions
arnaev-9.088
 Grassley-8.460
Station-8.339
 Straw-8.256
 Explos-8.088
Token(
Token ID7
Feature activation+1.36e+00

Pos logit contributions
ongyang+0.831
+0.824
 sett+0.822
 emanc+0.820
emis+0.817
Neg logit contributions
arnaev-0.961
 Grassley-0.888
 Explos-0.869
 Straw-0.866
Station-0.860
Token47
Token ID2857
Feature activation-4.92e-02

Pos logit contributions
ongyang+0.968
 sett+0.959
 emanc+0.958
emis+0.953
+0.952
Neg logit contributions
arnaev-1.071
 Grassley-0.991
 Explos-0.967
Station-0.967
 Straw-0.967
Tokens
Token ID82
Feature activation-1.95e-01

Pos logit contributions
arnaev+0.035
 Grassley+0.033
Station+0.032
 Explos+0.032
 Straw+0.032
Neg logit contributions
ongyang-0.039
 emanc-0.038
 sett-0.038
emis-0.038
-0.038
Token)}
Token ID38165
Feature activation-7.21e-01

Pos logit contributions
arnaev+0.116
 Grassley+0.106
Station+0.103
 Explos+0.103
 Straw+0.103
Neg logit contributions
ongyang-0.175
 emanc-0.174
 sett-0.173
emis-0.173
-0.171
Token Atomic
Token ID28976
Feature activation-2.29e+00

Pos logit contributions
arnaev+1.500
 Grassley+1.384
 Explos+1.355
Station+1.350
 Straw+1.347
Neg logit contributions
ongyang-2.214
 emanc-2.187
emis-2.180
 sett-2.176
-2.160
Token <
Token ID1279
Feature activation+1.42e-01

Pos logit contributions
arnaev+1.928
 Grassley+1.818
Station+1.794
 Explos+1.785
 Straw+1.777
Neg logit contributions
ongyang-1.495
 emanc-1.474
 sett-1.465
emis-1.464
-1.438
Token T
Token ID309
Feature activation+1.90e+00

Pos logit contributions
ongyang+0.119
 emanc+0.119
 sett+0.119
emis+0.118
+0.116
Neg logit contributions
arnaev-0.094
 Grassley-0.086
Station-0.083
 Explos-0.082
 Straw-0.082
Token >
Token ID1875
Feature activation+2.46e+00

Pos logit contributions
 sett+1.393
ongyang+1.388
 emanc+1.385
emis+1.375
+1.349
Neg logit contributions
arnaev-1.457
 Grassley-1.344
Station-1.305
 Explos-1.300
 Straw-1.297
Token {
Token ID1391
Feature activation+2.49e+00

Pos logit contributions
 emanc+1.373
 sett+1.371
ongyang+1.367
emis+1.341
+1.334
Neg logit contributions
arnaev-2.329
 Grassley-2.158
Station-2.100
 Straw-2.089
 Explos-2.079
Token pub
Token ID2240
Feature activation+8.36e+00

Pos logit contributions
 emanc+1.620
 sett+1.617
ongyang+1.613
emis+1.577
+1.565
Neg logit contributions
arnaev-2.116
 Grassley-1.964
Station-1.926
 Straw-1.905
 Explos-1.903
Token fn
Token ID24714
Feature activation+5.70e+00

Pos logit contributions
 emanc+4.604
 sett+4.568
ongyang+4.471
 fid+4.420
emis+4.413
Neg logit contributions
arnaev-7.711
 Grassley-7.051
Station-6.894
 Straw-6.861
 Explos-6.755
Token load
Token ID3440
Feature activation-3.99e+00

Pos logit contributions
 sett+3.688
 emanc+3.654
ongyang+3.539
 fid+3.501
 torped+3.491
Neg logit contributions
arnaev-4.936
 Grassley-4.499
Station-4.428
 Explos-4.289
 Straw-4.289
Token <
Token ID1279
Feature activation-2.16e+00

Pos logit contributions
arnaev+3.180
Station+3.005
 Grassley+2.996
 Explos+2.974
 Straw+2.942
Neg logit contributions
ongyang-2.726
 emanc-2.711
emis-2.676
 sett-2.671
 immersion-2.623
Token '
Token ID705
Feature activation-4.79e+00

Pos logit contributions
arnaev+1.560
 Grassley+1.457
 Explos+1.426
Station+1.425
 Straw+1.421
Neg logit contributions
ongyang-1.668
 emanc-1.646
 sett-1.635
emis-1.634
-1.623
Tokena
Token ID64
Feature activation-4.67e-01

Pos logit contributions
arnaev+3.824
 Grassley+3.578
Station+3.515
 Explos+3.511
 Straw+3.507
Neg logit contributions
ongyang-3.331
 emanc-3.245
-3.217
emis-3.210
 sett-3.200
Token")
Token ID4943
Feature activation+7.75e-02

Pos logit contributions
ongyang+1.496
emis+1.465
 sett+1.451
 emanc+1.449
+1.443
Neg logit contributions
arnaev-3.500
 Grassley-3.275
 Explos-3.242
 Straw-3.232
Station-3.210
Token is
Token ID318
Feature activation-2.37e-02

Pos logit contributions
ongyang+0.054
 emanc+0.054
 sett+0.053
emis+0.053
+0.052
Neg logit contributions
arnaev-0.062
 Grassley-0.058
Station-0.057
 Explos-0.057
 Straw-0.057
Token an
Token ID281
Feature activation+9.34e-01

Pos logit contributions
arnaev+0.018
 Grassley+0.017
Station+0.017
 Explos+0.017
 Straw+0.016
Neg logit contributions
ongyang-0.017
 emanc-0.017
 sett-0.017
emis-0.017
-0.017
Token autos
Token ID44619
Feature activation+1.12e+00

Pos logit contributions
ongyang+0.474
 emanc+0.465
 sett+0.462
emis+0.460
+0.454
Neg logit contributions
arnaev-0.925
 Grassley-0.879
Station-0.864
 Explos-0.863
 Straw-0.861
Tokenomal
Token ID18048
Feature activation+1.59e+00

Pos logit contributions
ongyang+0.600
 emanc+0.592
 sett+0.587
emis+0.585
+0.576
Neg logit contributions
arnaev-1.073
 Grassley-1.015
Station-0.999
 Explos-0.996
 Straw-0.994
Token dominant
Token ID11410
Feature activation+8.34e+00

Pos logit contributions
 emanc+0.607
ongyang+0.606
 sett+0.601
emis+0.586
+0.572
Neg logit contributions
arnaev-1.776
 Grassley-1.685
Station-1.665
 Explos-1.661
 Straw-1.656
Token ker
Token ID41927
Feature activation+2.07e+00

Pos logit contributions
 ker+1.004
 sett+0.827
 emanc+0.771
ongyang+0.710
emis+0.611
Neg logit contributions
arnaev-11.592
Station-11.002
 Grassley-10.974
 Explos-10.944
 Straw-10.809
Tokenat
Token ID265
Feature activation+3.06e+00

Pos logit contributions
ongyang+1.272
emis+1.250
 sett+1.245
 emanc+1.242
+1.225
Neg logit contributions
arnaev-1.820
 Grassley-1.717
 Explos-1.686
 Straw-1.683
Station-1.674
Tokenoder
Token ID12342
Feature activation+2.82e+00

Pos logit contributions
ongyang+2.249
emis+2.201
 emanc+2.198
 sett+2.190
+2.172
Neg logit contributions
arnaev-2.337
 Grassley-2.185
 Explos-2.146
Station-2.145
 Straw-2.131
Tokenma
Token ID2611
Feature activation-7.52e-01

Pos logit contributions
ongyang+1.951
emis+1.943
 sett+1.920
 emanc+1.920
+1.891
Neg logit contributions
arnaev-2.272
 Grassley-2.107
 Explos-2.081
 Straw-2.067
Station-2.064
Token of
Token ID286
Feature activation+1.47e+00

Pos logit contributions
arnaev+0.576
 Grassley+0.540
Station+0.528
 Explos+0.526
 Straw+0.526
Neg logit contributions
ongyang-0.552
 emanc-0.544
emis-0.539
 sett-0.539
-0.532
Token N
Token ID399
Feature activation+7.08e-01

Pos logit contributions
ongyang+2.401
 emanc+2.399
 sett+2.384
emis+2.373
 torped+2.345
Neg logit contributions
arnaev-3.132
 Grassley-2.745
Station-2.742
 Explos-2.700
 Straw-2.665
Token.
Token ID13
Feature activation+2.50e+00

Pos logit contributions
 emanc+0.561
ongyang+0.560
 sett+0.551
 immersion+0.547
emis+0.546
Neg logit contributions
arnaev-0.495
 Grassley-0.466
 Straw-0.459
 Explos-0.452
Station-0.452
Token Roth
Token ID16131
Feature activation+2.53e+00

Pos logit contributions
ongyang+2.227
 emanc+2.218
 sett+2.215
emis+2.193
+2.158
Neg logit contributions
arnaev-1.527
 Grassley-1.337
Station-1.329
 Explos-1.309
 Straw-1.287
Tokenbard
Token ID23024
Feature activation+6.65e+00

Pos logit contributions
ongyang+1.643
 emanc+1.625
 sett+1.619
emis+1.615
+1.590
Neg logit contributions
arnaev-2.148
 Grassley-2.011
Station-1.973
 Explos-1.964
 Straw-1.959
Token (
Token ID357
Feature activation+7.91e+00

Pos logit contributions
emis+3.645
 emanc+3.565
 sett+3.561
 immersion+3.481
ongyang+3.458
Neg logit contributions
arnaev-6.505
Station-5.851
 Grassley-5.777
ufact-5.649
 Straw-5.598
TokenProm
Token ID24129
Feature activation+8.27e+00

Pos logit contributions
 sett+5.207
+5.129
emis+5.104
ongyang+5.050
 immersion+5.007
Neg logit contributions
arnaev-6.483
 Grassley-5.968
 Explos-5.783
 Straw-5.761
ufact-5.703
Tokenetheus
Token ID36916
Feature activation+5.77e+00

Pos logit contributions
emis+3.682
ongyang+3.587
 sett+3.546
 emanc+3.526
ixel+3.405
Neg logit contributions
arnaev-8.770
 Grassley-8.204
 Straw-8.174
 Explos-8.115
Station-8.030
Token Books
Token ID13661
Feature activation+7.15e+00

Pos logit contributions
 sett+4.260
emis+4.229
 immersion+4.137
 emanc+4.130
ongyang+4.102
Neg logit contributions
arnaev-4.454
 Grassley-4.035
 Straw-3.957
Station-3.898
 Explos-3.821
Token,
Token ID11
Feature activation+7.12e+00

Pos logit contributions
 sett+4.015
+4.000
 emanc+3.967
ongyang+3.948
emis+3.904
Neg logit contributions
arnaev-6.595
 Grassley-5.991
 Straw-5.945
Station-5.937
 Explos-5.911
Token 2000
Token ID4751
Feature activation+3.85e+00

Pos logit contributions
+5.716
 sett+5.701
 emanc+5.624
emis+5.592
ongyang+5.515
Neg logit contributions
arnaev-4.811
 Grassley-4.300
Station-4.295
ufact-4.233
 Explos-4.214
Token),
Token ID828
Feature activation+5.04e+00

Pos logit contributions
ongyang+2.407
 sett+2.397
+2.346
 emanc+2.341
emis+2.297
Neg logit contributions
arnaev-3.391
 Grassley-3.140
Station-3.124
 Explos-3.094
 Straw-3.075
Tokenx
Token ID87
Feature activation-1.75e+00

Pos logit contributions
arnaev+0.591
 Grassley+0.548
Station+0.540
 Explos+0.531
 Straw+0.531
Neg logit contributions
ongyang-0.854
 emanc-0.850
 sett-0.843
emis-0.834
 immersion-0.832
Token.
Token ID13
Feature activation-2.80e+00

Pos logit contributions
arnaev+1.225
 Grassley+1.145
Station+1.128
 Explos+1.110
 Straw+1.109
Neg logit contributions
ongyang-1.396
 emanc-1.383
 sett-1.368
emis-1.361
 immersion-1.344
Token162
Token ID25061
Feature activation-2.47e+00

Pos logit contributions
arnaev+2.317
 Grassley+2.176
Station+2.165
 Explos+2.145
 Straw+2.118
Neg logit contributions
ongyang-1.853
 emanc-1.821
 sett-1.813
emis-1.798
-1.778
Token 1
Token ID352
Feature activation+7.94e-01

Pos logit contributions
arnaev+2.002
 Grassley+1.903
 Explos+1.866
Station+1.862
 Straw+1.859
Neg logit contributions
ongyang-1.697
 emanc-1.672
emis-1.660
 sett-1.650
-1.622
Token128
Token ID12762
Feature activation+2.68e+00

Pos logit contributions
+0.497
 sett+0.496
ongyang+0.493
 emanc+0.493
emis+0.489
Neg logit contributions
arnaev-0.692
 Grassley-0.637
 Straw-0.621
 Explos-0.619
Station-0.619
Token019
Token ID30484
Feature activation+8.27e+00

Pos logit contributions
 sett+1.834
+1.827
emis+1.826
ongyang+1.821
 emanc+1.818
Neg logit contributions
arnaev-2.147
 Grassley-1.971
 Explos-1.925
 Straw-1.924
Station-1.911
Token x
Token ID2124
Feature activation+6.30e-01

Pos logit contributions
 sett+4.766
 emanc+4.582
emis+4.563
+4.542
 fid+4.533
Neg logit contributions
arnaev-7.580
ufact-6.781
Station-6.602
 Grassley-6.588
ilial-6.524
Token.
Token ID13
Feature activation-1.13e+00

Pos logit contributions
ongyang+0.464
 emanc+0.459
 sett+0.459
emis+0.457
+0.454
Neg logit contributions
arnaev-0.479
 Grassley-0.443
 Explos-0.434
Station-0.432
 Straw-0.431
Tokenx
Token ID87
Feature activation-1.24e+00

Pos logit contributions
arnaev+0.700
 Grassley+0.649
Station+0.638
 Straw+0.629
 Explos+0.628
Neg logit contributions
ongyang-0.984
 emanc-0.978
 sett-0.970
emis-0.961
 immersion-0.956
Token.
Token ID13
Feature activation-2.26e+00

Pos logit contributions
arnaev+0.885
 Grassley+0.831
Station+0.815
 Straw+0.806
 Explos+0.805
Neg logit contributions
ongyang-0.977
 emanc-0.966
 sett-0.956
emis-0.955
 immersion-0.941
Tokenx
Token ID87
Feature activation-3.82e+00

Pos logit contributions
arnaev+1.357
 Grassley+1.249
Station+1.239
 Straw+1.210
 Explos+1.205
Neg logit contributions
ongyang-2.008
 emanc-2.004
 sett-1.988
 immersion-1.961
emis-1.958
Token(
Token ID7
Feature activation-2.85e+00

Pos logit contributions
arnaev+0.036
 Grassley+0.034
 Explos+0.033
Station+0.033
 Straw+0.033
Neg logit contributions
ongyang-0.034
 emanc-0.034
 sett-0.033
emis-0.033
-0.033
Token6
Token ID21
Feature activation-4.38e-01

Pos logit contributions
arnaev+2.163
 Grassley+2.029
Station+1.993
 Explos+1.984
 Straw+1.975
Neg logit contributions
ongyang-2.112
 emanc-2.081
emis-2.064
 sett-2.061
 immersion-2.029
Tokens
Token ID82
Feature activation-9.49e-01

Pos logit contributions
arnaev+0.339
 Grassley+0.316
Station+0.309
 Explos+0.308
 Straw+0.307
Neg logit contributions
ongyang-0.317
 emanc-0.314
 sett-0.313
emis-0.312
-0.308
Token)}
Token ID38165
Feature activation+1.11e+00

Pos logit contributions
arnaev+0.547
 Grassley+0.502
Station+0.489
 Straw+0.484
 Explos+0.484
Neg logit contributions
ongyang-0.874
 emanc-0.869
 sett-0.862
emis-0.861
 immersion-0.850
Token Ng
Token ID34786
Feature activation+4.38e+00

Pos logit contributions
ongyang+0.857
 emanc+0.856
 sett+0.852
emis+0.842
+0.838
Neg logit contributions
arnaev-0.811
 Grassley-0.741
Station-0.731
 Straw-0.720
 Explos-0.718
Token6
Token ID21
Feature activation+8.17e+00

Pos logit contributions
ongyang+3.029
+2.968
emis+2.968
 emanc+2.953
 sett+2.950
Neg logit contributions
arnaev-3.512
 Grassley-3.292
 Straw-3.221
 Explos-3.173
Station-3.153
Token {
Token ID1391
Feature activation+1.76e+00

Pos logit contributions
+3.379
 sett+3.338
emis+3.254
 emanc+3.245
ongyang+3.218
Neg logit contributions
arnaev-8.746
ufact-7.994
 Grassley-7.986
Station-7.836
 Straw-7.789
Token(
Token ID7
Feature activation+2.52e-01

Pos logit contributions
+1.197
ongyang+1.193
 sett+1.183
 emanc+1.177
emis+1.175
Neg logit contributions
arnaev-1.442
 Grassley-1.329
 Explos-1.301
 Straw-1.297
Station-1.278
Token7
Token ID22
Feature activation+1.73e+00

Pos logit contributions
ongyang+0.181
 emanc+0.179
 sett+0.179
emis+0.178
+0.177
Neg logit contributions
arnaev-0.196
 Grassley-0.182
Station-0.178
 Explos-0.177
 Straw-0.177
Tokens
Token ID82
Feature activation+5.29e-01

Pos logit contributions
 sett+1.218
 emanc+1.215
ongyang+1.215
emis+1.207
+1.202
Neg logit contributions
arnaev-1.364
 Grassley-1.261
 Explos-1.235
Station-1.230
 Straw-1.225
Token)}
Token ID38165
Feature activation-4.74e-01

Pos logit contributions
ongyang+0.472
 emanc+0.467
 sett+0.466
emis+0.465
+0.461
Neg logit contributions
arnaev-0.321
 Grassley-0.292
Station-0.284
 Explos-0.284
 Straw-0.282
Tokenx
Token ID87
Feature activation-1.55e+00

Pos logit contributions
arnaev+0.545
 Grassley+0.506
Station+0.497
 Explos+0.489
 Straw+0.489
Neg logit contributions
ongyang-0.780
 emanc-0.777
 sett-0.770
emis-0.762
 immersion-0.759
Token.
Token ID13
Feature activation-3.92e+00

Pos logit contributions
arnaev+1.066
 Grassley+1.007
Station+0.993
 Straw+0.972
 Explos+0.970
Neg logit contributions
ongyang-1.258
 emanc-1.247
 sett-1.230
emis-1.223
 immersion-1.212
Token139
Token ID20219
Feature activation-1.77e-01

Pos logit contributions
arnaev+2.668
Station+2.582
 Grassley+2.500
 Explos+2.428
 Straw+2.419
Neg logit contributions
 emanc-3.090
ongyang-3.071
 sett-3.048
-2.983
emis-2.964
Token 10
Token ID838
Feature activation-7.51e-01

Pos logit contributions
arnaev+0.152
 Grassley+0.141
Station+0.139
 Explos+0.138
 Straw+0.138
Neg logit contributions
ongyang-0.114
 emanc-0.113
 sett-0.113
emis-0.112
-0.111
Token64
Token ID2414
Feature activation+1.56e+00

Pos logit contributions
arnaev+0.582
 Grassley+0.538
 Explos+0.525
 Straw+0.523
Station+0.523
Neg logit contributions
ongyang-0.539
 sett-0.537
 emanc-0.536
-0.535
emis-0.534
Token659
Token ID36445
Feature activation+8.14e+00

Pos logit contributions
 sett+1.089
emis+1.087
+1.086
ongyang+1.085
 emanc+1.083
Neg logit contributions
arnaev-1.232
 Grassley-1.136
 Explos-1.109
 Straw-1.107
Station-1.104
Token x
Token ID2124
Feature activation+1.33e+00

Pos logit contributions
 sett+4.760
 emanc+4.557
+4.525
 fid+4.504
emis+4.502
Neg logit contributions
arnaev-7.416
ufact-6.584
Station-6.479
 Grassley-6.463
ilial-6.402
Token.
Token ID13
Feature activation+2.22e-01

Pos logit contributions
ongyang+0.957
 sett+0.952
 emanc+0.949
emis+0.945
+0.945
Neg logit contributions
arnaev-1.035
 Grassley-0.952
 Explos-0.935
 Straw-0.929
Station-0.928
Tokenx
Token ID87
Feature activation+8.95e-01

Pos logit contributions
ongyang+0.188
 emanc+0.186
 sett+0.185
emis+0.185
+0.183
Neg logit contributions
arnaev-0.145
 Grassley-0.134
Station-0.131
 Explos-0.130
 Straw-0.130
Token.
Token ID13
Feature activation+1.41e+00

Pos logit contributions
ongyang+0.658
 emanc+0.651
 sett+0.650
emis+0.649
+0.644
Neg logit contributions
arnaev-0.682
 Grassley-0.630
 Explos-0.617
Station-0.615
 Straw-0.614
Tokenx
Token ID87
Feature activation+5.70e-01

Pos logit contributions
ongyang+1.180
 emanc+1.167
 sett+1.163
emis+1.162
+1.150
Neg logit contributions
arnaev-0.930
 Grassley-0.855
Station-0.832
 Explos-0.831
 Straw-0.828
Token90
Token ID3829
Feature activation+1.90e+00

Pos logit contributions
arnaev+1.842
 Grassley+1.727
Station+1.694
 Explos+1.686
 Straw+1.679
Neg logit contributions
ongyang-1.796
 emanc-1.772
emis-1.757
 sett-1.756
 immersion-1.726
Tokens
Token ID82
Feature activation-1.23e+00

Pos logit contributions
ongyang+1.427
 sett+1.415
 emanc+1.414
emis+1.408
+1.391
Neg logit contributions
arnaev-1.413
 Grassley-1.300
Station-1.268
 Explos-1.267
 Straw-1.264
Token)}
Token ID38165
Feature activation-5.15e-01

Pos logit contributions
arnaev+0.700
 Grassley+0.646
Station+0.630
 Straw+0.622
 Explos+0.620
Neg logit contributions
ongyang-1.135
 emanc-1.131
 sett-1.121
emis-1.118
 immersion-1.105
Token N
Token ID399
Feature activation+2.60e+00

Pos logit contributions
arnaev+0.373
 Grassley+0.346
Station+0.338
 Explos+0.337
 Straw+0.336
Neg logit contributions
ongyang-0.400
 emanc-0.396
 sett-0.394
emis-0.393
-0.389
Tokenxc
Token ID25306
Feature activation+6.45e+00

Pos logit contributions
ongyang+1.914
emis+1.882
 emanc+1.871
+1.866
 sett+1.862
Neg logit contributions
arnaev-1.992
 Grassley-1.864
 Straw-1.818
 Explos-1.810
Station-1.796
Token7
Token ID22
Feature activation+8.13e+00

Pos logit contributions
ongyang+4.309
emis+4.233
+4.228
 emanc+4.219
 sett+4.153
Neg logit contributions
arnaev-5.213
 Grassley-4.863
 Straw-4.766
 Explos-4.713
Station-4.700
Token {
Token ID1391
Feature activation+1.69e+00

Pos logit contributions
+3.475
 sett+3.437
 emanc+3.435
emis+3.337
ongyang+3.324
Neg logit contributions
arnaev-8.562
 Grassley-7.865
ufact-7.760
Station-7.743
 Straw-7.671
Token(
Token ID7
Feature activation-4.24e-01

Pos logit contributions
+1.146
ongyang+1.145
 sett+1.136
 emanc+1.130
emis+1.129
Neg logit contributions
arnaev-1.379
 Grassley-1.270
 Explos-1.244
 Straw-1.240
Station-1.223
Token5
Token ID20
Feature activation+2.00e+00

Pos logit contributions
arnaev+0.328
 Grassley+0.305
Station+0.298
 Explos+0.298
 Straw+0.297
Neg logit contributions
ongyang-0.308
 emanc-0.305
 sett-0.304
emis-0.302
-0.300
Tokens
Token ID82
Feature activation+1.08e+00

Pos logit contributions
 sett+1.433
ongyang+1.426
 emanc+1.425
emis+1.419
+1.404
Neg logit contributions
arnaev-1.553
 Grassley-1.428
Station-1.393
 Explos-1.391
 Straw-1.386
Token)}
Token ID38165
Feature activation+1.29e+00

Pos logit contributions
ongyang+0.952
 sett+0.939
 emanc+0.939
emis+0.937
+0.932
Neg logit contributions
arnaev-0.670
 Grassley-0.609
 Explos-0.594
Station-0.592
 Straw-0.589
Tokenx
Token ID87
Feature activation-1.92e+00

Pos logit contributions
arnaev+0.412
 Grassley+0.381
Station+0.374
 Explos+0.369
 Straw+0.369
Neg logit contributions
ongyang-0.573
 emanc-0.570
 sett-0.565
emis-0.561
 immersion-0.557
Token.
Token ID13
Feature activation-3.84e+00

Pos logit contributions
arnaev+1.327
 Grassley+1.253
Station+1.230
 Straw+1.204
 Explos+1.198
Neg logit contributions
ongyang-1.557
 emanc-1.547
emis-1.517
 sett-1.517
 immersion-1.501
Token143
Token ID21139
Feature activation-2.04e+00

Pos logit contributions
arnaev+2.623
Station+2.429
 Grassley+2.420
+2.319
 Straw+2.307
Neg logit contributions
 emanc-3.155
ongyang-3.104
 sett-3.043
 proble-3.017
emis-3.009
Token 10
Token ID838
Feature activation+1.52e-01

Pos logit contributions
arnaev+1.664
 Grassley+1.575
 Explos+1.543
Station+1.542
 Straw+1.539
Neg logit contributions
ongyang-1.387
 emanc-1.370
emis-1.358
 sett-1.354
-1.331
Token33
Token ID2091
Feature activation+6.08e-01

Pos logit contributions
+0.107
 sett+0.107
ongyang+0.106
 emanc+0.106
emis+0.106
Neg logit contributions
arnaev-0.120
 Grassley-0.110
 Explos-0.107
 Straw-0.107
Station-0.107
Token455
Token ID30505
Feature activation+8.13e+00

Pos logit contributions
 sett+0.427
ongyang+0.427
emis+0.426
 emanc+0.426
+0.425
Neg logit contributions
arnaev-0.480
 Grassley-0.444
 Explos-0.434
 Straw-0.433
Station-0.432
Token x
Token ID2124
Feature activation+1.81e+00

Pos logit contributions
 sett+4.747
 emanc+4.598
 fid+4.529
+4.522
emis+4.521
Neg logit contributions
arnaev-7.436
ufact-6.614
Station-6.502
 Grassley-6.486
 Explos-6.416
Token.
Token ID13
Feature activation-4.89e-01

Pos logit contributions
ongyang+1.278
 sett+1.277
 emanc+1.268
+1.268
emis+1.264
Neg logit contributions
arnaev-1.428
 Grassley-1.308
 Explos-1.288
 Straw-1.276
Station-1.274
Tokenx
Token ID87
Feature activation+5.83e-01

Pos logit contributions
arnaev+0.311
 Grassley+0.288
Station+0.281
 Explos+0.279
 Straw+0.278
Neg logit contributions
ongyang-0.421
 emanc-0.417
 sett-0.415
emis-0.412
-0.408
Token.
Token ID13
Feature activation-1.53e-01

Pos logit contributions
ongyang+0.433
 emanc+0.428
 sett+0.427
emis+0.426
+0.422
Neg logit contributions
arnaev-0.441
 Grassley-0.408
 Explos-0.399
Station-0.398
 Straw-0.397
Tokenx
Token ID87
Feature activation-1.95e+00

Pos logit contributions
arnaev+0.096
 Grassley+0.089
Station+0.087
 Explos+0.086
 Straw+0.086
Neg logit contributions
ongyang-0.133
 emanc-0.132
 sett-0.131
emis-0.130
-0.130
Token we
Token ID356
Feature activation-1.61e+00

Pos logit contributions
arnaev+2.096
 Grassley+1.984
Station+1.942
 Straw+1.939
 Explos+1.939
Neg logit contributions
ongyang-1.871
 emanc-1.833
emis-1.827
 sett-1.818
-1.799
Token follow
Token ID1061
Feature activation-9.98e-02

Pos logit contributions
arnaev+1.284
 Grassley+1.207
Station+1.179
 Explos+1.176
 Straw+1.174
Neg logit contributions
ongyang-1.128
 emanc-1.109
 sett-1.104
emis-1.103
-1.089
Token the
Token ID262
Feature activation-1.09e+00

Pos logit contributions
arnaev+0.084
 Grassley+0.078
Station+0.077
 Explos+0.076
 Straw+0.076
Neg logit contributions
ongyang-0.066
 emanc-0.066
 sett-0.065
emis-0.065
-0.064
Token SH
Token ID6006
Feature activation-8.01e-01

Pos logit contributions
arnaev+0.959
 Grassley+0.902
Station+0.886
 Explos+0.884
 Straw+0.881
Neg logit contributions
ongyang-0.673
 emanc-0.664
 sett-0.660
emis-0.658
-0.649
TokenRM
Token ID29138
Feature activation+3.29e+00

Pos logit contributions
arnaev+0.576
 Grassley+0.536
Station+0.525
 Explos+0.523
 Straw+0.521
Neg logit contributions
ongyang-0.626
 emanc-0.618
 sett-0.614
emis-0.613
-0.605
Token (
Token ID357
Feature activation+8.12e+00

Pos logit contributions
ongyang+2.134
 emanc+2.127
 sett+2.111
+2.100
 immersion+2.087
Neg logit contributions
arnaev-2.781
 Grassley-2.572
 Straw-2.506
Station-2.501
 Explos-2.487
TokenStr
Token ID13290
Feature activation-1.14e+00

Pos logit contributions
ongyang+5.909
 sett+5.879
+5.842
emis+5.708
 immersion+5.698
Neg logit contributions
arnaev-6.083
 Grassley-5.429
 AZ-5.412
 Straw-5.302
 Explos-5.282
Tokenategic
Token ID47917
Feature activation+1.73e-01

Pos logit contributions
arnaev+0.677
 Grassley+0.619
Station+0.601
 Explos+0.599
 Straw+0.597
Neg logit contributions
ongyang-1.025
 emanc-1.016
 sett-1.012
emis-1.010
-1.000
Token Human
Token ID5524
Feature activation+6.08e-01

Pos logit contributions
ongyang+0.124
 emanc+0.123
 sett+0.123
emis+0.122
+0.120
Neg logit contributions
arnaev-0.135
 Grassley-0.125
Station-0.123
 Explos-0.121
 Straw-0.121
Token Resource
Token ID20857
Feature activation-7.44e-01

Pos logit contributions
ongyang+0.463
 emanc+0.458
 sett+0.457
emis+0.455
+0.450
Neg logit contributions
arnaev-0.449
 Grassley-0.413
Station-0.406
 Explos-0.402
 Straw-0.401
Token Management
Token ID8549
Feature activation+8.62e-01

Pos logit contributions
arnaev+0.595
 Grassley+0.555
Station+0.543
 Explos+0.542
 Straw+0.540
Neg logit contributions
ongyang-0.522
 emanc-0.516
 sett-0.514
emis-0.512
-0.505
Tokenpop
Token ID12924
Feature activation-3.30e-01

Pos logit contributions
ongyang+2.005
 sett+1.968
emis+1.967
 emanc+1.959
+1.935
Neg logit contributions
arnaev-2.051
 Grassley-1.907
 Explos-1.866
 Straw-1.844
Station-1.840
Token/
Token ID14
Feature activation+1.12e+00

Pos logit contributions
arnaev+0.253
 Grassley+0.237
Station+0.232
 Explos+0.231
 Straw+0.231
Neg logit contributions
ongyang-0.241
 emanc-0.239
 sett-0.237
emis-0.236
-0.234
Tokenret
Token ID1186
Feature activation+2.16e+00

Pos logit contributions
ongyang+0.621
 emanc+0.609
 sett+0.608
emis+0.606
+0.595
Neg logit contributions
arnaev-1.061
 Grassley-1.002
 Explos-0.984
Station-0.982
 Straw-0.980
Token's
Token ID338
Feature activation+5.67e+00

Pos logit contributions
ongyang+1.489
 sett+1.475
 emanc+1.462
emis+1.434
 immersion+1.416
Neg logit contributions
arnaev-1.774
 Grassley-1.647
Station-1.610
 Explos-1.595
 Straw-1.588
Token frame
Token ID5739
Feature activation+2.03e+00

Pos logit contributions
 sett+3.107
 emanc+3.033
ongyang+3.014
 immersion+2.970
+2.914
Neg logit contributions
arnaev-5.490
 Grassley-5.056
Station-4.981
 Explos-4.972
 Straw-4.908
Token |
Token ID930
Feature activation+8.06e+00

Pos logit contributions
 sett+1.154
ongyang+1.144
 emanc+1.140
emis+1.139
+1.130
Neg logit contributions
arnaev-1.887
 Grassley-1.748
Station-1.714
 Explos-1.711
 Straw-1.710
Token [
Token ID685
Feature activation+3.68e+00

Pos logit contributions
 sett+3.715
 emanc+3.630
ongyang+3.503
+3.493
emis+3.469
Neg logit contributions
arnaev-8.286
 Grassley-7.760
Station-7.564
 Straw-7.414
 Explos-7.391
Tokenaddress
Token ID21975
Feature activation-4.68e-01

Pos logit contributions
emis+2.132
ongyang+2.125
 emanc+2.115
 sett+2.114
+2.085
Neg logit contributions
arnaev-3.370
 Grassley-3.154
 Explos-3.091
 Straw-3.090
Station-3.045
Token of
Token ID286
Feature activation+4.96e+00

Pos logit contributions
arnaev+0.358
 Grassley+0.336
Station+0.329
 Explos+0.327
 Straw+0.327
Neg logit contributions
ongyang-0.344
 emanc-0.339
emis-0.337
 sett-0.336
-0.332
Token system
Token ID1080
Feature activation+3.03e+00

Pos logit contributions
 sett+2.859
ongyang+2.782
 emanc+2.780
+2.730
emis+2.723
Neg logit contributions
arnaev-4.606
 Grassley-4.274
Station-4.217
 Explos-4.201
 Straw-4.130
Token]
Token ID60
Feature activation+8.90e-01

Pos logit contributions
 sett+1.107
ongyang+1.107
 emanc+1.090
+1.081
emis+1.080
Neg logit contributions
arnaev-3.411
 Grassley-3.215
 Explos-3.172
Station-3.161
 Straw-3.156
Token feed
Token ID3745
Feature activation+4.44e+00

Pos logit contributions
arnaev+0.164
 Grassley+0.151
Station+0.147
 Explos+0.147
 Straw+0.146
Neg logit contributions
ongyang-0.163
 emanc-0.162
 sett-0.162
emis-0.162
-0.160
Token by
Token ID416
Feature activation+5.81e+00

Pos logit contributions
 emanc+2.905
 sett+2.876
+2.860
ongyang+2.855
emis+2.848
Neg logit contributions
arnaev-3.743
 Grassley-3.415
Station-3.341
 Explos-3.324
 Straw-3.321
Token going
Token ID1016
Feature activation+2.26e+00

Pos logit contributions
ongyang+3.467
 emanc+3.426
 sett+3.403
emis+3.386
+3.342
Neg logit contributions
arnaev-5.242
 Grassley-4.933
Station-4.852
 Explos-4.838
 Straw-4.823
Token here
Token ID994
Feature activation+1.61e+00

Pos logit contributions
 sett+1.601
 emanc+1.599
emis+1.571
ongyang+1.558
+1.546
Neg logit contributions
arnaev-1.812
 Grassley-1.672
 Explos-1.655
 Straw-1.635
Station-1.608
Token.
Token ID13
Feature activation+1.18e+00

Pos logit contributions
ongyang+1.165
 emanc+1.156
 sett+1.156
emis+1.150
+1.139
Neg logit contributions
arnaev-1.255
 Grassley-1.158
Station-1.131
 Straw-1.130
 Explos-1.128
Token But
Token ID887
Feature activation+8.06e+00

Pos logit contributions
ongyang+0.736
 emanc+0.729
 sett+0.723
emis+0.717
+0.710
Neg logit contributions
arnaev-1.028
 Grassley-0.973
 Straw-0.954
 Explos-0.954
Station-0.951
Token please
Token ID3387
Feature activation+5.28e+00

Pos logit contributions
 sett+6.085
 emanc+6.083
 fid+6.011
 immersion+6.002
emis+5.945
Neg logit contributions
arnaev-6.102
ufact-5.232
 Grassley-5.221
 Explos-5.123
Station-5.106
Token note
Token ID3465
Feature activation+4.13e+00

Pos logit contributions
 sty+2.073
 sett+2.058
ixel+2.041
 emanc+2.031
emis+2.016
Neg logit contributions
arnaev-5.647
ufact-5.521
Station-5.357
 Grassley-5.324
 Explos-5.300
Token that
Token ID326
Feature activation+4.82e+00

Pos logit contributions
ongyang+2.376
 sett+2.310
 immersion+2.294
 emanc+2.294
emis+2.260
Neg logit contributions
arnaev-3.777
 Grassley-3.588
Station-3.544
 Straw-3.532
 Explos-3.486
Token my
Token ID616
Feature activation+5.99e+00

Pos logit contributions
 emanc+3.439
ongyang+3.436
 sett+3.395
emis+3.369
 immersion+3.358
Neg logit contributions
arnaev-3.719
 Grassley-3.474
Station-3.404
 Straw-3.375
 Explos-3.364
Token tweets
Token ID12665
Feature activation+2.67e+00

Pos logit contributions
 sett+3.203
+3.134
 emanc+3.061
ongyang+3.014
 torped+3.000
Neg logit contributions
arnaev-5.633
 Grassley-5.389
 Explos-5.379
Station-5.294
ufact-5.208
Token]
Token ID60
Feature activation-1.16e-01

Pos logit contributions
arnaev+0.603
 Grassley+0.569
Station+0.560
 Explos+0.557
 Straw+0.557
Neg logit contributions
ongyang-0.405
 emanc-0.400
 sett-0.397
emis-0.396
-0.390
Token::
Token ID3712
Feature activation-1.47e+00

Pos logit contributions
arnaev+0.090
 Grassley+0.084
 Explos+0.082
 Straw+0.081
Station+0.081
Neg logit contributions
ongyang-0.084
 emanc-0.083
 sett-0.083
emis-0.082
-0.082
TokenAll
Token ID3237
Feature activation-2.74e+00

Pos logit contributions
arnaev+1.091
 Grassley+1.020
Station+1.006
 Explos+0.993
 Straw+0.992
Neg logit contributions
ongyang-1.099
 emanc-1.089
 sett-1.080
emis-1.079
-1.063
TokenSc
Token ID3351
Feature activation-2.47e+00

Pos logit contributions
arnaev+2.190
 Grassley+2.060
Station+2.045
 Straw+2.029
 Explos+2.015
Neg logit contributions
ongyang-1.878
 emanc-1.851
emis-1.842
 sett-1.839
-1.812
Tokenreens
Token ID5681
Feature activation+4.66e-01

Pos logit contributions
arnaev+2.343
 Grassley+2.216
Station+2.197
 Explos+2.173
 Straw+2.170
Neg logit contributions
ongyang-1.337
 emanc-1.330
 sett-1.320
-1.301
emis-1.297
Token |
Token ID930
Feature activation+8.02e+00

Pos logit contributions
ongyang+0.316
 emanc+0.313
 sett+0.312
emis+0.310
+0.307
Neg logit contributions
arnaev-0.383
 Grassley-0.358
 Explos-0.350
Station-0.349
 Straw-0.348
Token Where
Token ID6350
Feature activation+1.33e+00

Pos logit contributions
 emanc+4.930
 sett+4.859
+4.740
ongyang+4.721
emis+4.693
Neg logit contributions
arnaev-6.895
 Grassley-6.322
 Explos-6.142
 Straw-6.058
Station-6.039
Token Primary
Token ID21087
Feature activation+5.07e-01

Pos logit contributions
ongyang+0.860
 sett+0.858
 emanc+0.857
+0.837
emis+0.833
Neg logit contributions
arnaev-1.128
 Grassley-1.048
 Explos-1.021
 Straw-1.019
Station-1.017
Token |
Token ID930
Feature activation+7.17e+00

Pos logit contributions
ongyang+0.356
 emanc+0.355
 sett+0.355
emis+0.351
+0.350
Neg logit contributions
arnaev-0.405
 Grassley-0.374
 Explos-0.364
 Straw-0.362
Station-0.360
Token Select
Token ID9683
Feature activation+1.17e+00

Pos logit contributions
 emanc+5.278
 sett+5.261
+5.172
ongyang+5.163
emis+5.162
Neg logit contributions
arnaev-5.311
 Grassley-4.749
 Explos-4.651
Station-4.591
 Straw-4.546
Token -
Token ID532
Feature activation-1.34e+00

Pos logit contributions
ongyang+0.847
 emanc+0.840
 sett+0.838
emis+0.831
+0.825
Neg logit contributions
arnaev-0.902
 Grassley-0.834
Station-0.815
 Explos-0.815
 Straw-0.808
Token noted
Token ID4367
Feature activation+1.13e+00

Pos logit contributions
arnaev+0.032
 Grassley+0.030
Station+0.030
 Explos+0.030
 Straw+0.030
Neg logit contributions
ongyang-0.024
 emanc-0.024
 sett-0.024
emis-0.023
-0.023
Token.
Token ID13
Feature activation+4.57e-01

Pos logit contributions
ongyang+0.812
 emanc+0.806
 sett+0.804
emis+0.795
+0.793
Neg logit contributions
arnaev-0.887
 Grassley-0.824
 Explos-0.813
Station-0.806
 Straw-0.800
Token<|endoftext|>
Token ID50256
Feature activation-1.83e-01

Pos logit contributions
ongyang+0.302
 sett+0.299
 emanc+0.299
+0.297
emis+0.296
Neg logit contributions
arnaev-0.383
 Grassley-0.354
Station-0.349
 Explos-0.346
 Straw-0.344
TokenT
Token ID51
Feature activation-1.88e+00

Pos logit contributions
arnaev+0.139
 Grassley+0.130
 Explos+0.127
 Straw+0.126
Station+0.126
Neg logit contributions
ongyang-0.136
 emanc-0.134
 sett-0.133
emis-0.133
-0.132
TokenEL
Token ID3698
Feature activation+1.66e+00

Pos logit contributions
arnaev+1.510
 Grassley+1.411
Station+1.386
 Straw+1.377
 Explos+1.377
Neg logit contributions
ongyang-1.300
 emanc-1.290
 sett-1.283
emis-1.275
-1.263
Token AV
Token ID14661
Feature activation+8.01e+00

Pos logit contributions
 sett+1.071
 emanc+1.064
ongyang+1.054
emis+1.049
+1.049
Neg logit contributions
arnaev-1.434
 Grassley-1.316
Station-1.299
 Explos-1.289
 Straw-1.288
TokenIV
Token ID3824
Feature activation+8.15e-01

Pos logit contributions
emis+5.014
 emanc+4.904
ongyang+4.886
 sett+4.870
+4.852
Neg logit contributions
arnaev-7.069
 Grassley-6.482
 Straw-6.407
Station-6.194
ufact-6.026
Token
Token ID784
Feature activation+1.86e+00

Pos logit contributions
ongyang+0.555
 emanc+0.552
 sett+0.550
emis+0.547
+0.545
Neg logit contributions
arnaev-0.667
 Grassley-0.619
Station-0.608
 Straw-0.603
 Explos-0.602
Token A
Token ID317
Feature activation-1.36e-01

Pos logit contributions
 sett+1.239
ongyang+1.229
 emanc+1.226
emis+1.214
+1.212
Neg logit contributions
arnaev-1.540
 Grassley-1.416
Station-1.395
 Straw-1.378
 Explos-1.370
Token clandestine
Token ID39903
Feature activation-2.27e+00

Pos logit contributions
arnaev+0.119
 Grassley+0.112
Station+0.110
 Explos+0.109
 Straw+0.109
Neg logit contributions
ongyang-0.085
 emanc-0.084
 sett-0.084
emis-0.084
-0.082
Token Israeli
Token ID6085
Feature activation-1.30e-01

Pos logit contributions
arnaev+2.014
 Grassley+1.931
 Explos+1.900
 Straw+1.892
 AZ+1.877
Neg logit contributions
ongyang-1.369
emis-1.343
 emanc-1.323
-1.320
ixel-1.286
Tokenona
Token ID4450
Feature activation+3.37e+00

Pos logit contributions
arnaev+0.578
 Grassley+0.539
Station+0.527
 Explos+0.526
 Straw+0.524
Neg logit contributions
ongyang-0.558
 emanc-0.552
 sett-0.549
emis-0.547
-0.541
Token,
Token ID11
Feature activation+1.64e+00

Pos logit contributions
 sett+2.339
ongyang+2.334
 emanc+2.328
emis+2.320
+2.296
Neg logit contributions
arnaev-2.719
 Grassley-2.512
 Explos-2.443
Station-2.443
 Straw-2.416
Token Hawai
Token ID10847
Feature activation+3.49e+00

Pos logit contributions
ongyang+1.110
 emanc+1.101
 sett+1.097
emis+1.090
+1.079
Neg logit contributions
arnaev-1.345
 Grassley-1.255
Station-1.231
 Explos-1.226
 Straw-1.220
Token
Token ID134
Feature activation+2.73e+00

Pos logit contributions
ongyang+2.064
 sett+2.038
 emanc+2.022
emis+2.007
+1.995
Neg logit contributions
arnaev-3.191
 Grassley-2.952
 Explos-2.919
Station-2.908
 Straw-2.882
Token
Token ID119
Feature activation+1.48e+00

Pos logit contributions
ongyang+1.683
emis+1.658
 emanc+1.656
 sett+1.655
+1.627
Neg logit contributions
arnaev-2.412
 Grassley-2.262
Station-2.224
 Explos-2.221
 Straw-2.208
Tokeni
Token ID72
Feature activation+7.99e+00

Pos logit contributions
ongyang+0.843
 emanc+0.826
 sett+0.823
emis+0.822
+0.810
Neg logit contributions
arnaev-1.373
 Grassley-1.292
 Explos-1.271
Station-1.271
 Straw-1.266
Token a
Token ID257
Feature activation+4.30e+00

Pos logit contributions
 sett+5.238
 emanc+5.135
emis+5.032
 immersion+5.001
 ker+4.964
Neg logit contributions
arnaev-6.788
 Grassley-6.100
Station-5.996
 Explos-5.983
 Straw-5.830
Token me
Token ID502
Feature activation+4.87e+00

Pos logit contributions
 sett+2.788
emis+2.759
 emanc+2.753
ongyang+2.749
+2.688
Neg logit contributions
arnaev-3.671
 Grassley-3.403
 Explos-3.341
Station-3.327
 Straw-3.282
Token Hal
Token ID11023
Feature activation-1.14e+00

Pos logit contributions
 sett+3.224
ongyang+3.173
 emanc+3.169
emis+3.146
+3.077
Neg logit contributions
arnaev-4.112
 Grassley-3.781
Station-3.718
 Explos-3.703
 Straw-3.630
Tokenep
Token ID538
Feature activation-5.06e-01

Pos logit contributions
arnaev+0.891
 Grassley+0.834
Station+0.816
 Explos+0.815
 Straw+0.815
Neg logit contributions
ongyang-0.814
 emanc-0.807
 sett-0.800
emis-0.797
-0.791
Tokenā
Token ID10235
Feature activation+1.48e+00

Pos logit contributions
arnaev+0.382
 Grassley+0.356
Station+0.348
 Explos+0.347
 Straw+0.346
Neg logit contributions
ongyang-0.378
 emanc-0.373
 sett-0.371
emis-0.371
-0.366
Token[
Token ID58
Feature activation-1.72e+00

Pos logit contributions
arnaev+3.811
 Grassley+3.583
Station+3.542
 Explos+3.503
 Straw+3.473
Neg logit contributions
ongyang-4.015
 emanc-3.965
 sett-3.917
emis-3.912
 immersion-3.865
Token+(
Token ID33747
Feature activation+1.99e-01

Pos logit contributions
arnaev+1.420
 Grassley+1.333
Station+1.307
 Explos+1.303
 Straw+1.300
Neg logit contributions
ongyang-1.152
 emanc-1.138
 sett-1.131
emis-1.128
-1.113
Token\
Token ID59
Feature activation-6.32e+00

Pos logit contributions
ongyang+0.146
 emanc+0.144
 sett+0.144
emis+0.143
+0.142
Neg logit contributions
arnaev-0.153
 Grassley-0.142
 Explos-0.139
Station-0.138
 Straw-0.138
TokenS
Token ID50
Feature activation-3.90e+00

Pos logit contributions
arnaev+4.694
 Grassley+4.406
Station+4.378
 Straw+4.296
 Explos+4.286
Neg logit contributions
ongyang-4.640
 emanc-4.595
 sett-4.521
emis-4.512
 immersion-4.435
Token+
Token ID10
Feature activation-3.15e+00

Pos logit contributions
arnaev+3.256
 Grassley+3.102
Station+3.068
 Explos+3.034
 Straw+3.021
Neg logit contributions
ongyang-2.547
 emanc-2.488
emis-2.482
 sett-2.460
 immersion-2.420
Token)\
Token ID19415
Feature activation-9.54e+00

Pos logit contributions
arnaev+2.169
 Grassley+2.025
Station+1.997
 Explos+1.964
 Straw+1.963
Neg logit contributions
ongyang-2.537
 emanc-2.501
emis-2.488
 sett-2.488
 immersion-2.444
Tokens
Token ID82
Feature activation-1.85e+00

Pos logit contributions
arnaev+7.096
Station+6.907
 Grassley+6.855
 Straw+6.657
 AZ+6.626
Neg logit contributions
ongyang-6.593
 emanc-6.530
 sett-6.384
emis-6.331
 immersion-6.282
Token+
Token ID10
Feature activation-1.74e+00

Pos logit contributions
arnaev+1.619
 Grassley+1.529
Station+1.503
 Explos+1.496
 Straw+1.492
Neg logit contributions
ongyang-1.151
 emanc-1.135
 sett-1.126
emis-1.125
-1.104
Token"
Token ID1
Feature activation-3.08e+00

Pos logit contributions
arnaev+1.369
 Grassley+1.281
Station+1.257
 Explos+1.250
 Straw+1.247
Neg logit contributions
ongyang-1.244
 emanc-1.229
 sett-1.222
emis-1.220
-1.203
Token\
Token ID59
Feature activation-6.21e+00

Pos logit contributions
arnaev+2.396
 Grassley+2.266
Station+2.231
 Explos+2.211
 Straw+2.205
Neg logit contributions
ongyang-2.190
 emanc-2.150
emis-2.138
 sett-2.135
 immersion-2.095
TokenS
Token ID50
Feature activation-2.40e+00

Pos logit contributions
arnaev+4.588
 Grassley+4.345
Station+4.295
 Straw+4.194
 Explos+4.191
Neg logit contributions
ongyang-4.559
 emanc-4.514
 sett-4.469
emis-4.449
 immersion-4.365
Token>
Token ID29
Feature activation+2.46e+00

Pos logit contributions
ongyang+1.374
 sett+1.369
 emanc+1.366
emis+1.339
 immersion+1.327
Neg logit contributions
arnaev-2.013
 Grassley-1.875
 Straw-1.846
Station-1.846
 Explos-1.843
Token{{
Token ID27007
Feature activation-8.38e-01

Pos logit contributions
ongyang+1.549
 sett+1.522
+1.517
 emanc+1.513
emis+1.508
Neg logit contributions
arnaev-2.145
 Grassley-1.992
 Explos-1.945
 Straw-1.943
Station-1.929
Token phone
Token ID3072
Feature activation-3.62e+00

Pos logit contributions
arnaev+0.674
 Grassley+0.632
Station+0.619
 Explos+0.617
 Straw+0.616
Neg logit contributions
ongyang-0.582
 emanc-0.575
 sett-0.571
emis-0.571
-0.563
Token.
Token ID13
Feature activation-1.43e+00

Pos logit contributions
arnaev+2.538
 Grassley+2.390
Station+2.349
 Explos+2.326
 Straw+2.320
Neg logit contributions
ongyang-2.842
 emanc-2.801
emis-2.799
 sett-2.772
-2.740
Tokensn
Token ID16184
Feature activation-2.49e+00

Pos logit contributions
arnaev+1.099
 Grassley+1.025
Station+1.008
 Explos+1.000
 Straw+0.997
Neg logit contributions
ongyang-1.050
 emanc-1.039
 sett-1.033
emis-1.028
-1.016
Tokenipp
Token ID3974
Feature activation-9.27e+00

Pos logit contributions
arnaev+1.802
 Grassley+1.688
Station+1.650
 Straw+1.640
 Explos+1.631
Neg logit contributions
 emanc-1.895
ongyang-1.894
 sett-1.871
-1.863
emis-1.854
Tokenet
Token ID316
Feature activation-3.52e+00

Pos logit contributions
arnaev+6.860
 Grassley+6.492
Station+6.351
pn+6.251
+6.241
Neg logit contributions
 emanc-6.551
ongyang-6.394
 immersion-6.364
-6.356
 sett-6.263
Token }}
Token ID34949
Feature activation-2.31e+00

Pos logit contributions
arnaev+2.069
 Grassley+1.919
Station+1.903
 Explos+1.865
 Straw+1.861
Neg logit contributions
ongyang-3.156
 emanc-3.122
emis-3.107
 sett-3.095
 immersion-3.053
Token
Token ID3556
Feature activation-3.84e+00

Pos logit contributions
arnaev+1.520
 Grassley+1.409
Station+1.377
 Explos+1.370
 Straw+1.367
Neg logit contributions
ongyang-1.932
 emanc-1.910
 sett-1.900
emis-1.898
-1.877
Tokenp
Token ID79
Feature activation-3.08e+00

Pos logit contributions
arnaev+2.095
 Grassley+1.943
Station+1.901
 Straw+1.843
 Explos+1.833
Neg logit contributions
ongyang-3.603
 emanc-3.579
 sett-3.559
-3.530
emis-3.528
Token>
Token ID29
Feature activation-8.84e-01

Pos logit contributions
arnaev+2.546
 Grassley+2.400
Station+2.352
 Straw+2.338
 Explos+2.337
Neg logit contributions
ongyang-2.064
 emanc-2.032
emis-2.020
 sett-2.020
-1.989
Token ap
Token ID2471
Feature activation-1.88e+00

Pos logit contributions
arnaev+1.301
 Grassley+1.229
Station+1.208
 Explos+1.205
 Straw+1.202
Neg logit contributions
ongyang-0.792
 emanc-0.780
 sett-0.775
emis-0.772
-0.762
Token =
Token ID796
Feature activation-3.58e+00

Pos logit contributions
arnaev+1.442
 Grassley+1.356
Station+1.342
 Explos+1.324
 Straw+1.318
Neg logit contributions
ongyang-1.377
 emanc-1.365
 sett-1.350
emis-1.346
 immersion-1.330
Token arg
Token ID1822
Feature activation-4.47e+00

Pos logit contributions
arnaev+1.947
 Grassley+1.841
 AZ+1.784
 Straw+1.765
Station+1.765
Neg logit contributions
ongyang-3.354
emis-3.272
 emanc-3.255
-3.254
 sett-3.235
Tokenparse
Token ID29572
Feature activation-2.02e+00

Pos logit contributions
arnaev+1.776
Station+1.598
 Grassley+1.574
pn+1.570
 Explos+1.553
Neg logit contributions
 emanc-4.774
ongyang-4.733
 sett-4.714
emis-4.693
 immersion-4.673
Token.
Token ID13
Feature activation-4.15e+00

Pos logit contributions
arnaev+1.439
 Grassley+1.354
Station+1.331
 Straw+1.319
 Explos+1.316
Neg logit contributions
ongyang-1.582
 emanc-1.563
emis-1.548
 sett-1.545
 immersion-1.522
TokenArg
Token ID28100
Feature activation-8.94e+00

Pos logit contributions
arnaev+1.383
Station+1.263
 Grassley+1.233
 Straw+1.181
 Explos+1.166
Neg logit contributions
ongyang-4.778
 emanc-4.763
 sett-4.724
emis-4.704
 immersion-4.681
Tokenument
Token ID1713
Feature activation-1.55e+00

Pos logit contributions
arnaev+2.833
Station+2.723
+2.457
 Grassley+2.354
 Straw+2.332
Neg logit contributions
 emanc-10.195
 proble-10.142
 sett-10.043
ongyang-9.857
 sty-9.852
TokenParser
Token ID46677
Feature activation-1.57e+00

Pos logit contributions
arnaev+0.641
 Grassley+0.584
Station+0.580
 Explos+0.557
 Straw+0.557
Neg logit contributions
ongyang-1.672
 emanc-1.667
 sett-1.649
emis-1.644
 immersion-1.631
Token()
Token ID3419
Feature activation-4.23e+00

Pos logit contributions
arnaev+1.023
 Grassley+0.956
Station+0.937
 Explos+0.926
 Straw+0.924
Neg logit contributions
ongyang-1.330
 emanc-1.322
emis-1.310
 sett-1.308
 immersion-1.287
Token ap
Token ID2471
Feature activation-4.48e+00

Pos logit contributions
arnaev+3.541
 Grassley+3.393
 AZ+3.352
 Straw+3.323
 Explos+3.321
Neg logit contributions
ongyang-2.710
emis-2.613
-2.601
 emanc-2.576
 sett-2.559
Token.
Token ID13
Feature activation-2.82e+00

Pos logit contributions
arnaev+2.877
 Grassley+2.751
Station+2.723
 Straw+2.670
 AZ+2.649
Neg logit contributions
ongyang-3.792
 emanc-3.740
emis-3.686
 immersion-3.659
 sett-3.657
Tokend
Token ID67
Feature activation+1.02e-01

Pos logit contributions
arnaev+1.278
 Grassley+1.198
Station+1.174
 Explos+1.171
 Straw+1.168
Neg logit contributions
ongyang-1.061
 emanc-1.049
 sett-1.043
emis-1.040
-1.027
Token 3
Token ID513
Feature activation-6.49e-01

Pos logit contributions
ongyang+0.066
 emanc+0.065
 sett+0.064
emis+0.064
+0.063
Neg logit contributions
arnaev-0.088
 Grassley-0.083
Station-0.081
 Explos-0.081
 Straw-0.081
Token.
Token ID13
Feature activation-1.23e+00

Pos logit contributions
arnaev+0.475
 Grassley+0.443
Station+0.434
 Explos+0.432
 Straw+0.431
Neg logit contributions
ongyang-0.499
 emanc-0.493
 sett-0.489
emis-0.489
-0.482
Token Count
Token ID2764
Feature activation-6.04e+00

Pos logit contributions
arnaev+0.948
 Grassley+0.887
Station+0.868
 Explos+0.867
 Straw+0.865
Neg logit contributions
ongyang-0.891
 emanc-0.880
 sett-0.873
emis-0.873
-0.861
Token below
Token ID2174
Feature activation-1.92e+00

Pos logit contributions
arnaev+5.189
 Grassley+4.906
Station+4.843
 Straw+4.840
 Explos+4.786
Neg logit contributions
ongyang-3.788
emis-3.652
 emanc-3.635
 sett-3.584
-3.541
Token one
Token ID530
Feature activation-8.83e+00

Pos logit contributions
arnaev+1.667
 Grassley+1.572
Station+1.543
 Straw+1.539
 Explos+1.538
Neg logit contributions
ongyang-1.212
 emanc-1.189
emis-1.184
 sett-1.181
-1.165
Token thousand
Token ID7319
Feature activation-3.47e+00

Pos logit contributions
arnaev+6.175
 Grassley+5.797
 Straw+5.729
Station+5.669
 AZ+5.651
Neg logit contributions
ongyang-6.591
emis-6.356
 emanc-6.307
ixel-6.268
-6.211
Token is
Token ID318
Feature activation-1.75e-01

Pos logit contributions
arnaev+2.706
 Grassley+2.538
Station+2.494
 Explos+2.487
 Straw+2.484
Neg logit contributions
ongyang-2.481
emis-2.425
 emanc-2.424
 sett-2.404
-2.385
Token low
Token ID1877
Feature activation-7.27e-01

Pos logit contributions
arnaev+0.184
 Grassley+0.175
Station+0.172
 Explos+0.172
 Straw+0.172
Neg logit contributions
ongyang-0.078
 emanc-0.077
 sett-0.077
emis-0.076
-0.075
Token (
Token ID357
Feature activation-3.87e+00

Pos logit contributions
arnaev+0.613
 Grassley+0.574
Station+0.563
 Explos+0.561
 Straw+0.560
Neg logit contributions
ongyang-0.477
 emanc-0.473
 sett-0.471
emis-0.465
-0.463
Token7
Token ID22
Feature activation-9.79e-01

Pos logit contributions
arnaev+2.651
 Grassley+2.471
Station+2.447
 Explos+2.401
 Straw+2.388
Neg logit contributions
ongyang-3.117
 emanc-3.094
 sett-3.069
emis-3.047
 immersion-3.014
Token updates
Token ID5992
Feature activation-5.59e+00

Pos logit contributions
arnaev+2.913
 Grassley+2.700
 Explos+2.670
Station+2.617
 Straw+2.616
Neg logit contributions
ongyang-4.668
emis-4.601
 emanc-4.596
 sett-4.561
-4.547
Token?
Token ID30
Feature activation-4.31e+00

Pos logit contributions
arnaev+3.576
 Grassley+3.473
 Straw+3.358
 Explos+3.347
Station+3.323
Neg logit contributions
ongyang-4.685
-4.535
emis-4.529
 emanc-4.504
 sett-4.470
Token No
Token ID1400
Feature activation-6.01e+00

Pos logit contributions
arnaev+3.135
 Grassley+3.058
 Straw+3.029
 Explos+3.014
 AZ+2.957
Neg logit contributions
ongyang-3.272
 emanc-3.206
emis-3.179
 sett-3.157
 immersion-3.140
Token more
Token ID517
Feature activation-7.48e-01

Pos logit contributions
arnaev+3.701
 Grassley+3.525
 Straw+3.475
 Explos+3.473
 AZ+3.437
Neg logit contributions
ongyang-5.078
emis-4.972
ixel-4.906
 emanc-4.873
-4.828
Token bad
Token ID2089
Feature activation-2.67e+00

Pos logit contributions
arnaev+0.679
 Grassley+0.648
 Straw+0.632
Station+0.629
 Explos+0.628
Neg logit contributions
ongyang-0.440
 emanc-0.431
emis-0.430
 sett-0.426
-0.421
Token news
Token ID1705
Feature activation-8.83e+00

Pos logit contributions
arnaev+2.583
 Grassley+2.485
 Straw+2.442
 Explos+2.437
 AZ+2.436
Neg logit contributions
ongyang-1.375
 emanc-1.340
emis-1.325
 sett-1.308
-1.306
Token pl
Token ID458
Feature activation-6.44e+00

Pos logit contributions
arnaev+6.082
 Grassley+5.998
 Straw+5.866
 straw+5.786
 Lug+5.770
Neg logit contributions
ongyang-6.667
-6.475
emis-6.377
ixel-6.300
 emanc-6.245
Tokens
Token ID82
Feature activation-1.31e+00

Pos logit contributions
arnaev+3.771
Station+3.545
 Grassley+3.521
 Straw+3.502
 Explos+3.462
Neg logit contributions
ongyang-5.706
 emanc-5.702
 proble-5.618
-5.580
 sett-5.532
Token.
Token ID13
Feature activation-4.47e+00

Pos logit contributions
arnaev+0.958
 Grassley+0.895
Station+0.875
 Explos+0.872
 Straw+0.870
Neg logit contributions
ongyang-1.007
 emanc-0.996
 sett-0.989
emis-0.987
-0.975
Token Good
Token ID4599
Feature activation-6.93e+00

Pos logit contributions
arnaev+2.858
 Grassley+2.778
 Straw+2.718
 Explos+2.676
Station+2.633
Neg logit contributions
ongyang-3.799
 emanc-3.773
 sett-3.702
 immersion-3.698
emis-3.691
Token updates
Token ID5992
Feature activation-7.22e+00

Pos logit contributions
arnaev+3.132
 AZ+2.866
 Explos+2.863
 Grassley+2.855
Station+2.768
Neg logit contributions
ongyang-6.922
emis-6.858
 emanc-6.801
 sett-6.767
-6.715
TokenElement
Token ID20180
Feature activation-3.85e+00

Pos logit contributions
arnaev+2.798
Station+2.793
 Grassley+2.694
 Explos+2.573
 Straw+2.540
Neg logit contributions
ongyang-5.273
 emanc-5.218
 sett-5.156
emis-5.083
 torped-5.065
Token(
Token ID7
Feature activation-3.71e+00

Pos logit contributions
arnaev+2.657
 Grassley+2.525
Station+2.522
 Explos+2.453
 Straw+2.448
Neg logit contributions
ongyang-3.087
 emanc-3.066
emis-3.009
 sett-3.008
 immersion-2.979
Tokencv
Token ID33967
Feature activation-3.53e+00

Pos logit contributions
arnaev+2.927
Station+2.710
 Grassley+2.707
 AZ+2.625
pn+2.614
Neg logit contributions
 emanc-2.621
 sett-2.585
ongyang-2.552
-2.518
emis-2.502
Token2
Token ID17
Feature activation-4.13e+00

Pos logit contributions
arnaev+2.164
 Grassley+2.028
Station+2.018
 Straw+1.941
 Explos+1.913
Neg logit contributions
 emanc-3.102
ongyang-3.095
 sett-3.042
emis-3.039
 immersion-3.007
Token.
Token ID13
Feature activation-3.96e+00

Pos logit contributions
arnaev+2.682
Station+2.574
 Grassley+2.562
 Straw+2.482
 Explos+2.469
Neg logit contributions
ongyang-3.451
 emanc-3.420
 sett-3.355
emis-3.348
 proble-3.319
TokenM
Token ID44
Feature activation-8.61e+00

Pos logit contributions
arnaev+2.680
Station+2.632
 Grassley+2.562
 AZ+2.522
 Explos+2.512
Neg logit contributions
ongyang-3.167
 emanc-3.115
 sett-3.080
emis-3.043
 immersion-3.025
TokenOR
Token ID1581
Feature activation-3.95e+00

Pos logit contributions
arnaev+4.514
Station+4.482
 AZ+4.357
 Grassley+4.284
+4.168
Neg logit contributions
 emanc-7.981
 proble-7.961
ongyang-7.897
 sett-7.884
 torped-7.776
TokenPH
Token ID11909
Feature activation+1.42e-01

Pos logit contributions
arnaev+1.788
Station+1.648
 Grassley+1.624
 Explos+1.553
 AZ+1.551
Neg logit contributions
ongyang-4.100
 emanc-4.085
 sett-4.066
emis-3.994
 immersion-3.984
Token_
Token ID62
Feature activation-5.02e+00

Pos logit contributions
ongyang+0.101
 emanc+0.100
 sett+0.100
emis+0.099
+0.098
Neg logit contributions
arnaev-0.112
 Grassley-0.104
Station-0.102
 Explos-0.102
 Straw-0.102
TokenRECT
Token ID23988
Feature activation-1.57e+00

Pos logit contributions
arnaev+2.964
Station+2.836
 AZ+2.755
 Grassley+2.741
+2.654
Neg logit contributions
 emanc-4.494
ongyang-4.450
 sett-4.408
emis-4.381
 immersion-4.344
Token,
Token ID11
Feature activation+7.70e-01

Pos logit contributions
arnaev+1.238
 Grassley+1.171
Station+1.152
 Explos+1.144
 Straw+1.141
Neg logit contributions
ongyang-1.112
 emanc-1.098
emis-1.085
 sett-1.085
 immersion-1.064
Token a
Token ID257
Feature activation+1.13e+00

Pos logit contributions
 emanc+0.823
ongyang+0.819
 sett+0.817
emis+0.812
+0.808
Neg logit contributions
arnaev-1.071
 Grassley-0.998
Station-0.979
 Explos-0.974
 Straw-0.971
Token gimm
Token ID33135
Feature activation+7.54e-01

Pos logit contributions
ongyang+0.690
 emanc+0.688
 sett+0.685
emis+0.679
+0.675
Neg logit contributions
arnaev-1.005
 Grassley-0.939
Station-0.923
 Explos-0.922
 Straw-0.916
Tokenicky
Token ID17479
Feature activation+6.16e-01

Pos logit contributions
ongyang+0.388
 emanc+0.381
emis+0.381
 sett+0.378
+0.370
Neg logit contributions
arnaev-0.742
 Grassley-0.701
Station-0.693
 Explos-0.691
 Straw-0.690
Token,
Token ID11
Feature activation+1.70e+00

Pos logit contributions
ongyang+0.370
 emanc+0.368
 sett+0.367
emis+0.362
+0.359
Neg logit contributions
arnaev-0.555
 Grassley-0.519
Station-0.510
 Explos-0.509
 Straw-0.507
Token w
Token ID266
Feature activation-1.39e+00

Pos logit contributions
 emanc+0.970
ongyang+0.970
 sett+0.964
emis+0.949
+0.947
Neg logit contributions
arnaev-1.572
 Grassley-1.471
Station-1.446
 Explos-1.445
 Straw-1.436
Tokenann
Token ID1236
Feature activation-8.55e+00

Pos logit contributions
arnaev+1.157
 Grassley+1.086
Station+1.065
 Straw+1.061
 Explos+1.058
Neg logit contributions
ongyang-0.920
 emanc-0.909
 sett-0.905
emis-0.896
-0.887
Tokenabe
Token ID11231
Feature activation+2.10e-01

Pos logit contributions
arnaev+5.393
 Grassley+4.883
Station+4.863
 Straw+4.801
+4.702
Neg logit contributions
ongyang-7.288
-7.096
 emanc-7.046
 sett-7.032
 immersion-6.976
Token hi
Token ID23105
Feature activation-8.16e-01

Pos logit contributions
ongyang+0.128
 emanc+0.127
 sett+0.127
emis+0.126
+0.124
Neg logit contributions
arnaev-0.187
 Grassley-0.175
Station-0.172
 Explos-0.172
 Straw-0.171
Token-
Token ID12
Feature activation-1.05e+00

Pos logit contributions
arnaev+0.670
 Grassley+0.627
Station+0.612
 Explos+0.611
 Straw+0.610
Neg logit contributions
ongyang-0.555
 emanc-0.550
 sett-0.547
emis-0.544
-0.540
Tokenfi
Token ID12463
Feature activation+5.06e-01

Pos logit contributions
arnaev+0.771
 Grassley+0.717
Station+0.701
 Explos+0.699
 Straw+0.697
Neg logit contributions
ongyang-0.799
 emanc-0.791
 sett-0.787
emis-0.785
-0.776
Token pret
Token ID2181
Feature activation-7.01e-01

Pos logit contributions
ongyang+0.309
 emanc+0.306
 sett+0.305
emis+0.302
+0.299
Neg logit contributions
arnaev-0.451
 Grassley-0.423
Station-0.415
 Explos-0.415
 Straw-0.413
Token:
Token ID25
Feature activation-9.57e-01

Pos logit contributions
ongyang+0.042
 sett+0.041
 emanc+0.041
emis+0.041
+0.040
Neg logit contributions
arnaev-0.038
 Grassley-0.036
 Explos-0.035
Station-0.035
 Straw-0.034
Tokenset
Token ID2617
Feature activation-3.20e+00

Pos logit contributions
arnaev+0.703
 Grassley+0.653
Station+0.640
 Explos+0.637
 Straw+0.635
Neg logit contributions
ongyang-0.732
 emanc-0.724
 sett-0.719
emis-0.718
-0.711
Token dir
Token ID26672
Feature activation-4.80e+00

Pos logit contributions
arnaev+2.886
 Grassley+2.717
Station+2.691
 Straw+2.679
 Explos+2.673
Neg logit contributions
ongyang-1.877
emis-1.815
 emanc-1.796
-1.794
 sett-1.757
Token=
Token ID28
Feature activation-4.87e+00

Pos logit contributions
arnaev+3.586
Station+3.334
 Grassley+3.329
 Straw+3.285
 Explos+3.276
Neg logit contributions
ongyang-3.547
 emanc-3.476
emis-3.465
 sett-3.427
-3.408
Tokenc
Token ID66
Feature activation-2.23e+00

Pos logit contributions
arnaev+3.568
Station+3.330
 Grassley+3.297
 Straw+3.245
 Explos+3.234
Neg logit contributions
ongyang-3.605
 emanc-3.575
 sett-3.519
emis-3.507
 immersion-3.480
Token\
Token ID59
Feature activation-8.53e+00

Pos logit contributions
arnaev+1.531
 Grassley+1.417
Station+1.393
 Explos+1.383
 Straw+1.378
Neg logit contributions
ongyang-1.802
 emanc-1.782
emis-1.771
 sett-1.766
-1.753
Token:\
Token ID7479
Feature activation-8.11e+00

Pos logit contributions
arnaev+6.155
Station+5.774
 Grassley+5.702
 Explos+5.605
 Straw+5.593
Neg logit contributions
ongyang-6.189
 emanc-6.018
emis-5.924
-5.920
 immersion-5.904
Tokentmp
Token ID22065
Feature activation-5.18e+00

Pos logit contributions
arnaev+5.957
Station+5.692
 Grassley+5.571
 Straw+5.526
 Explos+5.505
Neg logit contributions
ongyang-5.703
 emanc-5.587
 immersion-5.485
 sett-5.461
emis-5.452
Token:
Token ID25
Feature activation-3.82e+00

Pos logit contributions
arnaev+3.981
Station+3.718
 Grassley+3.708
 Straw+3.666
 Explos+3.661
Neg logit contributions
ongyang-3.657
emis-3.571
 emanc-3.566
-3.546
 immersion-3.539
Token */
Token ID9466
Feature activation-5.22e-01

Pos logit contributions
arnaev+2.932
 Grassley+2.720
Station+2.712
 Straw+2.672
 Explos+2.665
Neg logit contributions
ongyang-2.739
 emanc-2.697
emis-2.672
 sett-2.662
-2.646
Token This
Token ID770
Feature activation+2.78e-01

Pos logit contributions
arnaev+0.425
 Grassley+0.401
Station+0.394
 Explos+0.393
 Straw+0.392
Neg logit contributions
ongyang-0.356
 emanc-0.349
emis-0.348
 sett-0.345
-0.343
Token($
Token ID16763
Feature activation-4.92e+00

Pos logit contributions
 sett+2.764
ongyang+2.753
 emanc+2.742
+2.720
emis+2.716
Neg logit contributions
arnaev-3.625
 Grassley-3.319
 Explos-3.263
 Straw-3.220
Station-3.176
Tokens
Token ID82
Feature activation-3.40e+00

Pos logit contributions
arnaev+4.098
 Grassley+3.886
Station+3.880
 Straw+3.781
 Explos+3.763
Neg logit contributions
ongyang-3.187
 emanc-3.180
 sett-3.161
emis-3.106
 immersion-3.057
Tokenz
Token ID89
Feature activation-4.64e+00

Pos logit contributions
arnaev+1.493
Station+1.331
 Grassley+1.318
 Explos+1.259
 Straw+1.257
Neg logit contributions
 emanc-3.578
ongyang-3.574
 sett-3.531
emis-3.503
 immersion-3.490
Token1
Token ID16
Feature activation-6.53e+00

Pos logit contributions
arnaev+3.201
 Grassley+3.001
Station+2.970
 Straw+2.923
 Explos+2.904
Neg logit contributions
ongyang-3.665
 emanc-3.638
emis-3.609
 sett-3.592
 immersion-3.555
Token.
Token ID13
Feature activation-3.90e+00

Pos logit contributions
arnaev+4.686
 Grassley+4.475
Station+4.461
 Explos+4.355
 Straw+4.339
Neg logit contributions
ongyang-4.894
 emanc-4.777
emis-4.765
 sett-4.709
 immersion-4.679
TokenHeight
Token ID23106
Feature activation-8.33e+00

Pos logit contributions
arnaev+2.233
Station+2.084
 Grassley+2.073
 Straw+2.005
 Explos+2.002
Neg logit contributions
ongyang-3.553
 emanc-3.527
emis-3.485
 sett-3.480
-3.444
Token),
Token ID828
Feature activation+1.14e+00

Pos logit contributions
arnaev+5.733
Station+5.651
 Grassley+5.511
 Explos+5.470
 Straw+5.410
Neg logit contributions
ongyang-6.293
 emanc-6.096
emis-6.093
 immersion-5.964
 sett-5.942
Token$
Token ID3
Feature activation-2.67e+00

Pos logit contributions
ongyang+0.777
 emanc+0.770
 sett+0.768
emis+0.761
+0.757
Neg logit contributions
arnaev-0.935
 Grassley-0.869
 Explos-0.848
 Straw-0.843
Station-0.839
TokenSR
Token ID12562
Feature activation-9.61e-02

Pos logit contributions
arnaev+2.144
 Grassley+2.009
Station+1.976
 Explos+1.959
 Straw+1.958
Neg logit contributions
ongyang-1.850
 emanc-1.832
 sett-1.822
emis-1.812
-1.788
Token.
Token ID13
Feature activation-5.21e-01

Pos logit contributions
arnaev+0.073
 Grassley+0.068
 Explos+0.067
Station+0.067
 Straw+0.066
Neg logit contributions
ongyang-0.071
 emanc-0.070
 sett-0.070
emis-0.069
-0.069
TokenWidth
Token ID30916
Feature activation-4.90e+00

Pos logit contributions
arnaev+0.313
 Grassley+0.285
 Explos+0.276
 Straw+0.274
Station+0.274
Neg logit contributions
ongyang-0.469
 emanc-0.464
 sett-0.463
emis-0.462
-0.459
Token[
Token ID58
Feature activation+3.04e-01

Pos logit contributions
arnaev+2.267
 Grassley+2.116
Station+2.072
 Explos+2.058
 Straw+2.051
Neg logit contributions
ongyang-2.337
 emanc-2.308
 sett-2.294
emis-2.289
-2.260
Token+
Token ID10
Feature activation-7.98e-01

Pos logit contributions
ongyang+0.217
 emanc+0.214
 sett+0.214
emis+0.212
+0.211
Neg logit contributions
arnaev-0.240
 Grassley-0.223
 Explos-0.219
 Straw-0.218
Station-0.218
Token\
Token ID59
Feature activation-4.83e+00

Pos logit contributions
arnaev+0.652
 Grassley+0.611
Station+0.598
 Explos+0.597
 Straw+0.595
Neg logit contributions
ongyang-0.544
 emanc-0.538
 sett-0.535
emis-0.533
-0.527
TokenS
Token ID50
Feature activation-1.72e+00

Pos logit contributions
arnaev+3.218
 Grassley+2.991
Station+2.951
 Straw+2.892
 Explos+2.891
Neg logit contributions
ongyang-3.968
 emanc-3.927
 sett-3.888
emis-3.885
-3.841
Token+
Token ID10
Feature activation+1.04e-01

Pos logit contributions
arnaev+1.307
 Grassley+1.222
Station+1.196
 Explos+1.190
 Straw+1.187
Neg logit contributions
ongyang-1.275
 emanc-1.260
 sett-1.252
emis-1.251
-1.233
Token\
Token ID59
Feature activation-8.32e+00

Pos logit contributions
ongyang+0.068
 emanc+0.067
 sett+0.066
emis+0.066
+0.065
Neg logit contributions
arnaev-0.089
 Grassley-0.083
 Explos-0.081
Station-0.081
 Straw-0.081
Tokens
Token ID82
Feature activation-2.01e+00

Pos logit contributions
arnaev+5.156
 Grassley+4.855
Station+4.824
 Straw+4.658
 AZ+4.646
Neg logit contributions
ongyang-6.908
 emanc-6.839
emis-6.728
 sett-6.722
 immersion-6.674
Token+
Token ID10
Feature activation+3.16e-01

Pos logit contributions
arnaev+1.529
 Grassley+1.429
Station+1.399
 Explos+1.393
 Straw+1.389
Neg logit contributions
ongyang-1.483
 emanc-1.466
 sett-1.457
emis-1.454
-1.435
Token"(
Token ID18109
Feature activation-2.45e+00

Pos logit contributions
ongyang+0.181
 emanc+0.178
 sett+0.177
emis+0.175
+0.174
Neg logit contributions
arnaev-0.293
 Grassley-0.276
 Explos-0.271
Station-0.270
 Straw-0.270
Token\
Token ID59
Feature activation-6.77e+00

Pos logit contributions
arnaev+1.954
 Grassley+1.836
Station+1.809
 Explos+1.791
 Straw+1.788
Neg logit contributions
ongyang-1.715
 emanc-1.691
 sett-1.683
emis-1.679
-1.649
TokenS
Token ID50
Feature activation-3.10e+00

Pos logit contributions
arnaev+4.181
Station+3.929
 Grassley+3.920
 Explos+3.801
 Straw+3.774
Neg logit contributions
ongyang-5.768
 emanc-5.709
 sett-5.644
emis-5.610
 immersion-5.571
Token Tiff
Token ID35775
Feature activation+2.76e+00

Pos logit contributions
arnaev+1.071
 Grassley+0.990
Station+0.972
 Explos+0.967
 Straw+0.963
Neg logit contributions
ongyang-1.128
 emanc-1.119
 sett-1.113
emis-1.107
-1.096
Tokenin
Token ID259
Feature activation-8.14e-01

Pos logit contributions
ongyang+1.473
emis+1.435
 emanc+1.395
 sett+1.376
+1.342
Neg logit contributions
arnaev-2.675
 Grassley-2.529
Station-2.486
 Explos-2.477
 Straw-2.466
Token,
Token ID11
Feature activation-3.92e-01

Pos logit contributions
arnaev+0.680
 Grassley+0.634
Station+0.627
 Explos+0.623
 Straw+0.621
Neg logit contributions
ongyang-0.537
 emanc-0.531
 sett-0.527
emis-0.525
-0.520
Token Iowa
Token ID9406
Feature activation+1.15e-01

Pos logit contributions
arnaev+0.225
 Grassley+0.199
Station+0.197
 Explos+0.195
 Straw+0.193
Neg logit contributions
ongyang-0.364
 emanc-0.363
 sett-0.360
emis-0.359
-0.356
Token.
Token ID13
Feature activation-1.75e+00

Pos logit contributions
ongyang+0.083
 emanc+0.082
 sett+0.082
emis+0.081
+0.080
Neg logit contributions
arnaev-0.089
 Grassley-0.082
Station-0.082
 Explos-0.081
 Straw-0.080
Token Hide
Token ID10415
Feature activation-8.30e+00

Pos logit contributions
arnaev+1.093
 Grassley+0.997
Station+0.974
 Explos+0.968
 Straw+0.963
Neg logit contributions
ongyang-1.534
 emanc-1.520
 sett-1.514
emis-1.510
-1.498
Token Caption
Token ID11260
Feature activation-4.85e-01

Pos logit contributions
arnaev+4.555
 Grassley+4.480
Station+4.298
 AZ+4.225
 Explos+4.219
Neg logit contributions
ongyang-7.801
 emanc-7.795
 proble-7.607
emis-7.586
 immersion-7.515
Token 5
Token ID642
Feature activation-2.82e+00

Pos logit contributions
arnaev+0.363
 Grassley+0.339
Station+0.332
 Explos+0.330
 Straw+0.329
Neg logit contributions
ongyang-0.364
 emanc-0.360
 sett-0.358
emis-0.357
-0.353
Token of
Token ID286
Feature activation+1.04e+00

Pos logit contributions
arnaev+2.038
 Grassley+1.939
Station+1.910
 Straw+1.886
 Explos+1.879
Neg logit contributions
ongyang-2.194
 emanc-2.152
 sett-2.121
emis-2.120
 immersion-2.094
Token 15
Token ID1315
Feature activation-3.56e-01

Pos logit contributions
ongyang+0.736
 emanc+0.726
 sett+0.719
emis+0.718
+0.709
Neg logit contributions
arnaev-0.827
 Grassley-0.778
Station-0.760
 Explos-0.759
 Straw-0.757
Token Photos
Token ID9434
Feature activation-2.75e+00

Pos logit contributions
arnaev+0.189
 Grassley+0.169
Station+0.164
 Explos+0.162
 Straw+0.162
Neg logit contributions
ongyang-0.343
 emanc-0.340
emis-0.340
 sett-0.339
-0.337
Token at
Token ID379
Feature activation-1.55e+00

Pos logit contributions
arnaev+1.841
 Grassley+1.743
Station+1.697
 Straw+1.691
 Explos+1.684
Neg logit contributions
ongyang-1.512
 emanc-1.496
emis-1.492
 sett-1.483
-1.469
Token Sen
Token ID2311
Feature activation-9.15e-01

Pos logit contributions
arnaev+1.213
 Grassley+1.151
 Straw+1.117
Station+1.116
 Explos+1.116
Neg logit contributions
ongyang-1.095
 emanc-1.082
emis-1.080
 sett-1.071
-1.064
Token.
Token ID13
Feature activation+3.26e-02

Pos logit contributions
arnaev+0.672
 Grassley+0.627
Station+0.612
 Explos+0.609
 Straw+0.609
Neg logit contributions
ongyang-0.700
 emanc-0.694
 sett-0.689
emis-0.687
-0.680
TokenJeff
Token ID19139
Feature activation-9.57e-03

Pos logit contributions
ongyang+0.024
 sett+0.023
 emanc+0.023
emis+0.023
 immersion+0.023
Neg logit contributions
arnaev-0.025
 Grassley-0.023
Station-0.023
 Explos-0.023
 Straw-0.023
Token Flake
Token ID39727
Feature activation-2.33e+00

Pos logit contributions
arnaev+0.006
 Grassley+0.005
Station+0.005
 Explos+0.005
 Straw+0.005
Neg logit contributions
ongyang-0.009
 emanc-0.009
 sett-0.009
emis-0.009
-0.009
Token(
Token ID7
Feature activation-8.30e+00

Pos logit contributions
arnaev+1.874
 Grassley+1.780
 Straw+1.727
Station+1.723
 Explos+1.721
Neg logit contributions
ongyang-1.601
 emanc-1.592
 sett-1.579
emis-1.578
-1.554
TokenR
Token ID49
Feature activation-4.33e+00

Pos logit contributions
arnaev+3.981
 Grassley+3.837
 AZ+3.817
Station+3.702
 Straw+3.672
Neg logit contributions
ongyang-8.199
 emanc-8.134
 sett-8.031
emis-7.997
 immersion-7.855
Token-
Token ID12
Feature activation-4.53e+00

Pos logit contributions
arnaev+3.394
 Grassley+3.179
Station+3.113
 Straw+3.106
 Explos+3.101
Neg logit contributions
ongyang-3.067
 emanc-3.040
 sett-3.018
emis-3.009
-2.979
TokenAri
Token ID26529
Feature activation-3.10e+00

Pos logit contributions
arnaev+1.071
 Grassley+0.887
Station+0.841
 AZ+0.815
 Straw+0.813
Neg logit contributions
ongyang-5.688
 emanc-5.642
 sett-5.613
emis-5.593
 immersion-5.543
Tokenz
Token ID89
Feature activation-7.24e+00

Pos logit contributions
arnaev+1.367
 Grassley+1.249
Station+1.201
 Straw+1.193
 Explos+1.191
Neg logit contributions
 emanc-3.232
ongyang-3.227
-3.216
 sett-3.208
emis-3.176
Token.)
Token ID2014
Feature activation-3.73e+00

Pos logit contributions
arnaev+4.090
 Grassley+3.787
 Straw+3.652
Station+3.632
 AZ+3.603
Neg logit contributions
 emanc-6.564
ongyang-6.557
 sett-6.446
-6.424
emis-6.376
Token.,
Token ID1539
Feature activation+4.05e+00

Pos logit contributions
arnaev+4.171
 Grassley+3.808
 Explos+3.703
 Straw+3.692
Station+3.676
Neg logit contributions
 emanc-6.786
 sett-6.713
ongyang-6.692
-6.614
 immersion-6.598
Token Ross
Token ID9847
Feature activation-1.01e+00

Pos logit contributions
emis+2.974
 sett+2.971
ongyang+2.942
 emanc+2.930
+2.910
Neg logit contributions
arnaev-3.025
Station-2.719
 Grassley-2.659
 Explos-2.628
 Straw-2.562
Token,
Token ID11
Feature activation-2.23e+00

Pos logit contributions
arnaev+0.839
 Grassley+0.787
Station+0.773
 Explos+0.770
 Straw+0.766
Neg logit contributions
ongyang-0.671
 emanc-0.662
emis-0.658
 sett-0.658
-0.648
Token S
Token ID311
Feature activation-6.47e+00

Pos logit contributions
arnaev+1.549
 Grassley+1.465
 Explos+1.422
 Straw+1.420
Station+1.418
Neg logit contributions
ongyang-1.797
 emanc-1.769
emis-1.758
 sett-1.753
-1.730
Token.
Token ID13
Feature activation-5.45e+00

Pos logit contributions
arnaev+4.133
 Grassley+3.776
Station+3.652
 Straw+3.648
 Explos+3.645
Neg logit contributions
 emanc-5.434
 sett-5.386
ongyang-5.356
emis-5.271
-5.270
Token W
Token ID370
Feature activation-8.20e+00

Pos logit contributions
arnaev+3.663
 Grassley+3.600
 Explos+3.513
 Straw+3.499
 AZ+3.456
Neg logit contributions
ongyang-4.442
 emanc-4.335
emis-4.292
 sett-4.251
 immersion-4.234
Token.,
Token ID1539
Feature activation+4.71e+00

Pos logit contributions
arnaev+4.766
 Grassley+4.372
 Straw+4.258
 Explos+4.245
Station+4.242
Neg logit contributions
 emanc-7.163
 sett-7.087
ongyang-7.057
 immersion-6.958
-6.949
Token Is
Token ID1148
Feature activation+1.33e+00

Pos logit contributions
emis+3.451
 sett+3.446
ongyang+3.403
 emanc+3.395
+3.379
Neg logit contributions
arnaev-3.495
Station-3.128
 Grassley-3.046
 Explos-3.016
ufact-2.939
Tokenava
Token ID4170
Feature activation+1.19e+00

Pos logit contributions
ongyang+0.966
emis+0.954
 sett+0.941
 emanc+0.937
+0.920
Neg logit contributions
arnaev-1.024
 Grassley-0.968
 Explos-0.948
Station-0.947
 Straw-0.939
Token,
Token ID11
Feature activation-1.88e+00

Pos logit contributions
ongyang+0.765
emis+0.763
 emanc+0.756
 sett+0.750
+0.743
Neg logit contributions
arnaev-1.017
 Grassley-0.951
Station-0.938
 Explos-0.931
 Straw-0.926
Token D
Token ID360
Feature activation-5.83e+00

Pos logit contributions
arnaev+1.336
 Grassley+1.255
 Explos+1.220
Station+1.220
 Straw+1.218
Neg logit contributions
ongyang-1.486
 emanc-1.465
emis-1.456
 sett-1.454
-1.436
Tokenset
Token ID2617
Feature activation-3.20e+00

Pos logit contributions
arnaev+0.703
 Grassley+0.653
Station+0.640
 Explos+0.637
 Straw+0.635
Neg logit contributions
ongyang-0.732
 emanc-0.724
 sett-0.719
emis-0.718
-0.711
Token dir
Token ID26672
Feature activation-4.80e+00

Pos logit contributions
arnaev+2.886
 Grassley+2.717
Station+2.691
 Straw+2.679
 Explos+2.673
Neg logit contributions
ongyang-1.877
emis-1.815
 emanc-1.796
-1.794
 sett-1.757
Token=
Token ID28
Feature activation-4.87e+00

Pos logit contributions
arnaev+3.586
Station+3.334
 Grassley+3.329
 Straw+3.285
 Explos+3.276
Neg logit contributions
ongyang-3.547
 emanc-3.476
emis-3.465
 sett-3.427
-3.408
Tokenc
Token ID66
Feature activation-2.23e+00

Pos logit contributions
arnaev+3.568
Station+3.330
 Grassley+3.297
 Straw+3.245
 Explos+3.234
Neg logit contributions
ongyang-3.605
 emanc-3.575
 sett-3.519
emis-3.507
 immersion-3.480
Token\
Token ID59
Feature activation-8.53e+00

Pos logit contributions
arnaev+1.531
 Grassley+1.417
Station+1.393
 Explos+1.383
 Straw+1.378
Neg logit contributions
ongyang-1.802
 emanc-1.782
emis-1.771
 sett-1.766
-1.753
Token:\
Token ID7479
Feature activation-8.11e+00

Pos logit contributions
arnaev+6.155
Station+5.774
 Grassley+5.702
 Explos+5.605
 Straw+5.593
Neg logit contributions
ongyang-6.189
 emanc-6.018
emis-5.924
-5.920
 immersion-5.904
Tokentmp
Token ID22065
Feature activation-5.18e+00

Pos logit contributions
arnaev+5.957
Station+5.692
 Grassley+5.571
 Straw+5.526
 Explos+5.505
Neg logit contributions
ongyang-5.703
 emanc-5.587
 immersion-5.485
 sett-5.461
emis-5.452
Token:
Token ID25
Feature activation-3.82e+00

Pos logit contributions
arnaev+3.981
Station+3.718
 Grassley+3.708
 Straw+3.666
 Explos+3.661
Neg logit contributions
ongyang-3.657
emis-3.571
 emanc-3.566
-3.546
 immersion-3.539
Token */
Token ID9466
Feature activation-5.22e-01

Pos logit contributions
arnaev+2.932
 Grassley+2.720
Station+2.712
 Straw+2.672
 Explos+2.665
Neg logit contributions
ongyang-2.739
 emanc-2.697
emis-2.672
 sett-2.662
-2.646
Token This
Token ID770
Feature activation+2.78e-01

Pos logit contributions
arnaev+0.425
 Grassley+0.401
Station+0.394
 Explos+0.393
 Straw+0.392
Neg logit contributions
ongyang-0.356
 emanc-0.349
emis-0.348
 sett-0.345
-0.343
Token sets
Token ID5621
Feature activation+1.56e-01

Pos logit contributions
ongyang+0.178
 emanc+0.175
 sett+0.174
emis+0.174
+0.172
Neg logit contributions
arnaev-0.240
 Grassley-0.225
Station-0.221
 Explos-0.221
 Straw-0.220
Token.
Token ID13
Feature activation-5.67e+00

Pos logit contributions
arnaev+4.282
 Grassley+3.880
Station+3.759
 Straw+3.755
 Explos+3.743
Neg logit contributions
 emanc-5.968
 sett-5.913
ongyang-5.849
-5.792
 immersion-5.787
Token S
Token ID311
Feature activation-4.22e+00

Pos logit contributions
arnaev+3.860
 Grassley+3.797
 Explos+3.698
 Straw+3.690
 AZ+3.656
Neg logit contributions
ongyang-4.558
 emanc-4.448
emis-4.406
 sett-4.366
 immersion-4.346
Token.,
Token ID1539
Feature activation+5.20e+00

Pos logit contributions
arnaev+2.564
 Grassley+2.347
Station+2.267
 Explos+2.264
 Straw+2.260
Neg logit contributions
 emanc-3.713
ongyang-3.699
 sett-3.684
emis-3.641
-3.617
Token Bates
Token ID35591
Feature activation+3.33e-01

Pos logit contributions
 sett+3.821
emis+3.818
 emanc+3.752
ongyang+3.749
+3.748
Neg logit contributions
arnaev-3.811
Station-3.411
 Grassley-3.302
 Explos-3.282
ufact-3.218
Token,
Token ID11
Feature activation-3.42e+00

Pos logit contributions
ongyang+0.220
 emanc+0.217
emis+0.217
 sett+0.216
+0.213
Neg logit contributions
arnaev-0.278
 Grassley-0.261
Station-0.257
 Explos-0.255
 Straw-0.254
Token J
Token ID449
Feature activation-8.05e+00

Pos logit contributions
arnaev+2.313
 Grassley+2.220
 Straw+2.149
 Explos+2.149
Station+2.131
Neg logit contributions
ongyang-2.801
 emanc-2.744
emis-2.733
 sett-2.712
 immersion-2.680
Token.
Token ID13
Feature activation-5.68e+00

Pos logit contributions
arnaev+4.992
 Grassley+4.530
 Straw+4.413
Station+4.393
 Explos+4.340
Neg logit contributions
 emanc-6.772
 sett-6.733
ongyang-6.640
 torped-6.548
 immersion-6.544
Token E
Token ID412
Feature activation-6.41e+00

Pos logit contributions
arnaev+3.769
 Grassley+3.709
 Explos+3.611
 Straw+3.608
 AZ+3.570
Neg logit contributions
ongyang-4.667
 emanc-4.544
emis-4.510
 sett-4.469
 immersion-4.444
Token.
Token ID13
Feature activation-5.11e+00

Pos logit contributions
arnaev+3.881
 Grassley+3.596
 Straw+3.470
 Explos+3.457
Station+3.454
Neg logit contributions
 emanc-5.517
ongyang-5.461
 sett-5.458
emis-5.372
-5.372
Token (
Token ID357
Feature activation+3.35e+00

Pos logit contributions
arnaev+3.929
 Grassley+3.765
 Explos+3.683
 Straw+3.674
Station+3.629
Neg logit contributions
ongyang-3.681
 emanc-3.636
 sett-3.589
emis-3.567
 immersion-3.537
Token 1997
Token ID8309
Feature activation-1.99e+00

Pos logit contributions
 sett+2.797
 emanc+2.790
+2.787
emis+2.775
ongyang+2.767
Neg logit contributions
arnaev-2.188
 Grassley-1.932
Station-1.902
 Explos-1.891
 Straw-1.871
Token P
Token ID350
Feature activation-4.76e+00

Pos logit contributions
arnaev+1.315
 Grassley+1.228
Station+1.195
 Explos+1.194
 Straw+1.192
Neg logit contributions
ongyang-1.489
 emanc-1.471
 sett-1.462
emis-1.461
-1.443
Token.,
Token ID1539
Feature activation+4.84e+00

Pos logit contributions
arnaev+3.103
 Grassley+2.859
Station+2.778
 Straw+2.776
 Explos+2.775
Neg logit contributions
 emanc-3.969
ongyang-3.952
 sett-3.945
emis-3.888
-3.873
Token Pick
Token ID12346
Feature activation-1.20e+00

Pos logit contributions
emis+3.565
 sett+3.546
ongyang+3.512
+3.489
 emanc+3.489
Neg logit contributions
arnaev-3.557
Station-3.198
 Grassley-3.099
 Explos-3.071
ufact-3.014
Tokenett
Token ID3087
Feature activation-2.01e+00

Pos logit contributions
arnaev+0.880
 Grassley+0.818
Station+0.801
 Explos+0.798
 Straw+0.794
Neg logit contributions
ongyang-0.919
 emanc-0.908
emis-0.904
 sett-0.903
-0.891
Token,
Token ID11
Feature activation-2.79e+00

Pos logit contributions
arnaev+1.633
 Grassley+1.530
Station+1.497
 Explos+1.495
 Straw+1.492
Neg logit contributions
ongyang-1.379
 emanc-1.364
 sett-1.355
emis-1.349
-1.334
Token W
Token ID370
Feature activation-8.04e+00

Pos logit contributions
arnaev+1.915
 Grassley+1.818
 Explos+1.763
 Straw+1.762
Station+1.756
Neg logit contributions
ongyang-2.265
 emanc-2.226
emis-2.215
 sett-2.203
-2.177
Token.,
Token ID1539
Feature activation+4.74e+00

Pos logit contributions
arnaev+4.903
 Grassley+4.490
 Explos+4.363
 Straw+4.361
Station+4.360
Neg logit contributions
 emanc-6.834
 sett-6.777
ongyang-6.719
-6.635
 immersion-6.620
Token H
Token ID367
Feature activation-1.50e-01

Pos logit contributions
emis+3.476
 sett+3.465
ongyang+3.425
 emanc+3.409
+3.406
Neg logit contributions
arnaev-3.507
Station-3.140
 Grassley-3.049
 Explos-3.020
ufact-2.963
Tokenarel
Token ID20318
Feature activation+8.13e-01

Pos logit contributions
arnaev+0.124
 Grassley+0.116
Station+0.114
 Explos+0.113
 Straw+0.113
Neg logit contributions
ongyang-0.101
 emanc-0.100
emis-0.099
 sett-0.099
-0.098
Token-
Token ID12
Feature activation+3.76e+00

Pos logit contributions
ongyang+0.535
emis+0.533
 emanc+0.533
 sett+0.530
+0.522
Neg logit contributions
arnaev-0.681
 Grassley-0.634
Station-0.623
 Explos-0.619
 Straw-0.617
TokenF
Token ID37
Feature activation+3.88e-01

Pos logit contributions
+2.737
emis+2.735
ongyang+2.712
 sett+2.709
 emanc+2.675
Neg logit contributions
arnaev-2.853
 Grassley-2.621
 Explos-2.572
 Straw-2.516
 AZ-2.512
Tokengb
Token ID22296
Feature activation+5.23e-01

Pos logit contributions
ongyang+1.582
emis+1.547
 emanc+1.547
+1.536
 sett+1.530
Neg logit contributions
arnaev-2.263
 Grassley-2.112
 Explos-2.106
 Straw-2.086
Station-2.072
Token($
Token ID16763
Feature activation-2.39e+00

Pos logit contributions
ongyang+0.360
 emanc+0.355
 sett+0.353
+0.351
emis+0.351
Neg logit contributions
arnaev-0.427
 Grassley-0.396
 Explos-0.387
 Straw-0.385
Station-0.383
TokenFC
Token ID4851
Feature activation-4.26e+00

Pos logit contributions
arnaev+1.351
 Grassley+1.230
Station+1.196
 Explos+1.187
 Straw+1.184
Neg logit contributions
ongyang-2.236
 emanc-2.218
 sett-2.209
emis-2.203
-2.181
Token1
Token ID16
Feature activation-1.78e+00

Pos logit contributions
arnaev+3.035
 Grassley+2.825
Station+2.806
 Straw+2.746
 Explos+2.736
Neg logit contributions
ongyang-3.303
 emanc-3.275
 sett-3.254
emis-3.227
 immersion-3.200
Token[
Token ID58
Feature activation-1.54e+00

Pos logit contributions
arnaev+1.334
 Grassley+1.242
Station+1.214
 Explos+1.211
 Straw+1.208
Neg logit contributions
ongyang-1.339
 emanc-1.324
 sett-1.317
emis-1.314
-1.300
Token0
Token ID15
Feature activation-8.03e+00

Pos logit contributions
arnaev+1.218
 Grassley+1.136
 Explos+1.111
Station+1.110
 Straw+1.106
Neg logit contributions
ongyang-1.100
 emanc-1.087
 sett-1.082
emis-1.079
-1.068
Token],
Token ID4357
Feature activation+3.03e+00

Pos logit contributions
arnaev+7.744
 Grassley+7.493
Station+7.430
 Explos+7.376
 AZ+7.339
Neg logit contributions
ongyang-3.821
 emanc-3.807
emis-3.711
 immersion-3.638
 sett-3.634
Token$
Token ID3
Feature activation-3.80e+00

Pos logit contributions
ongyang+1.756
 emanc+1.740
+1.732
 sett+1.725
emis+1.721
Neg logit contributions
arnaev-2.769
 Grassley-2.571
 Explos-2.530
 Straw-2.491
Station-2.472
TokenFC
Token ID4851
Feature activation-4.03e+00

Pos logit contributions
arnaev+2.463
 Grassley+2.283
Station+2.258
 Straw+2.211
 Explos+2.203
Neg logit contributions
ongyang-3.191
 emanc-3.175
 sett-3.168
emis-3.138
 immersion-3.095
Token1
Token ID16
Feature activation-3.43e-02

Pos logit contributions
arnaev+2.607
Station+2.523
 Grassley+2.494
 Straw+2.416
 Explos+2.381
Neg logit contributions
ongyang-3.376
 emanc-3.350
emis-3.280
 sett-3.279
 immersion-3.271
Token[
Token ID58
Feature activation-1.08e+00

Pos logit contributions
arnaev+0.025
 Grassley+0.024
 Explos+0.023
Station+0.023
 Straw+0.023
Neg logit contributions
ongyang-0.026
 emanc-0.026
 sett-0.026
emis-0.026
-0.025
Tokenle
Token ID293
Feature activation-2.02e+00

Pos logit contributions
arnaev+0.772
 Grassley+0.727
Station+0.714
 Explos+0.712
 Straw+0.711
Neg logit contributions
ongyang-0.537
 emanc-0.530
 sett-0.527
emis-0.525
-0.518
Token $
Token ID720
Feature activation-3.05e+00

Pos logit contributions
arnaev+1.701
 Grassley+1.609
Station+1.579
 Straw+1.578
 Explos+1.569
Neg logit contributions
ongyang-1.319
 emanc-1.289
emis-1.277
 sett-1.271
-1.266
Tokenart
Token ID433
Feature activation-1.53e-01

Pos logit contributions
arnaev+2.615
 Grassley+2.462
Station+2.437
 Straw+2.402
 Explos+2.401
Neg logit contributions
ongyang-1.934
 emanc-1.916
 sett-1.906
emis-1.879
-1.849
Tokenext
Token ID2302
Feature activation-1.30e+00

Pos logit contributions
arnaev+0.102
 Grassley+0.094
Station+0.092
 Explos+0.091
 Straw+0.091
Neg logit contributions
ongyang-0.127
 emanc-0.126
 sett-0.125
emis-0.125
-0.124
Token.
Token ID13
Feature activation-3.73e+00

Pos logit contributions
arnaev+1.071
 Grassley+1.004
Station+0.984
 Explos+0.982
 Straw+0.979
Neg logit contributions
ongyang-0.883
 emanc-0.873
 sett-0.868
emis-0.865
-0.855
TokenCount
Token ID12332
Feature activation-7.87e+00

Pos logit contributions
arnaev+2.433
Station+2.264
 Grassley+2.245
 Straw+2.197
 Explos+2.189
Neg logit contributions
ongyang-3.110
 emanc-3.086
 sett-3.064
emis-3.030
-3.001
Token ;
Token ID2162
Feature activation-1.31e+00

Pos logit contributions
arnaev+5.553
Station+5.285
 Grassley+5.276
 Straw+5.110
 Explos+5.083
Neg logit contributions
ongyang-5.966
 emanc-5.836
emis-5.773
 sett-5.743
 immersion-5.697
Token $
Token ID720
Feature activation-5.29e-01

Pos logit contributions
arnaev+1.194
 Grassley+1.127
Station+1.107
 Explos+1.104
 Straw+1.102
Neg logit contributions
ongyang-0.777
 emanc-0.766
 sett-0.761
emis-0.758
-0.747
Tokeni
Token ID72
Feature activation-7.08e-01

Pos logit contributions
arnaev+0.485
 Grassley+0.458
 Explos+0.449
Station+0.449
 Straw+0.448
Neg logit contributions
ongyang-0.308
 emanc-0.304
 sett-0.302
emis-0.302
-0.297
Token++)
Token ID29577
Feature activation-9.58e-02

Pos logit contributions
arnaev+0.576
 Grassley+0.538
Station+0.527
 Explos+0.526
 Straw+0.525
Neg logit contributions
ongyang-0.486
 emanc-0.481
 sett-0.479
emis-0.478
-0.472
Token {
Token ID1391
Feature activation-2.52e-01

Pos logit contributions
arnaev+0.093
 Grassley+0.088
Station+0.086
 Explos+0.086
 Straw+0.086
Neg logit contributions
ongyang-0.051
 emanc-0.050
 sett-0.050
emis-0.049
-0.049
Token x
Token ID2124
Feature activation+5.04e-01

Pos logit contributions
 sett+2.411
 emanc+2.381
emis+2.361
ongyang+2.359
+2.353
Neg logit contributions
arnaev-3.062
 Grassley-2.754
Station-2.719
 Explos-2.699
 Straw-2.688
Token.
Token ID13
Feature activation-1.68e+00

Pos logit contributions
ongyang+0.375
 emanc+0.372
 sett+0.371
emis+0.369
+0.367
Neg logit contributions
arnaev-0.380
 Grassley-0.352
 Explos-0.344
Station-0.344
 Straw-0.343
Tokenx
Token ID87
Feature activation-9.57e-01

Pos logit contributions
arnaev+1.008
 Grassley+0.940
Station+0.927
 Straw+0.911
 Explos+0.908
Neg logit contributions
ongyang-1.496
 emanc-1.488
 sett-1.472
 immersion-1.458
emis-1.456
Token.
Token ID13
Feature activation-1.23e+00

Pos logit contributions
arnaev+0.686
 Grassley+0.644
Station+0.631
 Explos+0.625
 Straw+0.625
Neg logit contributions
ongyang-0.748
 emanc-0.740
 sett-0.733
emis-0.732
-0.720
Tokenx
Token ID87
Feature activation-3.80e+00

Pos logit contributions
arnaev+0.750
 Grassley+0.697
Station+0.686
 Explos+0.675
 Straw+0.675
Neg logit contributions
ongyang-1.086
 emanc-1.082
 sett-1.072
emis-1.060
 immersion-1.058
Token.
Token ID13
Feature activation-7.73e+00

Pos logit contributions
arnaev+2.488
 Grassley+2.361
Station+2.344
 Explos+2.270
 Straw+2.266
Neg logit contributions
ongyang-3.174
 emanc-3.141
 sett-3.103
emis-3.083
 proble-3.075
Token167
Token ID21940
Feature activation-6.38e-01

Pos logit contributions
arnaev+4.668
Station+4.455
+4.351
pn+4.337
 Grassley+4.321
Neg logit contributions
 sett-6.361
 proble-6.354
ongyang-6.296
 sty-6.291
ixel-6.246
Token 101
Token ID8949
Feature activation+1.47e+00

Pos logit contributions
arnaev+0.537
 Grassley+0.504
Station+0.495
 Explos+0.493
 Straw+0.492
Neg logit contributions
ongyang-0.419
 emanc-0.414
 sett-0.412
emis-0.410
-0.405
Token320
Token ID19504
Feature activation+4.47e+00

Pos logit contributions
+1.026
 sett+1.012
emis+1.000
 emanc+0.999
ongyang+0.996
Neg logit contributions
arnaev-1.181
 Grassley-1.076
 Explos-1.053
 Straw-1.046
Station-1.035
Token6
Token ID21
Feature activation+5.45e+00

Pos logit contributions
 sett+2.898
 emanc+2.834
+2.825
emis+2.767
 fid+2.755
Neg logit contributions
arnaev-3.804
 Grassley-3.370
Station-3.353
 Explos-3.320
 Straw-3.309
Token x
Token ID2124
Feature activation+1.80e+00

Pos logit contributions
 sett+3.439
 emanc+3.364
emis+3.329
+3.327
ongyang+3.301
Neg logit contributions
arnaev-4.776
 Grassley-4.235
Station-4.207
ufact-4.196
 Explos-4.168
Token =
Token ID796
Feature activation+2.43e+00

Pos logit contributions
arnaev+0.077
 Grassley+0.072
 Explos+0.070
Station+0.070
 Straw+0.070
Neg logit contributions
ongyang-0.065
 emanc-0.064
 sett-0.064
emis-0.064
-0.063
Token ($
Token ID7198
Feature activation-1.48e+00

Pos logit contributions
 emanc+1.575
 sett+1.572
ongyang+1.566
emis+1.536
 immersion+1.531
Neg logit contributions
arnaev-2.074
 Grassley-1.924
Station-1.883
 Explos-1.870
 Straw-1.853
Tokentext
Token ID5239
Feature activation-2.06e+00

Pos logit contributions
arnaev+1.101
 Grassley+1.025
Station+1.004
 Explos+1.000
 Straw+0.997
Neg logit contributions
ongyang-1.120
 emanc-1.108
 sett-1.102
emis-1.099
-1.086
Token -
Token ID532
Feature activation-2.66e+00

Pos logit contributions
arnaev+1.576
 Grassley+1.473
Station+1.447
 Explos+1.437
 Straw+1.435
Neg logit contributions
ongyang-1.502
 emanc-1.486
 sett-1.475
emis-1.471
-1.457
Tokensplit
Token ID35312
Feature activation-2.39e+00

Pos logit contributions
arnaev+2.030
 Grassley+1.911
Station+1.889
 Explos+1.868
 Straw+1.859
Neg logit contributions
ongyang-1.945
 emanc-1.908
 sett-1.899
emis-1.899
-1.877
Token "\
Token ID37082
Feature activation-7.72e+00

Pos logit contributions
arnaev+1.920
 Grassley+1.799
Station+1.763
 Explos+1.757
 Straw+1.753
Neg logit contributions
ongyang-1.664
 emanc-1.644
 sett-1.634
emis-1.631
-1.610
Tokenr
Token ID81
Feature activation-6.75e-01

Pos logit contributions
arnaev+5.737
Station+5.419
 Grassley+5.370
 Straw+5.282
 Explos+5.257
Neg logit contributions
ongyang-5.552
 emanc-5.503
 sett-5.428
emis-5.356
 immersion-5.324
Token
Token ID198
Feature activation+2.67e+00

Pos logit contributions
arnaev+0.566
 Grassley+0.531
Station+0.520
 Explos+0.519
 Straw+0.518
Neg logit contributions
ongyang-0.447
 emanc-0.441
 sett-0.439
emis-0.437
-0.432
Token
Token ID198
Feature activation+2.98e+00

Pos logit contributions
ongyang+1.650
 sett+1.640
emis+1.640
+1.636
 emanc+1.626
Neg logit contributions
arnaev-2.335
 Grassley-2.155
 Explos-2.122
 Straw-2.109
Station-2.093
Token")
Token ID4943
Feature activation-9.36e-01

Pos logit contributions
ongyang+1.701
emis+1.670
 emanc+1.665
+1.663
 sett+1.651
Neg logit contributions
arnaev-2.749
 Grassley-2.594
 Explos-2.551
 Straw-2.533
Station-2.489
Token $
Token ID720
Feature activation-2.36e+00

Pos logit contributions
arnaev+0.770
 Grassley+0.720
Station+0.705
 Explos+0.704
 Straw+0.702
Neg logit contributions
ongyang-0.634
 emanc-0.628
 sett-0.625
emis-0.621
-0.614
Token",
Token ID1600
Feature activation+1.59e+00

Pos logit contributions
arnaev+3.046
 Grassley+2.888
Station+2.855
 Explos+2.838
 Straw+2.832
Neg logit contributions
ongyang-2.106
 emanc-2.091
emis-2.067
 sett-2.063
-2.027
Token {
Token ID1391
Feature activation+1.01e+00

Pos logit contributions
ongyang+0.874
 emanc+0.868
 sett+0.865
emis+0.856
+0.850
Neg logit contributions
arnaev-1.509
 Grassley-1.417
Station-1.392
 Explos-1.389
 Straw-1.382
Token9
Token ID24
Feature activation+9.21e-01

Pos logit contributions
ongyang+0.720
 emanc+0.711
 sett+0.709
emis+0.708
+0.707
Neg logit contributions
arnaev-0.796
 Grassley-0.740
 Explos-0.723
 Straw-0.721
Station-0.719
Token,
Token ID11
Feature activation+2.19e+00

Pos logit contributions
ongyang+0.601
 emanc+0.594
 sett+0.594
emis+0.592
+0.589
Neg logit contributions
arnaev-0.778
 Grassley-0.723
 Explos-0.710
 Straw-0.706
Station-0.706
Token 15
Token ID1315
Feature activation-2.25e+00

Pos logit contributions
 sett+1.387
 emanc+1.382
ongyang+1.373
emis+1.363
+1.362
Neg logit contributions
arnaev-1.889
 Grassley-1.744
Station-1.711
 Explos-1.699
 Straw-1.697
Token}
Token ID92
Feature activation+4.87e+00

Pos logit contributions
arnaev+1.776
 Grassley+1.690
Station+1.669
 Straw+1.653
 Explos+1.637
Neg logit contributions
ongyang-1.583
 emanc-1.562
 sett-1.536
emis-1.535
 immersion-1.522
Token ->
Token ID4613
Feature activation+8.76e-01

Pos logit contributions
 sett+2.958
emis+2.910
 emanc+2.903
ongyang+2.891
+2.881
Neg logit contributions
arnaev-4.359
 Grassley-3.948
Station-3.876
 Explos-3.867
 Straw-3.858
Token "
Token ID366
Feature activation-3.02e+00

Pos logit contributions
ongyang+0.541
 emanc+0.534
 sett+0.532
emis+0.529
+0.523
Neg logit contributions
arnaev-0.772
 Grassley-0.725
Station-0.712
 Explos-0.710
 Straw-0.708
TokenS
Token ID50
Feature activation-2.92e+00

Pos logit contributions
arnaev+1.992
 Grassley+1.844
Station+1.818
 Explos+1.794
 Straw+1.791
Neg logit contributions
ongyang-2.524
 emanc-2.504
 sett-2.484
emis-2.480
-2.448
Token",
Token ID1600
Feature activation+2.08e+00

Pos logit contributions
arnaev+2.595
 Grassley+2.458
Station+2.427
 Explos+2.414
 Straw+2.409
Neg logit contributions
ongyang-1.758
 emanc-1.742
emis-1.722
 sett-1.720
-1.690
Token {
Token ID1391
Feature activation+2.78e+00

Pos logit contributions
ongyang+1.124
 emanc+1.115
 sett+1.113
emis+1.103
+1.095
Neg logit contributions
arnaev-1.987
 Grassley-1.867
Station-1.832
 Explos-1.831
 Straw-1.820
Token kind
Token ID1611
Feature activation+1.27e+00

Pos logit contributions
 emanc+0.657
ongyang+0.653
 sett+0.651
emis+0.641
 immersion+0.637
Neg logit contributions
arnaev-1.002
 Grassley-0.936
Station-0.923
 Explos-0.918
 Straw-0.916
Token of
Token ID286
Feature activation-1.72e+00

Pos logit contributions
ongyang+0.874
 emanc+0.870
 sett+0.866
emis+0.861
+0.853
Neg logit contributions
arnaev-1.024
 Grassley-0.951
 Explos-0.933
Station-0.930
 Straw-0.928
Token an
Token ID281
Feature activation-9.59e-01

Pos logit contributions
arnaev+1.456
 Grassley+1.379
Station+1.349
 Explos+1.348
 Straw+1.344
Neg logit contributions
ongyang-1.125
emis-1.097
 emanc-1.096
 sett-1.092
-1.080
Token out
Token ID503
Feature activation-1.11e+00

Pos logit contributions
arnaev+0.849
 Grassley+0.806
 Explos+0.791
Station+0.790
 Straw+0.787
Neg logit contributions
ongyang-0.584
 sett-0.568
 emanc-0.568
emis-0.568
-0.560
Token of
Token ID286
Feature activation+4.20e-01

Pos logit contributions
arnaev+0.883
 Grassley+0.831
Station+0.813
 Explos+0.810
 Straw+0.809
Neg logit contributions
ongyang-0.782
 emanc-0.771
 sett-0.766
emis-0.766
-0.756
Token body
Token ID1767
Feature activation+7.57e+00

Pos logit contributions
 emanc+0.277
 sett+0.275
ongyang+0.275
 immersion+0.271
emis+0.270
Neg logit contributions
arnaev-0.355
 Grassley-0.326
 Explos-0.324
Station-0.323
 Straw-0.320
Token experience
Token ID1998
Feature activation+1.70e+00

Pos logit contributions
 immersion+3.283
 sett+3.205
 emanc+3.041
ongyang+2.935
 torped+2.898
Neg logit contributions
arnaev-8.241
Station-7.616
 Grassley-7.578
 Straw-7.537
 Explos-7.450
Token.
Token ID13
Feature activation+3.44e-01

Pos logit contributions
 emanc+1.182
 sett+1.180
ongyang+1.175
emis+1.164
 immersion+1.160
Neg logit contributions
arnaev-1.373
 Grassley-1.261
 Explos-1.243
Station-1.239
 Straw-1.237
Token
Token ID447
Feature activation+1.01e+00

Pos logit contributions
ongyang+0.226
 sett+0.224
 emanc+0.224
+0.223
emis+0.223
Neg logit contributions
arnaev-0.289
 Grassley-0.265
Station-0.261
 Explos-0.260
 Straw-0.259
Token
Token ID251
Feature activation-7.31e-02

Pos logit contributions
ongyang+0.600
 emanc+0.588
 sett+0.586
emis+0.586
+0.581
Neg logit contributions
arnaev-0.909
 Grassley-0.849
Station-0.839
 Explos-0.838
 Straw-0.832
Token<|endoftext|>
Token ID50256
Feature activation+2.14e-01

Pos logit contributions
arnaev+0.060
 Grassley+0.056
Station+0.055
 Explos+0.055
 Straw+0.055
Neg logit contributions
ongyang-0.049
 emanc-0.049
 sett-0.049
emis-0.048
-0.048
Token help
Token ID1037
Feature activation-4.30e-01

Pos logit contributions
 emanc+1.341
 sett+1.340
ongyang+1.340
emis+1.312
 immersion+1.310
Neg logit contributions
arnaev-2.045
 Grassley-1.891
Station-1.881
 Explos-1.867
 Straw-1.858
Token center
Token ID3641
Feature activation+7.74e-01

Pos logit contributions
arnaev+0.367
 Grassley+0.343
 Explos+0.337
Station+0.336
 Straw+0.335
Neg logit contributions
ongyang-0.279
 emanc-0.276
 sett-0.275
emis-0.274
-0.269
Token where
Token ID810
Feature activation+5.71e-01

Pos logit contributions
ongyang+0.528
 emanc+0.528
 sett+0.527
emis+0.521
 immersion+0.514
Neg logit contributions
arnaev-0.630
 Grassley-0.583
 Explos-0.576
Station-0.576
 Straw-0.571
Token Americans
Token ID3399
Feature activation+3.81e-01

Pos logit contributions
 emanc+0.372
ongyang+0.372
 sett+0.371
emis+0.367
+0.361
Neg logit contributions
arnaev-0.482
 Grassley-0.447
 Explos-0.442
Station-0.442
 Straw-0.437
Token can
Token ID460
Feature activation+2.70e+00

Pos logit contributions
ongyang+0.244
 emanc+0.243
 sett+0.241
emis+0.239
+0.236
Neg logit contributions
arnaev-0.328
 Grassley-0.305
Station-0.301
 Explos-0.300
 Straw-0.299
Token lodge
Token ID35362
Feature activation+5.19e+00

Pos logit contributions
 emanc+1.627
 sett+1.603
emis+1.566
ongyang+1.560
 immersion+1.542
Neg logit contributions
arnaev-2.472
 Grassley-2.264
Station-2.257
 Explos-2.254
 Straw-2.227
Token complaints
Token ID9687
Feature activation+7.87e-01

Pos logit contributions
 sett+2.607
 emanc+2.597
 immersion+2.495
 fid+2.451
ongyang+2.439
Neg logit contributions
arnaev-5.208
Station-4.788
 Grassley-4.745
 Explos-4.744
 Straw-4.686
Token against
Token ID1028
Feature activation-1.54e-01

Pos logit contributions
ongyang+0.511
 emanc+0.510
 sett+0.507
emis+0.501
+0.494
Neg logit contributions
arnaev-0.668
 Grassley-0.621
 Explos-0.614
Station-0.613
 Straw-0.610
Token banks
Token ID6341
Feature activation+1.53e+00

Pos logit contributions
arnaev+0.138
 Grassley+0.131
Station+0.128
 Straw+0.128
 Explos+0.128
Neg logit contributions
ongyang-0.094
 emanc-0.092
emis-0.091
 sett-0.091
-0.090
Token and
Token ID290
Feature activation+2.82e+00

Pos logit contributions
 emanc+0.984
ongyang+0.982
 sett+0.981
emis+0.962
+0.958
Neg logit contributions
arnaev-1.311
 Grassley-1.217
 Explos-1.206
Station-1.203
 Straw-1.193
Token financial
Token ID3176
Feature activation+1.05e+00

Pos logit contributions
ongyang+1.397
 emanc+1.394
 sett+1.391
emis+1.360
 immersion+1.339
Neg logit contributions
arnaev-2.821
 Grassley-2.652
Station-2.625
 Explos-2.610
 Straw-2.603
Token",
Token ID1600
Feature activation+2.08e+00

Pos logit contributions
arnaev+2.595
 Grassley+2.458
Station+2.427
 Explos+2.414
 Straw+2.409
Neg logit contributions
ongyang-1.758
 emanc-1.742
emis-1.722
 sett-1.720
-1.690
Token {
Token ID1391
Feature activation+2.78e+00

Pos logit contributions
ongyang+1.124
 emanc+1.115
 sett+1.113
emis+1.103
+1.095
Neg logit contributions
arnaev-1.987
 Grassley-1.867
Station-1.832
 Explos-1.831
 Straw-1.820
Token10
Token ID940
Feature activation+1.62e+00

Pos logit contributions
ongyang+1.818
+1.809
 emanc+1.793
 sett+1.790
emis+1.788
Neg logit contributions
arnaev-2.335
 Grassley-2.174
 Explos-2.126
 Straw-2.113
Station-2.093
Token,
Token ID11
Feature activation+4.36e+00

Pos logit contributions
ongyang+1.019
 sett+1.016
+1.013
emis+1.011
 emanc+1.009
Neg logit contributions
arnaev-1.395
 Grassley-1.288
 Explos-1.264
 Straw-1.258
Station-1.254
Token 15
Token ID1315
Feature activation-5.98e-01

Pos logit contributions
 sett+2.631
 emanc+2.619
+2.574
emis+2.566
ongyang+2.554
Neg logit contributions
arnaev-3.866
 Grassley-3.559
Station-3.489
 Straw-3.459
 Explos-3.455
Token}
Token ID92
Feature activation+5.08e+00

Pos logit contributions
arnaev+0.498
 Grassley+0.468
Station+0.460
 Explos+0.458
 Straw+0.457
Neg logit contributions
ongyang-0.398
 emanc-0.393
 sett-0.390
emis-0.389
-0.384
Token ->
Token ID4613
Feature activation+1.41e+00

Pos logit contributions
 sett+3.083
emis+3.023
 emanc+3.021
ongyang+2.999
+2.993
Neg logit contributions
arnaev-4.552
 Grassley-4.112
Station-4.036
 Explos-4.024
 Straw-4.018
Token "
Token ID366
Feature activation-1.70e+00

Pos logit contributions
ongyang+0.851
 sett+0.843
 emanc+0.843
emis+0.835
+0.829
Neg logit contributions
arnaev-1.262
 Grassley-1.178
Station-1.157
 Explos-1.154
 Straw-1.150
TokenS
Token ID50
Feature activation-2.51e+00

Pos logit contributions
arnaev+1.153
 Grassley+1.064
Station+1.037
 Explos+1.035
 Straw+1.031
Neg logit contributions
ongyang-1.399
 emanc-1.385
 sett-1.379
emis-1.375
-1.362
Token"
Token ID1
Feature activation-6.85e-01

Pos logit contributions
arnaev+2.236
 Grassley+2.117
Station+2.089
 Explos+2.078
 Straw+2.073
Neg logit contributions
ongyang-1.506
 emanc-1.491
emis-1.473
 sett-1.473
-1.447
Token|
Token ID91
Feature activation+2.45e+00

Pos logit contributions
arnaev+0.536
 Grassley+0.500
Station+0.489
 Explos+0.488
 Straw+0.487
Neg logit contributions
ongyang-0.491
 emanc-0.486
 sett-0.483
emis-0.482
-0.477
Token(
Token ID7
Feature activation-3.06e+00

Pos logit contributions
arnaev+0.143
 Grassley+0.133
Station+0.130
 Explos+0.130
 Straw+0.130
Neg logit contributions
ongyang-0.135
 emanc-0.133
 sett-0.133
emis-0.132
-0.131
Token418
Token ID39667
Feature activation-1.40e+00

Pos logit contributions
arnaev+2.312
 Grassley+2.173
Station+2.135
 Explos+2.122
 Straw+2.112
Neg logit contributions
ongyang-2.273
 emanc-2.239
emis-2.219
 sett-2.217
 immersion-2.183
Tokens
Token ID82
Feature activation-1.57e+00

Pos logit contributions
arnaev+0.963
 Grassley+0.901
Station+0.885
 Straw+0.877
 Explos+0.876
Neg logit contributions
ongyang-1.133
 emanc-1.120
emis-1.108
 sett-1.108
-1.095
Token)}
Token ID38165
Feature activation-5.10e-01

Pos logit contributions
arnaev+0.885
 Grassley+0.817
Station+0.795
 Straw+0.787
 Explos+0.783
Neg logit contributions
ongyang-1.457
 emanc-1.454
 sett-1.439
emis-1.437
 immersion-1.421
Token R
Token ID371
Feature activation-4.26e-01

Pos logit contributions
arnaev+0.362
 Grassley+0.335
Station+0.328
 Explos+0.326
 Straw+0.325
Neg logit contributions
ongyang-0.403
 emanc-0.400
 sett-0.398
emis-0.396
-0.392
Tokenxc
Token ID25306
Feature activation+6.04e+00

Pos logit contributions
arnaev+0.322
 Grassley+0.300
Station+0.294
 Explos+0.293
 Straw+0.292
Neg logit contributions
ongyang-0.316
 emanc-0.313
 sett-0.311
emis-0.310
-0.307
Token3
Token ID18
Feature activation+7.62e+00

Pos logit contributions
ongyang+4.005
 emanc+3.916
+3.914
 sett+3.897
emis+3.885
Neg logit contributions
arnaev-4.927
 Grassley-4.595
 Straw-4.498
Station-4.477
 Explos-4.476
Token {
Token ID1391
Feature activation+1.91e+00

Pos logit contributions
+3.196
 sett+3.160
emis+3.109
 emanc+3.094
ongyang+3.065
Neg logit contributions
arnaev-8.119
 Grassley-7.423
ufact-7.350
Station-7.273
 Straw-7.232
Token(
Token ID7
Feature activation-4.41e-01

Pos logit contributions
+1.288
ongyang+1.282
 sett+1.274
emis+1.266
 emanc+1.266
Neg logit contributions
arnaev-1.567
 Grassley-1.442
 Explos-1.412
 Straw-1.408
Station-1.387
Token64
Token ID2414
Feature activation+3.18e-01

Pos logit contributions
arnaev+0.341
 Grassley+0.318
Station+0.311
 Explos+0.310
 Straw+0.309
Neg logit contributions
ongyang-0.320
 emanc-0.317
 sett-0.316
emis-0.315
-0.312
Tokens
Token ID82
Feature activation+6.60e-01

Pos logit contributions
ongyang+0.242
 emanc+0.241
 sett+0.240
emis+0.239
+0.236
Neg logit contributions
arnaev-0.234
 Grassley-0.216
Station-0.212
 Explos-0.211
 Straw-0.210
Token that
Token ID326
Feature activation-1.34e+00

Pos logit contributions
arnaev+0.511
 Grassley+0.477
Station+0.469
 Explos+0.468
 Straw+0.464
Neg logit contributions
ongyang-0.391
 emanc-0.388
 sett-0.387
emis-0.383
 immersion-0.378
Token the
Token ID262
Feature activation-1.52e+00

Pos logit contributions
arnaev+1.055
 Grassley+0.994
Station+0.971
 Straw+0.970
 Explos+0.969
Neg logit contributions
ongyang-0.949
 emanc-0.930
emis-0.929
 sett-0.923
-0.918
Token volatility
Token ID30772
Feature activation-3.29e-01

Pos logit contributions
arnaev+1.392
 Grassley+1.330
 Straw+1.309
 Explos+1.304
Station+1.296
Neg logit contributions
ongyang-0.887
 emanc-0.858
emis-0.855
 sett-0.846
-0.846
Token is
Token ID318
Feature activation+5.06e-01

Pos logit contributions
arnaev+0.265
 Grassley+0.249
Station+0.244
 Explos+0.243
 Straw+0.242
Neg logit contributions
ongyang-0.228
 emanc-0.224
 sett-0.223
emis-0.223
-0.220
Token a
Token ID257
Feature activation+5.25e-01

Pos logit contributions
ongyang+0.357
 emanc+0.354
 sett+0.352
emis+0.350
+0.346
Neg logit contributions
arnaev-0.402
 Grassley-0.375
Station-0.368
 Explos-0.367
 Straw-0.366
Token result
Token ID1255
Feature activation+7.21e-01

Pos logit contributions
ongyang+0.287
 emanc+0.284
 sett+0.282
emis+0.281
+0.276
Neg logit contributions
arnaev-0.499
 Grassley-0.472
Station-0.464
 Explos-0.463
 Straw-0.462
Token of
Token ID286
Feature activation+1.66e-01

Pos logit contributions
ongyang+0.510
 emanc+0.505
 sett+0.503
emis+0.500
+0.495
Neg logit contributions
arnaev-0.570
 Grassley-0.532
Station-0.521
 Explos-0.520
 Straw-0.518
Token supply
Token ID5127
Feature activation+1.84e+00

Pos logit contributions
ongyang+0.108
 emanc+0.106
 sett+0.106
emis+0.105
+0.104
Neg logit contributions
arnaev-0.142
 Grassley-0.133
Station-0.131
 Explos-0.130
 Straw-0.130
Token-
Token ID12
Feature activation+1.52e+00

Pos logit contributions
ongyang+1.148
 emanc+1.139
 sett+1.133
emis+1.126
+1.113
Neg logit contributions
arnaev-1.617
 Grassley-1.516
Station-1.490
 Explos-1.484
 Straw-1.481
Tokenand
Token ID392
Feature activation+2.55e-01

Pos logit contributions
ongyang+0.908
 emanc+0.895
 sett+0.890
emis+0.889
+0.875
Neg logit contributions
arnaev-1.369
 Grassley-1.286
Station-1.262
 Explos-1.260
 Straw-1.258
Token-
Token ID12
Feature activation+3.54e-01

Pos logit contributions
ongyang+0.181
 emanc+0.179
emis+0.178
 sett+0.177
+0.175
Neg logit contributions
arnaev-0.200
 Grassley-0.188
Station-0.184
 Explos-0.184
 Straw-0.183
Token members
Token ID1866
Feature activation+1.11e+00

Pos logit contributions
arnaev+0.430
 Grassley+0.404
 Straw+0.394
 Explos+0.394
Station+0.394
Neg logit contributions
ongyang-0.382
 emanc-0.376
emis-0.374
 sett-0.372
-0.369
Token of
Token ID286
Feature activation+1.68e+00

Pos logit contributions
ongyang+0.773
 emanc+0.771
 sett+0.770
emis+0.759
+0.753
Neg logit contributions
arnaev-0.894
 Grassley-0.831
Station-0.821
 Explos-0.815
 Straw-0.808
Token smaller
Token ID4833
Feature activation+7.30e-01

Pos logit contributions
ongyang+1.178
 emanc+1.169
 sett+1.167
emis+1.152
+1.142
Neg logit contributions
arnaev-1.350
 Grassley-1.255
Station-1.237
 Explos-1.227
 Straw-1.221
Token ethnic
Token ID9450
Feature activation+1.60e+00

Pos logit contributions
ongyang+0.435
emis+0.427
 emanc+0.424
 sett+0.419
+0.417
Neg logit contributions
arnaev-0.658
 Grassley-0.624
 Straw-0.612
 Explos-0.611
Station-0.609
Token groups
Token ID2628
Feature activation+1.79e+00

Pos logit contributions
ongyang+0.930
 emanc+0.914
emis+0.911
 sett+0.904
+0.893
Neg logit contributions
arnaev-1.470
 Grassley-1.392
 Explos-1.364
Station-1.363
 Straw-1.362
Token like
Token ID588
Feature activation+9.84e-01

Pos logit contributions
 emanc+1.243
 sett+1.239
ongyang+1.238
emis+1.219
+1.210
Neg logit contributions
arnaev-1.440
 Grassley-1.335
Station-1.317
 Explos-1.311
 Straw-1.300
Token the
Token ID262
Feature activation-9.72e-03

Pos logit contributions
ongyang+0.703
 emanc+0.697
 sett+0.694
emis+0.690
+0.683
Neg logit contributions
arnaev-0.771
 Grassley-0.719
Station-0.706
 Explos-0.703
 Straw-0.700
Token Kal
Token ID12612
Feature activation+9.28e-01

Pos logit contributions
arnaev+0.008
 Grassley+0.007
Station+0.007
 Explos+0.007
 Straw+0.007
Neg logit contributions
ongyang-0.007
 emanc-0.007
 sett-0.007
emis-0.007
-0.007
Tokenen
Token ID268
Feature activation+2.84e+00

Pos logit contributions
ongyang+0.599
 emanc+0.589
emis+0.585
 sett+0.584
+0.576
Neg logit contributions
arnaev-0.793
 Grassley-0.746
Station-0.736
 Explos-0.731
 Straw-0.725
Tokenjin
Token ID18594
Feature activation+2.51e+00

Pos logit contributions
ongyang+1.925
 sett+1.924
emis+1.908
 emanc+1.908
+1.866
Neg logit contributions
arnaev-2.309
 Grassley-2.158
Station-2.117
 Explos-2.102
 Straw-2.072
Token and
Token ID290
Feature activation+7.34e-01

Pos logit contributions
 sett+1.696
ongyang+1.694
 emanc+1.688
emis+1.665
+1.656
Neg logit contributions
arnaev-2.059
 Grassley-1.918
Station-1.889
 Explos-1.874
 Straw-1.854
Token progressing
Token ID37335
Feature activation-1.78e+00

Pos logit contributions
arnaev+1.274
 Grassley+1.199
Station+1.174
 Explos+1.172
 Straw+1.170
Neg logit contributions
ongyang-1.102
 emanc-1.085
emis-1.079
 sett-1.077
-1.062
Token in
Token ID287
Feature activation-1.94e+00

Pos logit contributions
arnaev+1.425
 Grassley+1.336
Station+1.310
 Explos+1.305
 Straw+1.302
Neg logit contributions
ongyang-1.237
 emanc-1.219
 sett-1.212
emis-1.210
-1.194
Token terms
Token ID2846
Feature activation-2.07e+00

Pos logit contributions
arnaev+1.569
 Grassley+1.479
 Explos+1.449
 Straw+1.448
Station+1.446
Neg logit contributions
ongyang-1.333
 emanc-1.310
emis-1.307
 sett-1.301
-1.286
Token of
Token ID286
Feature activation+2.28e-02

Pos logit contributions
arnaev+1.523
 Grassley+1.433
Station+1.406
 Straw+1.399
 Explos+1.398
Neg logit contributions
ongyang-1.558
 emanc-1.528
emis-1.527
 sett-1.517
-1.501
Token increasing
Token ID3649
Feature activation+5.08e-01

Pos logit contributions
ongyang+0.014
 emanc+0.014
 sett+0.014
emis+0.014
+0.014
Neg logit contributions
arnaev-0.020
 Grassley-0.019
Station-0.019
 Explos-0.019
 Straw-0.018
Token performance
Token ID2854
Feature activation+2.11e-01

Pos logit contributions
ongyang+0.348
 emanc+0.347
 sett+0.345
emis+0.341
 immersion+0.339
Neg logit contributions
arnaev-0.414
 Grassley-0.385
Station-0.379
 Explos-0.376
 Straw-0.375
Token).
Token ID737
Feature activation+7.33e-01

Pos logit contributions
ongyang+0.146
 emanc+0.144
 sett+0.144
emis+0.143
+0.142
Neg logit contributions
arnaev-0.171
 Grassley-0.159
Station-0.156
 Explos-0.155
 Straw-0.155
Token In
Token ID554
Feature activation-6.15e-01

Pos logit contributions
ongyang+0.491
 sett+0.487
 emanc+0.486
emis+0.483
+0.481
Neg logit contributions
arnaev-0.606
 Grassley-0.563
Station-0.552
 Explos-0.548
 Straw-0.546
Token the
Token ID262
Feature activation-1.55e+00

Pos logit contributions
arnaev+0.531
 Grassley+0.500
Station+0.490
 Explos+0.490
 Straw+0.489
Neg logit contributions
ongyang-0.390
 emanc-0.384
 sett-0.382
emis-0.381
-0.376
Token end
Token ID886
Feature activation-5.75e-01

Pos logit contributions
arnaev+1.105
 Grassley+1.033
 Explos+1.008
 Straw+1.008
Station+1.007
Neg logit contributions
ongyang-1.208
 emanc-1.190
emis-1.185
 sett-1.181
-1.171
Token,
Token ID11
Feature activation+6.99e-01

Pos logit contributions
arnaev+0.471
 Grassley+0.439
Station+0.431
 Explos+0.430
 Straw+0.427
Neg logit contributions
ongyang-0.392
 emanc-0.389
 sett-0.388
emis-0.385
-0.382
Token Travels
Token ID48899
Feature activation+5.12e+00

Pos logit contributions
arnaev+0.285
 Grassley+0.264
Station+0.259
 Explos+0.259
 Straw+0.258
Neg logit contributions
ongyang-0.335
 emanc-0.332
emis-0.329
 sett-0.329
-0.326
Token destinations
Token ID23982
Feature activation+2.42e+00

Pos logit contributions
emis+1.827
 sett+1.794
 emanc+1.788
 immersion+1.788
ongyang+1.784
Neg logit contributions
arnaev-5.856
 Grassley-5.525
Station-5.445
 Straw-5.429
 Explos-5.383
Token,
Token ID11
Feature activation+1.07e+00

Pos logit contributions
+1.441
 sett+1.432
 emanc+1.419
emis+1.415
ongyang+1.414
Neg logit contributions
arnaev-2.165
 Grassley-1.983
 Explos-1.961
Station-1.955
 Straw-1.953
Token and
Token ID290
Feature activation+2.16e+00

Pos logit contributions
ongyang+0.676
 emanc+0.670
 sett+0.668
emis+0.664
+0.656
Neg logit contributions
arnaev-0.932
 Grassley-0.873
Station-0.858
 Explos-0.856
 Straw-0.853
Token explore
Token ID7301
Feature activation+2.09e+00

Pos logit contributions
ongyang+1.255
 emanc+1.237
 sett+1.228
emis+1.224
+1.207
Neg logit contributions
arnaev-1.984
 Grassley-1.873
Station-1.840
 Explos-1.835
 Straw-1.831
Token the
Token ID262
Feature activation+1.45e+00

Pos logit contributions
ongyang+1.367
 sett+1.364
 emanc+1.360
emis+1.346
+1.342
Neg logit contributions
arnaev-1.754
 Grassley-1.627
 Explos-1.597
Station-1.594
 Straw-1.585
Token world
Token ID995
Feature activation+1.65e-01

Pos logit contributions
ongyang+1.014
emis+0.991
 emanc+0.989
+0.979
 sett+0.978
Neg logit contributions
arnaev-1.160
 Grassley-1.088
 Straw-1.070
Station-1.070
 Explos-1.061
Token with
Token ID351
Feature activation+3.97e+00

Pos logit contributions
ongyang+0.111
 emanc+0.110
 sett+0.110
emis+0.109
+0.108
Neg logit contributions
arnaev-0.136
 Grassley-0.126
Station-0.124
 Explos-0.124
 Straw-0.124
Token kindred
Token ID46449
Feature activation+2.71e+00

Pos logit contributions
 sett+3.065
 emanc+3.062
ongyang+3.049
emis+3.004
 immersion+2.992
Neg logit contributions
arnaev-2.847
 Grassley-2.625
Station-2.612
 Explos-2.607
 Straw-2.567
Token spirits
Token ID13747
Feature activation+1.90e+00

Pos logit contributions
ongyang+1.750
 emanc+1.732
 sett+1.722
emis+1.716
+1.690
Neg logit contributions
arnaev-2.308
 Grassley-2.163
Station-2.124
 Explos-2.118
 Straw-2.113
Token.
Token ID13
Feature activation-2.00e-01

Pos logit contributions
 sett+1.307
+1.301
 emanc+1.299
emis+1.298
ongyang+1.297
Neg logit contributions
arnaev-1.532
 Grassley-1.401
 Explos-1.384
 Straw-1.371
Station-1.364
Token
Token ID447
Feature activation-7.18e-01

Pos logit contributions
arnaev+0.652
 Grassley+0.610
Station+0.598
 Explos+0.596
 Straw+0.595
Neg logit contributions
ongyang-0.565
 emanc-0.558
 sett-0.555
emis-0.554
-0.547
Token
Token ID247
Feature activation+1.10e+00

Pos logit contributions
arnaev+0.657
 Grassley+0.619
Station+0.609
 Explos+0.608
 Straw+0.606
Neg logit contributions
ongyang-0.421
 emanc-0.413
 sett-0.411
emis-0.410
-0.404
Tokens
Token ID82
Feature activation+2.03e-01

Pos logit contributions
ongyang+0.789
 emanc+0.779
 sett+0.777
emis+0.773
+0.767
Neg logit contributions
arnaev-0.861
 Grassley-0.803
Station-0.785
 Explos-0.784
 Straw-0.781
Token obviously
Token ID6189
Feature activation-2.82e+00

Pos logit contributions
ongyang+0.131
 emanc+0.130
 sett+0.130
emis+0.128
+0.127
Neg logit contributions
arnaev-0.173
 Grassley-0.162
Station-0.159
 Explos-0.159
 Straw-0.158
Token not
Token ID407
Feature activation-2.19e+00

Pos logit contributions
arnaev+2.325
 Grassley+2.197
Station+2.151
 Explos+2.147
 Straw+2.146
Neg logit contributions
ongyang-1.882
 emanc-1.847
emis-1.843
 sett-1.831
-1.813
Token impossible
Token ID5340
Feature activation+7.78e-01

Pos logit contributions
arnaev+1.812
 Grassley+1.712
Station+1.674
 Straw+1.673
 Explos+1.672
Neg logit contributions
ongyang-1.462
 emanc-1.436
emis-1.432
 sett-1.420
-1.411
Token that
Token ID326
Feature activation+2.92e-01

Pos logit contributions
ongyang+0.531
 emanc+0.523
 sett+0.522
emis+0.516
+0.514
Neg logit contributions
arnaev-0.640
 Grassley-0.596
Station-0.585
 Explos-0.584
 Straw-0.579
Token this
Token ID428
Feature activation+1.24e+00

Pos logit contributions
ongyang+0.201
 emanc+0.199
 sett+0.199
emis+0.196
+0.195
Neg logit contributions
arnaev-0.238
 Grassley-0.221
Station-0.217
 Explos-0.216
 Straw-0.214
Token could
Token ID714
Feature activation-1.28e+00

Pos logit contributions
ongyang+0.788
 emanc+0.784
 sett+0.784
emis+0.767
+0.766
Neg logit contributions
arnaev-1.071
 Grassley-0.997
Station-0.980
 Explos-0.977
 Straw-0.967
Token happen
Token ID1645
Feature activation-9.90e-02

Pos logit contributions
arnaev+1.106
 Grassley+1.041
Station+1.022
 Explos+1.018
 Straw+1.018
Neg logit contributions
ongyang-0.807
 emanc-0.793
emis-0.790
 sett-0.789
-0.778
Token again
Token ID757
Feature activation+1.41e-01

Pos logit contributions
arnaev+0.078
 Grassley+0.073
Station+0.071
 Explos+0.071
 Straw+0.071
Neg logit contributions
ongyang-0.071
 emanc-0.070
 sett-0.069
emis-0.069
-0.069
Token a
Token ID257
Feature activation-2.33e+00

Pos logit contributions
 emanc+1.289
 sett+1.282
ongyang+1.264
 immersion+1.257
emis+1.246
Neg logit contributions
arnaev-1.839
 Grassley-1.719
 Explos-1.675
Station-1.671
 Straw-1.664
Token way
Token ID835
Feature activation+1.44e+00

Pos logit contributions
arnaev+1.985
 Grassley+1.879
Station+1.844
 Straw+1.838
 Explos+1.836
Neg logit contributions
ongyang-1.499
emis-1.459
 emanc-1.456
 sett-1.443
-1.440
Token as
Token ID355
Feature activation+3.58e+00

Pos logit contributions
 emanc+0.871
 sett+0.862
ongyang+0.852
emis+0.848
 immersion+0.834
Neg logit contributions
arnaev-1.292
 Grassley-1.217
Station-1.194
 Explos-1.194
 Straw-1.184
Token may
Token ID743
Feature activation+1.12e+00

Pos logit contributions
 emanc+2.321
 sett+2.317
emis+2.246
 immersion+2.243
ongyang+2.232
Neg logit contributions
arnaev-3.071
 Grassley-2.830
Station-2.801
 Explos-2.780
 Straw-2.726
Token tend
Token ID4327
Feature activation-7.95e-01

Pos logit contributions
 emanc+0.714
 sett+0.704
ongyang+0.697
emis+0.693
 immersion+0.683
Neg logit contributions
arnaev-0.986
 Grassley-0.919
Station-0.906
 Explos-0.901
 Straw-0.897
Token to
Token ID284
Feature activation-1.12e+00

Pos logit contributions
arnaev+0.640
 Grassley+0.599
Station+0.587
 Explos+0.585
 Straw+0.582
Neg logit contributions
ongyang-0.552
 emanc-0.550
 sett-0.546
emis-0.543
-0.536
Token the
Token ID262
Feature activation+2.31e-01

Pos logit contributions
arnaev+0.983
 Grassley+0.928
Station+0.910
 Explos+0.909
 Straw+0.907
Neg logit contributions
ongyang-0.688
 emanc-0.672
emis-0.670
 sett-0.670
-0.662
Token instruction
Token ID12064
Feature activation+4.62e-01

Pos logit contributions
 emanc+0.139
ongyang+0.139
 sett+0.138
emis+0.137
 immersion+0.135
Neg logit contributions
arnaev-0.208
 Grassley-0.195
Station-0.192
 Explos-0.191
 Straw-0.190
Token of
Token ID286
Feature activation-7.95e-01

Pos logit contributions
 emanc+0.318
ongyang+0.318
 sett+0.315
emis+0.313
+0.309
Neg logit contributions
arnaev-0.376
 Grassley-0.350
 Explos-0.343
Station-0.343
 Straw-0.341
Token beginners
Token ID31729
Feature activation+5.40e-01

Pos logit contributions
arnaev+0.670
 Grassley+0.627
Station+0.616
 Explos+0.614
 Straw+0.611
Neg logit contributions
ongyang-0.522
 emanc-0.519
 sett-0.515
emis-0.512
-0.506
Token.
Token ID13
Feature activation+6.53e-01

Pos logit contributions
 emanc+0.373
ongyang+0.372
 sett+0.371
emis+0.366
+0.363
Neg logit contributions
arnaev-0.438
 Grassley-0.408
 Explos-0.400
Station-0.400
 Straw-0.397
Token
Token ID198
Feature activation+5.50e-01

Pos logit contributions
arnaev+0.004
 Grassley+0.003
Station+0.003
 Explos+0.003
 Straw+0.003
Neg logit contributions
ongyang-0.003
 emanc-0.003
 sett-0.003
emis-0.003
-0.003
TokenAfter
Token ID3260
Feature activation+8.25e-01

Pos logit contributions
ongyang+0.388
 emanc+0.383
+0.381
 sett+0.381
emis+0.380
Neg logit contributions
arnaev-0.440
 Grassley-0.407
 Explos-0.400
 Straw-0.396
Station-0.393
Token the
Token ID262
Feature activation-3.50e-01

Pos logit contributions
 emanc+0.528
ongyang+0.527
 sett+0.521
emis+0.518
+0.510
Neg logit contributions
arnaev-0.709
 Grassley-0.659
Station-0.650
 Explos-0.648
 Straw-0.643
Token initial
Token ID4238
Feature activation+1.90e-02

Pos logit contributions
arnaev+0.282
 Grassley+0.261
Station+0.258
 Explos+0.256
 Straw+0.254
Neg logit contributions
ongyang-0.243
 emanc-0.243
 sett-0.241
emis-0.238
-0.236
Token euph
Token ID40381
Feature activation+1.06e+00

Pos logit contributions
ongyang+0.012
 emanc+0.012
 sett+0.012
emis+0.012
+0.011
Neg logit contributions
arnaev-0.017
 Grassley-0.016
Station-0.015
 Explos-0.015
 Straw-0.015
Tokenoria
Token ID7661
Feature activation-7.25e-01

Pos logit contributions
ongyang+0.770
emis+0.758
 emanc+0.757
ixel+0.746
 sett+0.745
Neg logit contributions
arnaev-0.833
 Grassley-0.766
Station-0.757
 Explos-0.751
 Straw-0.749
Token wears
Token ID17326
Feature activation+7.58e-01

Pos logit contributions
arnaev+0.598
 Grassley+0.561
Station+0.550
 Explos+0.548
 Straw+0.547
Neg logit contributions
ongyang-0.489
 emanc-0.483
 sett-0.480
emis-0.479
-0.473
Token off
Token ID572
Feature activation-1.59e+00

Pos logit contributions
ongyang+0.401
 emanc+0.396
 sett+0.393
emis+0.392
+0.385
Neg logit contributions
arnaev-0.735
 Grassley-0.695
Station-0.684
 Explos-0.682
 Straw-0.681
Token a
Token ID257
Feature activation-3.06e+00

Pos logit contributions
arnaev+1.278
 Grassley+1.207
Station+1.179
 Explos+1.175
 Straw+1.172
Neg logit contributions
ongyang-1.102
 emanc-1.083
emis-1.077
 sett-1.075
-1.062
Token bit
Token ID1643
Feature activation+1.65e+00

Pos logit contributions
arnaev+2.729
 Grassley+2.610
 Straw+2.549
Station+2.544
 Explos+2.528
Neg logit contributions
ongyang-1.816
emis-1.772
 emanc-1.771
-1.741
 sett-1.741
Token,
Token ID11
Feature activation+3.61e-01

Pos logit contributions
 emanc+1.054
 sett+1.052
ongyang+1.046
emis+1.041
 immersion+1.030
Neg logit contributions
arnaev-1.417
 Grassley-1.308
Station-1.289
 Explos-1.288
 Straw-1.282
Tokenarp
Token ID5117
Feature activation+8.74e-01

Pos logit contributions
ongyang+1.182
 sett+1.166
 emanc+1.166
emis+1.158
+1.144
Neg logit contributions
arnaev-1.406
 Grassley-1.318
 Explos-1.279
Station-1.278
 Straw-1.278
Token factor
Token ID5766
Feature activation+8.27e-01

Pos logit contributions
ongyang+0.411
 emanc+0.405
 sett+0.403
emis+0.399
+0.391
Neg logit contributions
arnaev-0.901
 Grassley-0.855
Station-0.839
 Explos-0.839
 Straw-0.837
Token"
Token ID1
Feature activation-8.56e-01

Pos logit contributions
ongyang+0.454
 sett+0.449
 emanc+0.449
emis+0.442
+0.437
Neg logit contributions
arnaev-0.788
 Grassley-0.741
Station-0.727
 Explos-0.727
 Straw-0.724
Token number
Token ID1271
Feature activation-2.80e+00

Pos logit contributions
arnaev+0.764
 Grassley+0.727
Station+0.714
 Explos+0.712
 Straw+0.711
Neg logit contributions
ongyang-0.514
 emanc-0.504
emis-0.502
 sett-0.496
-0.495
Token that
Token ID326
Feature activation-2.58e-01

Pos logit contributions
arnaev+2.183
 Grassley+2.075
Station+2.038
 Explos+2.025
 Straw+2.020
Neg logit contributions
ongyang-1.983
 emanc-1.944
emis-1.937
-1.911
 sett-1.906
Token is
Token ID318
Feature activation-7.26e-01

Pos logit contributions
arnaev+0.211
 Grassley+0.196
Station+0.193
 Explos+0.192
 Straw+0.191
Neg logit contributions
ongyang-0.176
 emanc-0.175
 sett-0.174
emis-0.173
-0.170
Token greater
Token ID3744
Feature activation+1.37e+00

Pos logit contributions
arnaev+0.590
 Grassley+0.553
Station+0.542
 Explos+0.541
 Straw+0.539
Neg logit contributions
ongyang-0.498
 emanc-0.492
 sett-0.489
emis-0.488
-0.482
Token than
Token ID621
Feature activation+1.33e+00

Pos logit contributions
 emanc+0.862
ongyang+0.859
 sett+0.859
emis+0.841
 immersion+0.836
Neg logit contributions
arnaev-1.200
 Grassley-1.115
Station-1.095
 Straw-1.093
 Explos-1.091
Token 0
Token ID657
Feature activation-2.54e+00

Pos logit contributions
ongyang+0.886
 emanc+0.886
 sett+0.885
emis+0.870
+0.862
Neg logit contributions
arnaev-1.111
 Grassley-1.030
Station-1.010
 Explos-1.004
 Straw-1.001
Token,
Token ID11
Feature activation-2.30e+00

Pos logit contributions
arnaev+1.898
 Grassley+1.783
Station+1.744
 Explos+1.743
 Straw+1.735
Neg logit contributions
ongyang-1.893
 emanc-1.863
emis-1.859
 sett-1.846
-1.833
Token and
Token ID290
Feature activation-6.53e-01

Pos logit contributions
arnaev+1.881
 Grassley+1.765
Station+1.732
 Explos+1.727
 Straw+1.723
Neg logit contributions
ongyang-1.560
 emanc-1.539
emis-1.527
 sett-1.526
-1.508
Token items
Token ID3709
Feature activation-1.73e+00

Pos logit contributions
arnaev+0.761
 Grassley+0.723
 Explos+0.709
Station+0.708
 Straw+0.707
Neg logit contributions
ongyang-0.487
 emanc-0.477
emis-0.474
 sett-0.473
-0.466
Token amid
Token ID10371
Feature activation-6.99e-01

Pos logit contributions
arnaev+1.340
 Grassley+1.261
Station+1.230
 Explos+1.226
 Straw+1.225
Neg logit contributions
ongyang-1.252
 emanc-1.228
emis-1.223
 sett-1.222
-1.209
Token the
Token ID262
Feature activation-1.53e+00

Pos logit contributions
arnaev+0.589
 Grassley+0.552
Station+0.542
 Explos+0.540
 Straw+0.539
Neg logit contributions
ongyang-0.460
 emanc-0.455
 sett-0.452
emis-0.450
-0.444
Token j
Token ID474
Feature activation-1.55e-02

Pos logit contributions
arnaev+1.282
 Grassley+1.209
Station+1.183
 Explos+1.183
 Straw+1.181
Neg logit contributions
ongyang-1.010
 emanc-0.993
emis-0.987
 sett-0.987
-0.974
Tokenumble
Token ID10344
Feature activation-1.95e+00

Pos logit contributions
arnaev+0.013
 Grassley+0.013
 Explos+0.013
Station+0.013
 Straw+0.012
Neg logit contributions
ongyang-0.010
emis-0.010
 emanc-0.010
 sett-0.010
-0.009
Token of
Token ID286
Feature activation-1.90e+00

Pos logit contributions
arnaev+1.505
 Grassley+1.407
Station+1.378
 Explos+1.375
 Straw+1.372
Neg logit contributions
ongyang-1.419
 emanc-1.402
 sett-1.392
emis-1.391
-1.375
Token images
Token ID4263
Feature activation-5.63e-01

Pos logit contributions
arnaev+1.612
 Grassley+1.534
 Explos+1.503
Station+1.501
 Straw+1.501
Neg logit contributions
ongyang-1.216
emis-1.189
 emanc-1.188
 sett-1.180
-1.170
Token appearing
Token ID12655
Feature activation+2.05e+00

Pos logit contributions
arnaev+0.464
 Grassley+0.435
Station+0.427
 Explos+0.425
 Straw+0.424
Neg logit contributions
ongyang-0.380
 emanc-0.375
 sett-0.373
emis-0.372
-0.367
Token on
Token ID319
Feature activation-7.83e-01

Pos logit contributions
 emanc+1.285
ongyang+1.281
 sett+1.277
emis+1.266
 immersion+1.251
Neg logit contributions
arnaev-1.778
 Grassley-1.660
Station-1.633
 Explos-1.631
 Straw-1.629
Token their
Token ID511
Feature activation-9.21e-01

Pos logit contributions
arnaev+0.666
 Grassley+0.626
Station+0.614
 Explos+0.612
 Straw+0.611
Neg logit contributions
ongyang-0.507
 emanc-0.501
 sett-0.498
emis-0.496
-0.490
Token screens
Token ID8947
Feature activation+5.21e-01

Pos logit contributions
arnaev+0.832
 Grassley+0.784
Station+0.770
 Explos+0.768
 Straw+0.766
Neg logit contributions
ongyang-0.548
 emanc-0.541
 sett-0.538
emis-0.535
-0.528
Token that
Token ID326
Feature activation-5.69e-01

Pos logit contributions
 emanc+0.980
 sett+0.979
ongyang+0.974
 immersion+0.960
emis+0.950
Neg logit contributions
arnaev-1.388
 Grassley-1.288
Station-1.275
 Explos-1.269
 Straw-1.269
Token in
Token ID287
Feature activation-8.00e-01

Pos logit contributions
arnaev+0.474
 Grassley+0.443
Station+0.434
 Explos+0.434
 Straw+0.432
Neg logit contributions
ongyang-0.380
 emanc-0.377
 sett-0.375
emis-0.372
-0.368
Token September
Token ID2693
Feature activation+9.20e-02

Pos logit contributions
arnaev+0.611
 Grassley+0.570
Station+0.557
 Explos+0.556
 Straw+0.555
Neg logit contributions
ongyang-0.588
 emanc-0.581
 sett-0.578
emis-0.577
-0.570
Token 2014
Token ID1946
Feature activation-1.88e+00

Pos logit contributions
ongyang+0.077
 emanc+0.077
 sett+0.077
emis+0.076
+0.076
Neg logit contributions
arnaev-0.060
 Grassley-0.055
Station-0.054
 Explos-0.054
 Straw-0.054
Token the
Token ID262
Feature activation-5.31e-01

Pos logit contributions
arnaev+1.543
 Grassley+1.445
Station+1.417
 Explos+1.413
 Straw+1.409
Neg logit contributions
ongyang-1.278
 emanc-1.263
 sett-1.256
emis-1.251
-1.236
Token lake
Token ID13546
Feature activation-1.19e+00

Pos logit contributions
arnaev+0.440
 Grassley+0.410
Station+0.403
 Explos+0.402
 Straw+0.400
Neg logit contributions
ongyang-0.357
 emanc-0.354
 sett-0.352
emis-0.349
-0.346
Token
Token ID447
Feature activation-8.56e-01

Pos logit contributions
arnaev+1.002
 Grassley+0.940
Station+0.922
 Explos+0.920
 Straw+0.917
Neg logit contributions
ongyang-0.782
 emanc-0.774
 sett-0.769
emis-0.766
-0.756
Token
Token ID247
Feature activation+2.33e-01

Pos logit contributions
arnaev+0.553
 Grassley+0.515
Station+0.498
 Straw+0.494
 Explos+0.493
Neg logit contributions
ongyang-0.726
 emanc-0.723
 sett-0.719
emis-0.715
-0.707
Tokens
Token ID82
Feature activation-1.34e+00

Pos logit contributions
ongyang+0.181
 emanc+0.179
 sett+0.178
emis+0.178
+0.176
Neg logit contributions
arnaev-0.168
 Grassley-0.156
Station-0.153
 Explos-0.152
 Straw-0.152
Token surface
Token ID4417
Feature activation-3.03e-01

Pos logit contributions
arnaev+1.147
 Grassley+1.083
Station+1.062
 Explos+1.060
 Straw+1.057
Neg logit contributions
ongyang-0.856
 emanc-0.842
emis-0.836
 sett-0.836
-0.825
Token area
Token ID1989
Feature activation-1.25e-01

Pos logit contributions
arnaev+0.256
 Grassley+0.239
Station+0.235
 Explos+0.234
 Straw+0.234
Neg logit contributions
ongyang-0.199
 emanc-0.197
 sett-0.195
emis-0.195
-0.192
Token of
Token ID286
Feature activation+5.71e-01

Pos logit contributions
arnaev+0.424
 Grassley+0.396
Station+0.388
 Explos+0.388
 Straw+0.386
Neg logit contributions
ongyang-0.367
 emanc-0.364
 sett-0.363
emis-0.361
-0.356
Token the
Token ID262
Feature activation+1.20e-01

Pos logit contributions
ongyang+0.381
 emanc+0.380
 sett+0.379
emis+0.374
+0.371
Neg logit contributions
arnaev-0.477
 Grassley-0.443
Station-0.437
 Explos-0.433
 Straw-0.432
Token occupational
Token ID34266
Feature activation+1.10e+00

Pos logit contributions
ongyang+0.079
 emanc+0.079
 sett+0.078
emis+0.078
+0.077
Neg logit contributions
arnaev-0.102
 Grassley-0.095
Station-0.093
 Explos-0.093
 Straw-0.092
Token deriv
Token ID16124
Feature activation-7.48e-01

Pos logit contributions
ongyang+0.726
 emanc+0.725
 sett+0.724
emis+0.711
+0.707
Neg logit contributions
arnaev-0.921
 Grassley-0.856
Station-0.839
 Explos-0.835
 Straw-0.833
Tokenational
Token ID864
Feature activation-1.63e+00

Pos logit contributions
arnaev+0.523
 Grassley+0.485
Station+0.473
 Explos+0.472
 Straw+0.471
Neg logit contributions
ongyang-0.598
 emanc-0.591
 sett-0.589
emis-0.588
-0.581
Token suffix
Token ID35488
Feature activation-6.62e+00

Pos logit contributions
arnaev+1.390
 Grassley+1.311
Station+1.285
 Explos+1.283
 Straw+1.280
Neg logit contributions
ongyang-1.052
 emanc-1.036
emis-1.028
 sett-1.026
-1.013
Token -
Token ID532
Feature activation+5.47e-01

Pos logit contributions
arnaev+5.053
 Grassley+4.825
 AZ+4.798
 Explos+4.784
 Straw+4.737
Neg logit contributions
ongyang-4.471
 emanc-4.375
emis-4.318
-4.260
 sett-4.246
Tokencin
Token ID17879
Feature activation-1.84e+00

Pos logit contributions
ongyang+0.390
 emanc+0.384
emis+0.383
 sett+0.383
+0.378
Neg logit contributions
arnaev-0.431
 Grassley-0.404
Station-0.395
 Explos-0.394
 Straw-0.393
Token,
Token ID11
Feature activation-1.56e+00

Pos logit contributions
arnaev+1.447
 Grassley+1.353
Station+1.324
 Explos+1.322
 Straw+1.319
Neg logit contributions
ongyang-1.302
 emanc-1.292
 sett-1.281
emis-1.276
-1.264
Token but
Token ID475
Feature activation-6.00e-01

Pos logit contributions
arnaev+1.287
 Grassley+1.211
Station+1.186
 Explos+1.185
 Straw+1.182
Neg logit contributions
ongyang-1.046
 emanc-1.031
emis-1.025
 sett-1.022
-1.010
Token not
Token ID407
Feature activation-2.11e+00

Pos logit contributions
arnaev+0.483
 Grassley+0.451
Station+0.442
 Explos+0.441
 Straw+0.439
Neg logit contributions
ongyang-0.418
 emanc-0.414
 sett-0.412
emis-0.410
-0.405
Token09
Token ID2931
Feature activation-2.50e-01

Pos logit contributions
ongyang+0.522
 sett+0.517
 emanc+0.517
+0.516
emis+0.515
Neg logit contributions
arnaev-0.521
 Grassley-0.481
 Explos-0.469
 Straw-0.466
Station-0.464
Token-
Token ID12
Feature activation+5.07e+00

Pos logit contributions
arnaev+0.202
 Grassley+0.189
Station+0.185
 Explos+0.185
 Straw+0.184
Neg logit contributions
ongyang-0.172
 emanc-0.170
 sett-0.169
emis-0.169
-0.167
Token20
Token ID1238
Feature activation+4.01e+00

Pos logit contributions
+2.486
ongyang+2.369
emis+2.360
 sett+2.355
 emanc+2.335
Neg logit contributions
arnaev-5.109
 Grassley-4.752
 Explos-4.680
 Straw-4.653
ufact-4.652
Token 01
Token ID5534
Feature activation+1.02e+00

Pos logit contributions
 sett+2.672
+2.650
 emanc+2.607
emis+2.603
ongyang+2.563
Neg logit contributions
arnaev-3.341
 Grassley-2.974
ufact-2.928
Station-2.908
 Explos-2.896
Token:
Token ID25
Feature activation-2.79e+00

Pos logit contributions
 sett+0.752
+0.748
emis+0.746
 emanc+0.745
ongyang+0.745
Neg logit contributions
arnaev-0.773
 Grassley-0.701
 Explos-0.690
 Straw-0.685
Station-0.679
Token44
Token ID2598
Feature activation-5.39e+00

Pos logit contributions
arnaev+1.989
 Grassley+1.878
Station+1.850
 Explos+1.825
 Straw+1.821
Neg logit contributions
ongyang-2.189
 emanc-2.152
emis-2.126
 sett-2.121
 immersion-2.098
Token:
Token ID25
Feature activation-1.90e+00

Pos logit contributions
arnaev+3.258
 Grassley+3.101
Station+3.086
 Explos+3.011
 Straw+3.008
Neg logit contributions
ongyang-4.768
 emanc-4.701
emis-4.629
 sett-4.627
 immersion-4.599
Token24
Token ID1731
Feature activation-2.40e+00

Pos logit contributions
arnaev+1.395
 Grassley+1.307
Station+1.282
 Explos+1.273
 Straw+1.269
Neg logit contributions
ongyang-1.463
 emanc-1.443
 sett-1.429
emis-1.429
-1.406
Token #
Token ID1303
Feature activation+1.43e+00

Pos logit contributions
arnaev+1.711
 Grassley+1.609
Station+1.579
 Explos+1.571
 Straw+1.570
Neg logit contributions
ongyang-1.877
 emanc-1.853
 sett-1.837
emis-1.836
 immersion-1.807
Token19
Token ID1129
Feature activation-4.75e-01

Pos logit contributions
ongyang+0.781
 emanc+0.767
 sett+0.763
emis+0.761
+0.750
Neg logit contributions
arnaev-1.368
 Grassley-1.293
 Explos-1.268
Station-1.264
 Straw-1.262
Token edit
Token ID4370
Feature activation+1.70e+00

Pos logit contributions
arnaev+0.408
 Grassley+0.383
Station+0.377
 Explos+0.375
 Straw+0.374
Neg logit contributions
ongyang-0.304
 emanc-0.300
 sett-0.299
emis-0.297
-0.294
Tokenth
Token ID400
Feature activation+1.79e-01

Pos logit contributions
arnaev+0.837
 Grassley+0.775
Station+0.766
 Explos+0.762
 Straw+0.761
Neg logit contributions
ongyang-1.112
 emanc-1.098
emis-1.095
 sett-1.084
-1.074
Token anniversary
Token ID11162
Feature activation-6.55e-01

Pos logit contributions
ongyang+0.093
 emanc+0.092
 sett+0.092
emis+0.091
+0.090
Neg logit contributions
arnaev-0.175
 Grassley-0.165
Station-0.162
 Explos-0.162
 Straw-0.161
Token of
Token ID286
Feature activation-1.77e+00

Pos logit contributions
arnaev+0.515
 Grassley+0.481
Station+0.471
 Explos+0.469
 Straw+0.468
Neg logit contributions
ongyang-0.468
 emanc-0.463
 sett-0.461
emis-0.458
-0.453
Token Sultan
Token ID37399
Feature activation+2.16e+00

Pos logit contributions
arnaev+1.405
 Grassley+1.327
 Explos+1.301
Station+1.298
 Straw+1.298
Neg logit contributions
ongyang-1.237
emis-1.222
 emanc-1.220
 sett-1.208
-1.198
Token Hassan
Token ID24485
Feature activation-9.81e-03

Pos logit contributions
ongyang+1.307
 sett+1.290
 emanc+1.282
emis+1.267
+1.259
Neg logit contributions
arnaev-1.912
 Grassley-1.791
Station-1.779
 Explos-1.749
 Straw-1.746
Token al
Token ID435
Feature activation-5.65e+00

Pos logit contributions
arnaev+0.009
 Grassley+0.008
Station+0.008
 Straw+0.008
 Explos+0.008
Neg logit contributions
ongyang-0.006
 emanc-0.006
 sett-0.006
emis-0.006
-0.006
Token-
Token ID12
Feature activation-1.74e+00

Pos logit contributions
arnaev+4.070
 Grassley+3.854
 Straw+3.811
 Explos+3.762
 AZ+3.731
Neg logit contributions
ongyang-4.311
emis-4.232
 emanc-4.164
-4.130
 sett-4.059
TokenB
Token ID33
Feature activation-1.68e+00

Pos logit contributions
arnaev+1.050
 Grassley+0.959
Station+0.939
 Straw+0.932
 Explos+0.932
Neg logit contributions
ongyang-1.563
 emanc-1.549
emis-1.538
 sett-1.534
-1.515
Tokenolk
Token ID13597
Feature activation+3.87e-01

Pos logit contributions
arnaev+1.373
 Grassley+1.287
Station+1.261
 Straw+1.254
 Explos+1.251
Neg logit contributions
 emanc-1.135
ongyang-1.134
 sett-1.124
emis-1.114
-1.108
Tokeniah
Token ID9520
Feature activation+7.51e-01

Pos logit contributions
ongyang+0.327
 emanc+0.323
 sett+0.322
emis+0.320
+0.318
Neg logit contributions
arnaev-0.253
 Grassley-0.233
Station-0.228
 Explos-0.227
 Straw-0.225
Token's
Token ID338
Feature activation-2.46e+00

Pos logit contributions
ongyang+0.537
 emanc+0.535
 sett+0.532
emis+0.525
+0.522
Neg logit contributions
arnaev-0.590
 Grassley-0.549
Station-0.539
 Explos-0.535
 Straw-0.533
Token Mor
Token ID3461
Feature activation+1.05e-01

Pos logit contributions
arnaev+0.868
 Grassley+0.808
Station+0.790
 Explos+0.787
 Straw+0.785
Neg logit contributions
ongyang-0.901
 emanc-0.892
 sett-0.887
emis-0.885
-0.875
Tokenaga
Token ID8126
Feature activation+7.49e-01

Pos logit contributions
ongyang+0.075
 emanc+0.074
emis+0.074
 sett+0.074
+0.072
Neg logit contributions
arnaev-0.083
 Grassley-0.077
Station-0.076
 Explos-0.076
 Straw-0.075
Token,
Token ID11
Feature activation-1.48e+00

Pos logit contributions
ongyang+0.495
 emanc+0.489
 sett+0.488
emis+0.488
+0.478
Neg logit contributions
arnaev-0.629
 Grassley-0.583
Station-0.571
 Explos-0.570
 Straw-0.569
Token California
Token ID3442
Feature activation-1.18e-01

Pos logit contributions
arnaev+1.107
 Grassley+1.040
Station+1.013
 Straw+1.012
 Explos+1.011
Neg logit contributions
ongyang-1.110
 emanc-1.095
emis-1.089
 sett-1.088
-1.075
Token.
Token ID13
Feature activation-2.19e+00

Pos logit contributions
arnaev+0.090
 Grassley+0.084
Station+0.082
 Explos+0.082
 Straw+0.081
Neg logit contributions
ongyang-0.086
 emanc-0.085
 sett-0.085
emis-0.084
-0.084
Token Hide
Token ID10415
Feature activation-5.81e+00

Pos logit contributions
arnaev+1.359
 Grassley+1.235
Station+1.209
 Explos+1.199
 Straw+1.193
Neg logit contributions
ongyang-1.930
 emanc-1.911
 sett-1.904
emis-1.902
-1.884
Token Caption
Token ID11260
Feature activation-1.51e-01

Pos logit contributions
arnaev+3.458
 Grassley+3.339
Station+3.245
 Explos+3.224
 Straw+3.206
Neg logit contributions
ongyang-5.258
 emanc-5.217
emis-5.100
 sett-5.058
 immersion-5.043
Token 13
Token ID1511
Feature activation-8.34e-01

Pos logit contributions
arnaev+0.130
 Grassley+0.123
Station+0.121
 Explos+0.120
 Straw+0.120
Neg logit contributions
ongyang-0.096
 emanc-0.095
 sett-0.094
emis-0.094
-0.092
Token of
Token ID286
Feature activation+9.03e-01

Pos logit contributions
arnaev+0.644
 Grassley+0.603
Station+0.591
 Explos+0.588
 Straw+0.587
Neg logit contributions
ongyang-0.606
 emanc-0.598
 sett-0.594
emis-0.593
-0.585
Token 15
Token ID1315
Feature activation-5.54e-01

Pos logit contributions
ongyang+0.636
 emanc+0.627
 sett+0.622
emis+0.621
+0.613
Neg logit contributions
arnaev-0.720
 Grassley-0.677
Station-0.663
 Explos-0.661
 Straw-0.659
Token Photos
Token ID9434
Feature activation-6.85e-01

Pos logit contributions
arnaev+0.287
 Grassley+0.258
Station+0.250
 Explos+0.248
 Straw+0.247
Neg logit contributions
ongyang-0.543
 emanc-0.538
 sett-0.536
emis-0.535
-0.531
Token files
Token ID3696
Feature activation-2.48e+00

Pos logit contributions
arnaev+0.407
 Grassley+0.380
Station+0.372
 Explos+0.370
 Straw+0.369
Neg logit contributions
ongyang-0.365
 emanc-0.362
 sett-0.361
emis-0.359
-0.354
Token ]
Token ID2361
Feature activation-5.36e-02

Pos logit contributions
arnaev+2.379
 Grassley+2.251
Station+2.213
 Explos+2.207
 Straw+2.204
Neg logit contributions
ongyang-1.334
 emanc-1.309
 sett-1.295
emis-1.293
-1.271
Token WHERE
Token ID33411
Feature activation+1.91e+00

Pos logit contributions
arnaev+0.046
 Grassley+0.043
Station+0.042
 Explos+0.042
 Straw+0.041
Neg logit contributions
ongyang-0.035
 emanc-0.035
 sett-0.035
emis-0.034
-0.034
Token path
Token ID3108
Feature activation-4.92e+00

Pos logit contributions
 emanc+1.167
 sett+1.166
ongyang+1.153
emis+1.137
+1.127
Neg logit contributions
arnaev-1.696
 Grassley-1.571
Station-1.556
 Explos-1.549
 Straw-1.544
Token LIKE
Token ID34178
Feature activation-1.00e+00

Pos logit contributions
arnaev+3.628
 Grassley+3.426
Station+3.382
 Explos+3.381
 Straw+3.344
Neg logit contributions
ongyang-3.657
 emanc-3.591
emis-3.563
 sett-3.521
 immersion-3.473
Token '
Token ID705
Feature activation-5.78e+00

Pos logit contributions
arnaev+0.823
 Grassley+0.775
Station+0.758
 Explos+0.757
 Straw+0.755
Neg logit contributions
ongyang-0.679
 emanc-0.669
 sett-0.665
emis-0.664
-0.656
Token%
Token ID4
Feature activation-2.84e+00

Pos logit contributions
arnaev+4.458
 Grassley+4.219
Station+4.181
 Straw+4.142
 Explos+4.125
Neg logit contributions
ongyang-4.038
 emanc-3.967
 sett-3.921
emis-3.906
 immersion-3.852
Tokenproject
Token ID16302
Feature activation-1.09e+00

Pos logit contributions
arnaev+2.175
 Grassley+2.039
Station+2.002
 Explos+1.986
 Straw+1.982
Neg logit contributions
ongyang-2.075
 emanc-2.048
 sett-2.039
emis-2.035
-2.004
Token.
Token ID13
Feature activation-1.22e+00

Pos logit contributions
arnaev+0.816
 Grassley+0.760
Station+0.743
 Explos+0.741
 Straw+0.739
Neg logit contributions
ongyang-0.821
 emanc-0.812
 sett-0.808
emis-0.806
-0.797
Tokencl
Token ID565
Feature activation-3.73e+00

Pos logit contributions
arnaev+0.985
 Grassley+0.922
Station+0.904
 Explos+0.901
 Straw+0.899
Neg logit contributions
ongyang-0.838
 emanc-0.828
 sett-0.824
emis-0.822
-0.811
Tokenj
Token ID73
Feature activation-1.97e+00

Pos logit contributions
arnaev+2.554
 Grassley+2.378
Station+2.308
 Explos+2.298
 Straw+2.291
Neg logit contributions
ongyang-2.991
 sett-2.978
 emanc-2.977
emis-2.928
-2.921