TOP ACTIVATIONS
MAX = 15.656

x . x . x . 83 10 92 135 x
x . x . x . 82 11 66 756 x
direction to reach a water sy ringe held by an experiment
The two L ig ier JS P 3 N
are enabled . Now go back to the Kodi homes creen
$ image . Draw String ($ art ext [ $ i
performance . Going back to our ideal world ,
rejected the Per kin - El mer proposal . The H
2 + $ s z 2 . Height ), $ SR
75 x . x . x . 82 11 66 756
] Mega Pony [/ b ][/ color ] - 20 %
A Novel ( New York : St . Martin
but typically got his best results at night when the airport
we must place it front and center . Dec ades ago
a lawsuit against New York Governor Andrew Cuomo ; Janet Di
laws prohibiting needle exchanges and sy ringe possession without prescriptions have
. View all New York Times newsletters . For
requests for comment and Boh oli ub ov could not be
Simon Gerr ans ( Green Edge Cycling Team ) s .
's the largest crocod ile ever to be taken alive .

MIN ACTIVATIONS
MIN = -19.785

a skillet over medium - high heat . Place f rit
t crowd the pan ; only cook about 3 f rit
ED NET CALL UPDATE : 05 50 z VOL UN TE
Le a Suzuki , The Chronicle 4 of 15 Photo :
together . 4 . Make 6 p att ies . 5
not deep fried . 6 . Drain on a paper towel
? No more bad news pl s . Writer " I
. 3 . In a large bowl , combine the broccoli
ters at a time ), reduce heat to low and cook
? No more bad news pl s . Good
a large bowl , combine the broccoli pieces with all the
. normal * 1 ; } The result pushes
), reduce heat to low and cook f rit ters on
of the passport , whichever comes sooner in case the individual
with all the other ingredients and mix well until the mixture
fever or something like that . That
, 2017 ma N ā n ā k uli , Hawai
ali ( ve get arian pl atter ) consisting of s
_ P ulse Amount ; } 1 2 3 4 5
up some got cha 's I encountered . Assuming you already

INTERVAL 6.796 - 15.656
CONTAINS 1.504%

very poorly when voters are asked about her honesty and trust
also tended to corro de quickly , short ening the life
x . x . x . 78 115 16 72 x
is strongly influenced by the story of George W . Bush
've spoke , " Bel ieve me , Anna . If

INTERVAL -2.064 - 6.796
CONTAINS 74.418%

Ireland s national accounts will also provide few answers
remarkable with regard to common species , wildlife video of the
huge portion of its revenue from online ads , Google has
a measure that itself stretched the bounds of democratic legitimacy .
about that day 's game to be played in freezing temperatures

INTERVAL -10.924 - -2.064
CONTAINS 24.021%

{ 1 , 6 } has valid N Ns at {
, so far it appears as though Ubuntu and its community
it is one of the few that my closest gaming mates
will also need to detach the cables leading to the traction
? Think again . Here 's how Wales lined up for

INTERVAL -19.785 - -10.924
CONTAINS 0.057%

loans are Vi aches lav Pl ak as ov , Vol
is now the Party of Trump .
again that the old address https :// . nice hash .
days , implementing methods add Points ( user , points )
}, {{ 1 , 6 }, { 1 , 7 },
Token x
Token ID2124
Feature activation+5.15e+00

Pos logit contributions
ellar+4.231
yrinth+4.020
 Priv+3.615
 Balloon+3.382
 drag+3.337
Neg logit contributions
�士-9.794
 UCS-9.631
UTF-9.505
osph-9.421
py-9.004
Token.
Token ID13
Feature activation+9.20e+00

Pos logit contributions
ellar+3.364
yrinth+3.140
 Priv+2.815
---------+2.776
[_+2.753
Neg logit contributions
�士-4.161
 UCS-3.970
UTF-3.806
osph-3.722
py-3.540
Tokenx
Token ID87
Feature activation+8.69e+00

Pos logit contributions
ellar+4.477
yrinth+3.990
[_+3.494
---------+3.436
BW+3.392
Neg logit contributions
�士-9.148
 UCS-8.450
UTF-8.039
osph-7.846
senal-7.506
Token.
Token ID13
Feature activation+1.20e+01

Pos logit contributions
ellar+4.993
yrinth+4.405
 Priv+4.182
---------+4.173
[_+4.165
Neg logit contributions
�士-7.837
 UCS-7.014
UTF-6.767
osph-6.700
senal-6.549
Tokenx
Token ID87
Feature activation+1.25e+01

Pos logit contributions
ellar+5.294
yrinth+4.684
[_+4.256
night+4.029
---------+4.016
Neg logit contributions
�士-12.218
 UCS-11.223
UTF-10.627
osph-10.417
senal-10.271
Token.
Token ID13
Feature activation+1.57e+01

Pos logit contributions
ellar+6.489
[_+5.700
yrinth+5.609
---------+5.509
 Priv+5.370
Neg logit contributions
�士-11.585
 UCS-10.342
senal-10.001
UTF-9.915
osph-9.872
Token83
Token ID5999
Feature activation+1.50e+00

Pos logit contributions
ellar+5.433
yrinth+5.214
[_+4.046
---------+3.705
LG+3.612
Neg logit contributions
 UCS-15.696
�士-14.879
UTF-14.670
osph-14.345
pu-13.578
Token 10
Token ID838
Feature activation+1.12e+00

Pos logit contributions
ellar+1.057
yrinth+1.042
 Priv+0.898
 Balloon+0.877
---------+0.871
Neg logit contributions
 UCS-1.107
�士-1.079
UTF-1.066
osph-1.027
py-0.999
Token92
Token ID5892
Feature activation+9.93e+00

Pos logit contributions
ellar+0.854
yrinth+0.826
 Priv+0.722
 Balloon+0.709
---------+0.707
Neg logit contributions
 UCS-0.769
�士-0.746
UTF-0.733
osph-0.709
py-0.681
Token135
Token ID17059
Feature activation+9.04e+00

Pos logit contributions
ellar+6.114
yrinth+5.620
 Priv+5.085
---------+5.041
 Balloon+4.951
Neg logit contributions
 UCS-7.658
�士-7.581
osph-7.177
UTF-7.125
amera-6.697
Token x
Token ID2124
Feature activation+5.26e+00

Pos logit contributions
ellar+3.964
yrinth+3.620
 Priv+3.414
 Balloon+3.249
 drag+3.172
Neg logit contributions
�士-8.907
 UCS-8.280
UTF-8.216
osph-8.025
py-7.665
Token x
Token ID2124
Feature activation+5.01e+00

Pos logit contributions
ellar+3.405
yrinth+3.248
 Priv+2.841
 Balloon+2.693
 drag+2.645
Neg logit contributions
�士-6.833
 UCS-6.736
UTF-6.665
osph-6.497
py-6.313
Token.
Token ID13
Feature activation+9.05e+00

Pos logit contributions
ellar+3.280
yrinth+3.063
 Priv+2.738
---------+2.708
[_+2.679
Neg logit contributions
�士-4.040
 UCS-3.862
UTF-3.701
osph-3.619
py-3.431
Tokenx
Token ID87
Feature activation+9.46e+00

Pos logit contributions
ellar+4.402
yrinth+3.917
[_+3.427
---------+3.375
BW+3.317
Neg logit contributions
�士-9.027
 UCS-8.329
UTF-7.930
osph-7.742
senal-7.404
Token.
Token ID13
Feature activation+1.02e+01

Pos logit contributions
ellar+5.264
yrinth+4.554
[_+4.427
---------+4.417
 Priv+4.387
Neg logit contributions
�士-8.727
 UCS-7.706
UTF-7.439
senal-7.409
osph-7.398
Tokenx
Token ID87
Feature activation+1.42e+01

Pos logit contributions
ellar+4.754
yrinth+4.199
[_+3.715
---------+3.598
night+3.583
Neg logit contributions
�士-10.356
 UCS-9.517
UTF-9.055
osph-8.835
senal-8.601
Token.
Token ID13
Feature activation+1.48e+01

Pos logit contributions
ellar+6.885
[_+6.174
---------+5.865
yrinth+5.678
 Priv+5.652
Neg logit contributions
�士-13.332
 UCS-11.891
senal-11.712
UTF-11.320
osph-11.317
Token82
Token ID6469
Feature activation+6.24e+00

Pos logit contributions
ellar+6.453
yrinth+6.009
[_+5.060
ever+4.651
 Balloon+4.642
Neg logit contributions
 UCS-13.809
UTF-13.085
�士-12.661
osph-12.321
-11.610
Token 11
Token ID1367
Feature activation+2.51e+00

Pos logit contributions
ellar+3.998
yrinth+3.972
 Priv+3.509
---------+3.388
 Balloon+3.384
Neg logit contributions
�士-4.772
 UCS-4.684
UTF-4.593
osph-4.532
py-4.282
Token66
Token ID2791
Feature activation+8.50e+00

Pos logit contributions
ellar+1.875
yrinth+1.794
 Priv+1.592
---------+1.572
 Balloon+1.568
Neg logit contributions
 UCS-1.734
�士-1.698
UTF-1.657
osph-1.624
py-1.546
Token756
Token ID38219
Feature activation+1.06e+01

Pos logit contributions
ellar+5.695
yrinth+5.270
---------+4.933
 Priv+4.764
BW+4.760
Neg logit contributions
 UCS-6.110
�士-6.002
UTF-5.751
osph-5.727
py-5.305
Token x
Token ID2124
Feature activation+5.15e+00

Pos logit contributions
ellar+4.231
yrinth+4.020
 Priv+3.615
 Balloon+3.382
 drag+3.337
Neg logit contributions
�士-9.794
 UCS-9.631
UTF-9.505
osph-9.421
py-9.004
Token direction
Token ID4571
Feature activation-5.85e-02

Pos logit contributions
 UCS+2.337
UTF+2.238
�士+2.218
osph+2.125
py+2.115
Neg logit contributions
ellar-1.995
yrinth-1.958
 Priv-1.637
 Klux-1.614
 Balloon-1.600
Token to
Token ID284
Feature activation+2.51e+00

Pos logit contributions
 UCS+0.044
�士+0.042
UTF+0.042
osph+0.040
py+0.039
Neg logit contributions
ellar-0.041
yrinth-0.041
 Priv-0.034
 Balloon-0.034
 Klux-0.034
Token reach
Token ID3151
Feature activation+3.26e+00

Pos logit contributions
ellar+1.767
yrinth+1.735
 Priv+1.480
 Balloon+1.466
 drag+1.463
Neg logit contributions
 UCS-1.855
�士-1.819
UTF-1.817
osph-1.701
py-1.666
Token a
Token ID257
Feature activation+1.57e+00

Pos logit contributions
ellar+2.006
yrinth+1.969
 Balloon+1.625
 Priv+1.618
 drag+1.588
Neg logit contributions
 UCS-2.680
�士-2.650
UTF-2.635
osph-2.489
py-2.438
Token water
Token ID1660
Feature activation+4.03e+00

Pos logit contributions
ellar+1.057
yrinth+1.044
 Priv+0.874
 Balloon+0.872
 drag+0.860
Neg logit contributions
 UCS-1.212
�士-1.192
UTF-1.186
osph-1.119
py-1.101
Token sy
Token ID827
Feature activation+1.46e+01

Pos logit contributions
ellar+2.682
yrinth+2.648
 Balloon+2.229
 drag+2.224
 Priv+2.192
Neg logit contributions
 UCS-3.088
�士-3.059
UTF-3.030
osph-2.823
py-2.769
Tokenringe
Token ID38229
Feature activation+5.40e+00

Pos logit contributions
ellar+5.801
yrinth+5.336
apor+3.774
sted+3.764
 Balloon+3.687
Neg logit contributions
�士-14.789
UTF-14.379
 UCS-14.350
-12.984
osph-12.481
Token held
Token ID2714
Feature activation+1.84e+00

Pos logit contributions
ellar+3.462
yrinth+3.378
 drag+2.892
 Balloon+2.883
 Priv+2.865
Neg logit contributions
�士-4.299
 UCS-4.190
UTF-4.155
osph-3.883
pu-3.733
Token by
Token ID416
Feature activation-5.12e-01

Pos logit contributions
ellar+1.185
yrinth+1.164
 Priv+0.981
 Balloon+0.975
 drag+0.954
Neg logit contributions
 UCS-1.476
�士-1.453
UTF-1.428
osph-1.365
py-1.327
Token an
Token ID281
Feature activation+2.35e+00

Pos logit contributions
 UCS+0.406
�士+0.395
UTF+0.395
osph+0.377
py+0.368
Neg logit contributions
ellar-0.338
yrinth-0.331
 Priv-0.278
 Balloon-0.275
 drag-0.269
Token experiment
Token ID6306
Feature activation+4.00e+00

Pos logit contributions
ellar+1.601
yrinth+1.554
 Balloon+1.316
 Priv+1.312
 drag+1.297
Neg logit contributions
 UCS-1.775
�士-1.754
UTF-1.726
osph-1.660
py-1.631
Token
Token ID198
Feature activation+7.50e-02

Pos logit contributions
 UCS+0.617
UTF+0.596
�士+0.595
osph+0.568
py+0.557
Neg logit contributions
ellar-0.534
yrinth-0.525
 Priv-0.443
 Balloon-0.434
 Klux-0.428
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
ellar+0.053
yrinth+0.052
 Priv+0.043
 Klux+0.043
 Balloon+0.043
Neg logit contributions
 UCS-0.057
UTF-0.054
�士-0.053
osph-0.051
py-0.051
TokenThe
Token ID464
Feature activation-1.21e+00

Pos logit contributions
 UCS+0.103
�士+0.099
UTF+0.098
osph+0.094
py+0.092
Neg logit contributions
ellar-0.097
yrinth-0.096
 Priv-0.081
 Balloon-0.079
BW-0.079
Token two
Token ID734
Feature activation+3.59e+00

Pos logit contributions
 UCS+0.909
UTF+0.873
�士+0.870
osph+0.830
py+0.818
Neg logit contributions
ellar-0.857
yrinth-0.843
 Priv-0.710
 Balloon-0.700
 Klux-0.697
Token L
Token ID406
Feature activation+5.66e+00

Pos logit contributions
ellar+2.417
yrinth+2.378
 Priv+2.055
 drag+2.015
 Balloon+1.999
Neg logit contributions
 UCS-2.693
�士-2.676
UTF-2.656
osph-2.519
py-2.458
Tokenig
Token ID328
Feature activation+1.46e+01

Pos logit contributions
ellar+1.656
yrinth+1.541
 Priv+0.864
 drag+0.849
BW+0.840
Neg logit contributions
 UCS-6.571
�士-6.422
UTF-6.317
py-6.089
osph-6.086
Tokenier
Token ID959
Feature activation+6.76e+00

Pos logit contributions
yrinth+7.870
ellar+7.827
 Priv+6.428
 drag+6.211
 Klux+6.148
Neg logit contributions
�士-12.240
UTF-11.468
 UCS-11.389
osph-10.355
py-10.303
Token JS
Token ID26755
Feature activation+5.29e+00

Pos logit contributions
ellar+4.418
yrinth+4.378
 Priv+3.881
 drag+3.846
 Doodle+3.687
Neg logit contributions
�士-4.915
 UCS-4.907
UTF-4.897
osph-4.701
py-4.544
Token P
Token ID350
Feature activation+3.37e-01

Pos logit contributions
ellar+3.734
yrinth+3.660
 Priv+3.251
 drag+3.182
 Balloon+3.098
Neg logit contributions
 UCS-3.731
UTF-3.678
�士-3.661
osph-3.477
py-3.391
Token3
Token ID18
Feature activation+3.19e+00

Pos logit contributions
ellar+0.301
yrinth+0.296
 Priv+0.260
 Klux+0.257
 Balloon+0.256
Neg logit contributions
 UCS-0.191
UTF-0.180
�士-0.180
osph-0.167
py-0.165
Token N
Token ID399
Feature activation-2.52e+00

Pos logit contributions
ellar+2.220
yrinth+2.193
 Priv+1.878
 drag+1.830
 Balloon+1.822
Neg logit contributions
 UCS-2.360
UTF-2.306
�士-2.282
osph-2.182
py-2.129
Token are
Token ID389
Feature activation-2.73e+00

Pos logit contributions
 UCS+6.807
UTF+6.617
py+6.122
�士+6.102
osph+6.096
Neg logit contributions
ellar-9.386
yrinth-8.957
 Klux-8.061
 Doodle-7.804
 Priv-7.721
Token enabled
Token ID9343
Feature activation-2.75e+00

Pos logit contributions
 UCS+2.140
UTF+2.047
�士+2.029
osph+1.949
py+1.925
Neg logit contributions
ellar-1.846
yrinth-1.811
 Priv-1.496
 Klux-1.483
 Balloon-1.481
Token.
Token ID13
Feature activation-1.85e+00

Pos logit contributions
 UCS+1.973
UTF+1.888
�士+1.865
osph+1.790
py+1.767
Neg logit contributions
ellar-2.036
yrinth-1.999
 Priv-1.687
 Balloon-1.669
 Klux-1.668
Token Now
Token ID2735
Feature activation-1.17e+00

Pos logit contributions
 UCS+1.403
UTF+1.346
�士+1.337
osph+1.278
py+1.266
Neg logit contributions
ellar-1.291
yrinth-1.270
 Priv-1.060
 Klux-1.047
 Balloon-1.046
Token go
Token ID467
Feature activation+8.65e+00

Pos logit contributions
 UCS+0.905
UTF+0.871
�士+0.869
osph+0.829
py+0.818
Neg logit contributions
ellar-0.799
yrinth-0.786
 Priv-0.658
 Balloon-0.648
 Klux-0.645
Token back
Token ID736
Feature activation+1.45e+01

Pos logit contributions
yrinth+4.968
ellar+4.768
 drag+4.241
 Priv+4.052
 Balloon+4.026
Neg logit contributions
�士-6.908
UTF-6.859
 UCS-6.810
osph-6.413
pu-6.230
Token to
Token ID284
Feature activation+2.38e+00

Pos logit contributions
yrinth+7.203
ellar+6.577
 drag+5.887
 Priv+5.773
---------+5.759
Neg logit contributions
�士-11.749
 UCS-11.556
UTF-11.501
osph-10.847
pu-10.439
Token the
Token ID262
Feature activation-1.62e+00

Pos logit contributions
ellar+1.550
yrinth+1.547
 Priv+1.317
 Balloon+1.278
 drag+1.259
Neg logit contributions
 UCS-1.843
UTF-1.837
�士-1.828
osph-1.738
py-1.691
Token Kodi
Token ID44129
Feature activation+3.62e+00

Pos logit contributions
 UCS+1.280
UTF+1.232
�士+1.229
osph+1.175
py+1.158
Neg logit contributions
ellar-1.078
yrinth-1.060
 Priv-0.882
 Balloon-0.869
 Klux-0.864
Token homes
Token ID5682
Feature activation+3.41e+00

Pos logit contributions
ellar+2.453
yrinth+2.449
 Priv+2.105
 drag+2.044
 Balloon+2.043
Neg logit contributions
 UCS-2.659
�士-2.636
UTF-2.629
osph-2.525
py-2.418
Tokencreen
Token ID32060
Feature activation+4.78e+00

Pos logit contributions
ellar+2.532
yrinth+2.507
 Priv+2.108
 drag+2.085
 Klux+2.070
Neg logit contributions
 UCS-2.392
UTF-2.298
�士-2.295
osph-2.180
pu-2.041
Token $
Token ID720
Feature activation+7.63e+00

Pos logit contributions
ellar+0.362
yrinth+0.354
 Priv+0.306
 Balloon+0.300
 Klux+0.295
Neg logit contributions
 UCS-0.345
�士-0.332
UTF-0.331
osph-0.316
py-0.309
Tokenimage
Token ID9060
Feature activation+4.57e+00

Pos logit contributions
ellar+4.300
yrinth+4.067
BW+3.319
 Balloon+3.309
[_+3.219
Neg logit contributions
 UCS-6.558
�士-6.547
UTF-6.099
osph-5.960
-5.829
Token.
Token ID13
Feature activation+2.18e+00

Pos logit contributions
ellar+2.987
yrinth+2.867
[_+2.454
BW+2.442
 Priv+2.428
Neg logit contributions
 UCS-3.579
�士-3.492
UTF-3.357
osph-3.289
py-3.160
TokenDraw
Token ID25302
Feature activation+1.08e+00

Pos logit contributions
ellar+1.035
yrinth+1.008
BW+0.777
 Priv+0.759
 Balloon+0.751
Neg logit contributions
 UCS-2.121
�士-2.072
UTF-2.010
osph-1.976
py-1.921
TokenString
Token ID10100
Feature activation+1.50e+00

Pos logit contributions
ellar+0.935
yrinth+0.920
 Priv+0.805
 Balloon+0.801
BW+0.797
Neg logit contributions
 UCS-0.627
�士-0.604
UTF-0.577
osph-0.565
py-0.541
Token($
Token ID16763
Feature activation+1.44e+01

Pos logit contributions
ellar+1.104
yrinth+1.073
 Priv+0.933
 Balloon+0.914
BW+0.901
Neg logit contributions
 UCS-1.074
�士-1.048
UTF-1.015
osph-0.982
py-0.955
Tokenart
Token ID433
Feature activation+7.76e+00

Pos logit contributions
ellar+6.540
yrinth+5.378
night+4.774
[_+4.698
BW+4.579
Neg logit contributions
�士-14.441
 UCS-13.346
UTF-12.434
senal-11.972
osph-11.967
Tokenext
Token ID2302
Feature activation+1.17e+00

Pos logit contributions
ellar+3.551
yrinth+3.187
[_+2.499
night+2.479
---------+2.451
Neg logit contributions
�士-8.205
 UCS-7.668
UTF-7.327
osph-7.009
-6.877
Token[
Token ID58
Feature activation-7.67e-01

Pos logit contributions
ellar+0.835
yrinth+0.819
 Priv+0.694
 Balloon+0.684
 Klux+0.680
Neg logit contributions
 UCS-0.863
�士-0.831
UTF-0.827
osph-0.788
py-0.774
Token$
Token ID3
Feature activation+6.19e+00

Pos logit contributions
 UCS+0.402
UTF+0.386
�士+0.361
py+0.353
osph+0.350
Neg logit contributions
yrinth-0.715
ellar-0.714
 Priv-0.621
 Balloon-0.617
 Klux-0.616
Tokeni
Token ID72
Feature activation+8.48e+00

Pos logit contributions
ellar+3.571
yrinth+3.367
[_+2.741
 Priv+2.725
 Balloon+2.672
Neg logit contributions
�士-5.590
 UCS-5.402
UTF-5.056
osph-4.890
-4.721
Token performance
Token ID2854
Feature activation+2.37e+00

Pos logit contributions
 UCS+0.828
�士+0.800
UTF+0.798
osph+0.760
py+0.749
Neg logit contributions
ellar-0.719
yrinth-0.708
 Priv-0.594
 Balloon-0.584
 Klux-0.578
Token.
Token ID13
Feature activation+3.26e-01

Pos logit contributions
ellar+1.599
yrinth+1.569
 Priv+1.342
 Balloon+1.322
---------+1.299
Neg logit contributions
 UCS-1.799
�士-1.781
UTF-1.731
osph-1.645
py-1.610
Token
Token ID198
Feature activation-9.24e-01

Pos logit contributions
ellar+0.219
yrinth+0.214
 Priv+0.183
 Balloon+0.179
 Doodle+0.176
Neg logit contributions
 UCS-0.252
�士-0.246
UTF-0.245
osph-0.234
py-0.229
Token
Token ID198
Feature activation+3.64e-01

Pos logit contributions
 UCS+0.680
UTF+0.651
�士+0.617
py+0.615
osph+0.612
Neg logit contributions
yrinth-0.673
ellar-0.669
 Klux-0.553
 Priv-0.551
 Balloon-0.550
TokenGoing
Token ID27404
Feature activation+6.14e+00

Pos logit contributions
ellar+0.267
yrinth+0.263
 Priv+0.224
 Balloon+0.220
BW+0.220
Neg logit contributions
 UCS-0.262
�士-0.254
UTF-0.249
osph-0.239
py-0.233
Token back
Token ID736
Feature activation+1.43e+01

Pos logit contributions
yrinth+4.047
ellar+4.037
 Priv+3.601
 Balloon+3.544
 Klux+3.411
Neg logit contributions
�士-4.637
UTF-4.456
 UCS-4.416
osph-4.172
py-4.099
Token to
Token ID284
Feature activation+4.96e+00

Pos logit contributions
yrinth+7.098
ellar+6.985
---------+5.701
 drag+5.665
 Priv+5.588
Neg logit contributions
�士-11.476
 UCS-11.336
UTF-10.997
-10.208
py-10.175
Token our
Token ID674
Feature activation+4.69e+00

Pos logit contributions
ellar+3.424
yrinth+3.420
 Priv+2.994
 Balloon+2.937
 drag+2.882
Neg logit contributions
�士-3.578
UTF-3.542
 UCS-3.490
osph-3.319
py-3.220
Token ideal
Token ID7306
Feature activation+2.09e+00

Pos logit contributions
ellar+3.088
yrinth+3.042
 Priv+2.643
 Balloon+2.582
 Doodle+2.535
Neg logit contributions
�士-3.570
 UCS-3.505
UTF-3.494
osph-3.321
py-3.242
Token world
Token ID995
Feature activation+1.91e+00

Pos logit contributions
ellar+1.391
yrinth+1.377
 Priv+1.161
 Balloon+1.133
 Klux+1.112
Neg logit contributions
 UCS-1.606
�士-1.591
UTF-1.573
osph-1.492
py-1.473
Token,
Token ID11
Feature activation-1.04e+00

Pos logit contributions
ellar+1.304
yrinth+1.274
 Priv+1.077
 Balloon+1.062
 drag+1.039
Neg logit contributions
 UCS-1.463
�士-1.441
UTF-1.424
osph-1.347
py-1.320
Token rejected
Token ID8606
Feature activation+2.87e+00

Pos logit contributions
ellar+1.628
yrinth+1.599
 Priv+1.358
 Balloon+1.345
 Doodle+1.311
Neg logit contributions
 UCS-1.938
�士-1.888
UTF-1.886
osph-1.796
py-1.762
Token the
Token ID262
Feature activation+4.62e+00

Pos logit contributions
ellar+1.795
yrinth+1.751
 Priv+1.524
 Balloon+1.508
 drag+1.432
Neg logit contributions
 UCS-2.286
�士-2.268
UTF-2.254
osph-2.165
py-2.087
Token Per
Token ID2448
Feature activation-3.52e+00

Pos logit contributions
ellar+2.266
yrinth+2.167
 Priv+1.839
 Balloon+1.833
 drag+1.733
Neg logit contributions
�士-4.289
UTF-4.217
 UCS-4.202
osph-4.035
pu-3.913
Tokenkin
Token ID5116
Feature activation+6.73e+00

Pos logit contributions
 UCS+2.138
UTF+2.037
osph+1.971
py+1.944
pu+1.885
Neg logit contributions
yrinth-2.929
ellar-2.897
 Priv-2.530
 Doodle-2.500
 Balloon-2.477
Token-
Token ID12
Feature activation+1.34e+01

Pos logit contributions
ellar+4.150
yrinth+4.011
 Balloon+3.433
 Priv+3.407
---------+3.267
Neg logit contributions
 UCS-5.329
�士-5.301
UTF-5.224
osph-5.006
py-4.811
TokenEl
Token ID9527
Feature activation+1.43e+01

Pos logit contributions
ellar+7.110
yrinth+6.425
---------+5.793
BW+5.621
LG+5.607
Neg logit contributions
�士-11.910
 UCS-10.879
osph-10.621
UTF-10.095
pu-9.854
Tokenmer
Token ID647
Feature activation+5.71e+00

Pos logit contributions
ellar+5.743
yrinth+5.163
night+4.623
 Klux+4.300
 Priv+4.145
Neg logit contributions
�士-15.158
UTF-13.476
 UCS-13.285
osph-12.459
-12.194
Token proposal
Token ID6961
Feature activation-1.62e-04

Pos logit contributions
ellar+2.914
yrinth+2.784
 Balloon+2.396
 Priv+2.384
 Doodle+2.281
Neg logit contributions
�士-5.204
 UCS-5.078
UTF-5.074
osph-4.820
pu-4.681
Token.
Token ID13
Feature activation-1.49e+00

Pos logit contributions
 UCS+0.000
�士+0.000
UTF+0.000
osph+0.000
py+0.000
Neg logit contributions
ellar-0.000
yrinth-0.000
 Priv-0.000
 Balloon-0.000
 Klux-0.000
Token The
Token ID383
Feature activation+2.51e+00

Pos logit contributions
 UCS+1.049
UTF+1.005
�士+1.003
osph+0.953
py+0.937
Neg logit contributions
ellar-1.124
yrinth-1.106
 Priv-0.945
 Balloon-0.932
 Klux-0.927
Token H
Token ID367
Feature activation+1.78e+00

Pos logit contributions
ellar+1.653
yrinth+1.626
 Priv+1.399
 Balloon+1.385
 Doodle+1.332
Neg logit contributions
 UCS-1.941
�士-1.930
UTF-1.914
osph-1.820
py-1.769
Token2
Token ID17
Feature activation+4.94e+00

Pos logit contributions
ellar+1.530
yrinth+1.482
 Priv+1.311
 Balloon+1.292
BW+1.287
Neg logit contributions
 UCS-1.167
�士-1.131
UTF-1.092
osph-1.058
py-1.018
Token +
Token ID1343
Feature activation+1.17e+00

Pos logit contributions
ellar+3.146
yrinth+2.983
 Balloon+2.578
)--+2.566
[_+2.565
Neg logit contributions
 UCS-3.881
�士-3.855
UTF-3.662
osph-3.591
py-3.448
Token $
Token ID720
Feature activation+7.73e+00

Pos logit contributions
ellar+0.869
yrinth+0.848
 Priv+0.737
 Balloon+0.726
BW+0.711
Neg logit contributions
 UCS-0.828
�士-0.804
UTF-0.796
osph-0.765
py-0.747
Tokens
Token ID82
Feature activation+1.27e+00

Pos logit contributions
ellar+4.246
yrinth+3.882
BW+3.404
 Balloon+3.243
 Priv+3.232
Neg logit contributions
 UCS-6.716
�士-6.713
UTF-6.255
osph-6.153
py-5.980
Tokenz
Token ID89
Feature activation+8.80e+00

Pos logit contributions
ellar+0.914
yrinth+0.891
 Priv+0.755
BW+0.751
 Balloon+0.741
Neg logit contributions
 UCS-0.942
�士-0.919
UTF-0.879
osph-0.843
py-0.822
Token2
Token ID17
Feature activation+1.42e+01

Pos logit contributions
ellar+5.107
yrinth+4.805
[_+4.254
BW+4.239
 Priv+4.165
Neg logit contributions
 UCS-7.080
�士-6.980
UTF-6.585
osph-6.419
pu-6.158
Token.
Token ID13
Feature activation+7.93e+00

Pos logit contributions
ellar+7.012
yrinth+6.260
[_+6.231
)--+6.170
---------+5.800
Neg logit contributions
�士-11.600
 UCS-11.218
osph-10.533
UTF-10.381
pu-10.085
TokenHeight
Token ID23106
Feature activation+5.76e+00

Pos logit contributions
ellar+3.245
yrinth+2.963
BW+2.628
 Balloon+2.463
---------+2.434
Neg logit contributions
�士-7.812
 UCS-7.772
osph-7.415
UTF-7.194
ansen-7.016
Token),
Token ID828
Feature activation+2.07e+00

Pos logit contributions
ellar+3.299
yrinth+3.108
)--+2.686
 Priv+2.676
 Balloon+2.651
Neg logit contributions
�士-4.816
 UCS-4.797
UTF-4.573
osph-4.450
py-4.308
Token$
Token ID3
Feature activation+9.02e+00

Pos logit contributions
ellar+1.779
yrinth+1.737
 Priv+1.538
 Balloon+1.502
BW+1.493
Neg logit contributions
 UCS-1.230
�士-1.176
UTF-1.148
osph-1.105
py-1.060
TokenSR
Token ID12562
Feature activation+4.76e+00

Pos logit contributions
ellar+5.239
yrinth+4.856
BW+4.303
 Priv+4.118
LG+4.093
Neg logit contributions
�士-7.322
 UCS-7.281
UTF-6.827
osph-6.795
py-6.533
Token75
Token ID2425
Feature activation+7.43e+00

Pos logit contributions
ellar+3.107
yrinth+2.916
 Priv+2.640
 Balloon+2.591
---------+2.587
Neg logit contributions
�士-3.074
 UCS-3.058
UTF-2.944
osph-2.888
py-2.717
Token x
Token ID2124
Feature activation+5.01e+00

Pos logit contributions
ellar+3.405
yrinth+3.248
 Priv+2.841
 Balloon+2.693
 drag+2.645
Neg logit contributions
�士-6.833
 UCS-6.736
UTF-6.665
osph-6.497
py-6.313
Token.
Token ID13
Feature activation+9.05e+00

Pos logit contributions
ellar+3.280
yrinth+3.063
 Priv+2.738
---------+2.708
[_+2.679
Neg logit contributions
�士-4.040
 UCS-3.862
UTF-3.701
osph-3.619
py-3.431
Tokenx
Token ID87
Feature activation+9.46e+00

Pos logit contributions
ellar+4.402
yrinth+3.917
[_+3.427
---------+3.375
BW+3.317
Neg logit contributions
�士-9.027
 UCS-8.329
UTF-7.930
osph-7.742
senal-7.404
Token.
Token ID13
Feature activation+1.02e+01

Pos logit contributions
ellar+5.264
yrinth+4.554
[_+4.427
---------+4.417
 Priv+4.387
Neg logit contributions
�士-8.727
 UCS-7.706
UTF-7.439
senal-7.409
osph-7.398
Tokenx
Token ID87
Feature activation+1.42e+01

Pos logit contributions
ellar+4.754
yrinth+4.199
[_+3.715
---------+3.598
night+3.583
Neg logit contributions
�士-10.356
 UCS-9.517
UTF-9.055
osph-8.835
senal-8.601
Token.
Token ID13
Feature activation+1.48e+01

Pos logit contributions
ellar+6.885
[_+6.174
---------+5.865
yrinth+5.678
 Priv+5.652
Neg logit contributions
�士-13.332
 UCS-11.891
senal-11.712
UTF-11.320
osph-11.317
Token82
Token ID6469
Feature activation+6.24e+00

Pos logit contributions
ellar+6.453
yrinth+6.009
[_+5.060
ever+4.651
 Balloon+4.642
Neg logit contributions
 UCS-13.809
UTF-13.085
�士-12.661
osph-12.321
-11.610
Token 11
Token ID1367
Feature activation+2.51e+00

Pos logit contributions
ellar+3.998
yrinth+3.972
 Priv+3.509
---------+3.388
 Balloon+3.384
Neg logit contributions
�士-4.772
 UCS-4.684
UTF-4.593
osph-4.532
py-4.282
Token66
Token ID2791
Feature activation+8.50e+00

Pos logit contributions
ellar+1.875
yrinth+1.794
 Priv+1.592
---------+1.572
 Balloon+1.568
Neg logit contributions
 UCS-1.734
�士-1.698
UTF-1.657
osph-1.624
py-1.546
Token756
Token ID38219
Feature activation+1.06e+01

Pos logit contributions
ellar+5.695
yrinth+5.270
---------+4.933
 Priv+4.764
BW+4.760
Neg logit contributions
 UCS-6.110
�士-6.002
UTF-5.751
osph-5.727
py-5.305
Token]
Token ID60
Feature activation+6.05e+00

Pos logit contributions
ellar+3.097
yrinth+2.940
 Priv+2.525
---------+2.521
[_+2.491
Neg logit contributions
�士-3.769
 UCS-3.680
UTF-3.519
osph-3.390
py-3.251
TokenMega
Token ID43471
Feature activation+3.28e+00

Pos logit contributions
ellar+4.145
yrinth+4.103
BW+3.603
 Balloon+3.506
---------+3.498
Neg logit contributions
 UCS-4.362
�士-4.293
UTF-4.030
osph-4.014
py-3.757
Token Pony
Token ID30377
Feature activation-5.41e+00

Pos logit contributions
ellar+1.969
yrinth+1.937
 Priv+1.638
 Balloon+1.616
 Doodle+1.601
Neg logit contributions
 UCS-2.734
�士-2.689
UTF-2.670
osph-2.575
py-2.498
Token[/
Token ID13412
Feature activation+3.04e+00

Pos logit contributions
 UCS+3.709
UTF+3.459
�士+3.438
py+3.318
osph+3.318
Neg logit contributions
ellar-4.203
yrinth-4.114
 Klux-3.446
 Priv-3.430
----------3.361
Tokenb
Token ID65
Feature activation+2.00e+00

Pos logit contributions
ellar+1.989
yrinth+1.919
 Priv+1.614
BW+1.601
 Balloon+1.588
Neg logit contributions
 UCS-2.438
�士-2.419
UTF-2.329
osph-2.224
py-2.161
Token][/
Token ID44926
Feature activation+1.41e+01

Pos logit contributions
ellar+1.461
yrinth+1.424
 Priv+1.219
 Balloon+1.203
 Klux+1.191
Neg logit contributions
 UCS-1.443
�士-1.416
UTF-1.377
osph-1.315
py-1.285
Tokencolor
Token ID8043
Feature activation+8.93e-01

Pos logit contributions
ellar+2.867
yrinth+1.746
BW+1.527
night+1.358
---------+1.274
Neg logit contributions
�士-18.569
 UCS-16.496
senal-15.836
UTF-15.606
-15.291
Token]
Token ID60
Feature activation+3.61e+00

Pos logit contributions
ellar+0.640
yrinth+0.627
 Priv+0.532
 Balloon+0.524
 Klux+0.520
Neg logit contributions
 UCS-0.660
�士-0.642
UTF-0.634
osph-0.604
py-0.591
Token -
Token ID532
Feature activation+5.89e+00

Pos logit contributions
ellar+2.059
yrinth+2.056
 Balloon+1.667
 Priv+1.664
---------+1.605
Neg logit contributions
 UCS-3.127
�士-3.042
UTF-3.004
osph-2.932
py-2.822
Token 20
Token ID1160
Feature activation+2.52e+00

Pos logit contributions
yrinth+3.259
ellar+3.200
 Balloon+2.735
 Priv+2.661
 drag+2.549
Neg logit contributions
 UCS-5.028
�士-5.020
UTF-4.960
osph-4.811
py-4.572
Token%
Token ID4
Feature activation+2.44e+00

Pos logit contributions
ellar+1.517
yrinth+1.486
 Balloon+1.230
 Priv+1.223
BW+1.195
Neg logit contributions
 UCS-2.118
�士-2.060
UTF-2.044
osph-1.955
py-1.888
Token A
Token ID317
Feature activation+2.93e+00

Pos logit contributions
ellar+1.944
yrinth+1.926
 Priv+1.709
 Balloon+1.635
 Doodle+1.606
Neg logit contributions
 UCS-2.186
�士-2.151
UTF-2.134
osph-2.049
py-2.000
Token Novel
Token ID24467
Feature activation-1.72e+00

Pos logit contributions
ellar+1.972
yrinth+1.952
 Priv+1.703
 Balloon+1.647
 Doodle+1.613
Neg logit contributions
 UCS-2.218
�士-2.186
UTF-2.179
osph-2.082
py-2.019
Token (
Token ID357
Feature activation+7.46e+00

Pos logit contributions
 UCS+1.328
UTF+1.274
�士+1.270
osph+1.214
py+1.199
Neg logit contributions
ellar-1.178
yrinth-1.157
 Priv-0.966
 Balloon-0.953
 Klux-0.952
TokenNew
Token ID3791
Feature activation+4.37e+00

Pos logit contributions
ellar+4.827
yrinth+4.715
 Priv+4.067
BW+4.061
---------+4.031
Neg logit contributions
�士-5.456
 UCS-5.456
UTF-5.165
osph-5.159
py-4.901
Token York
Token ID1971
Feature activation+4.15e+00

Pos logit contributions
ellar+2.532
yrinth+2.505
 Priv+2.111
 Balloon+2.012
 Klux+1.934
Neg logit contributions
 UCS-3.690
UTF-3.662
�士-3.623
osph-3.465
py-3.383
Token:
Token ID25
Feature activation+1.40e+01

Pos logit contributions
ellar+2.697
yrinth+2.609
 Priv+2.238
 Balloon+2.185
 Doodle+2.127
Neg logit contributions
 UCS-3.226
�士-3.181
UTF-3.127
osph-3.009
py-2.986
Token St
Token ID520
Feature activation+6.11e+00

Pos logit contributions
ellar+8.046
 Priv+8.015
yrinth+7.435
 Balloon+7.377
 Band+7.222
Neg logit contributions
osph-9.812
�士-9.803
UTF-9.562
amera-9.422
 UCS-9.302
Token.
Token ID13
Feature activation+7.66e+00

Pos logit contributions
ellar+4.164
yrinth+3.833
 Priv+3.296
 Klux+3.165
---------+3.163
Neg logit contributions
 UCS-4.757
�士-4.641
UTF-4.547
py-4.264
-4.175
Token Martin
Token ID5780
Feature activation+1.14e+01

Pos logit contributions
ellar+3.256
yrinth+2.838
 Priv+2.536
 Balloon+2.266
 Doodle+2.193
Neg logit contributions
 UCS-7.528
�士-7.475
UTF-7.342
osph-6.993
py-6.988
Token
Token ID447
Feature activation+7.19e-01

Pos logit contributions
ellar+5.976
yrinth+5.567
 Priv+4.962
)--+4.866
 Balloon+4.761
Neg logit contributions
�士-9.539
UTF-9.456
 UCS-9.378
amera-8.968
py-8.909
Token
Token ID247
Feature activation+1.60e-01

Pos logit contributions
ellar+0.501
yrinth+0.491
 Priv+0.415
 Balloon+0.408
 Klux+0.405
Neg logit contributions
 UCS-0.548
UTF-0.522
�士-0.507
osph-0.493
py-0.489
Token but
Token ID475
Feature activation+3.22e+00

Pos logit contributions
ellar+2.233
yrinth+2.173
 Priv+1.859
 Balloon+1.831
 drag+1.799
Neg logit contributions
 UCS-2.638
�士-2.588
UTF-2.564
osph-2.434
py-2.386
Token typically
Token ID6032
Feature activation+9.46e+00

Pos logit contributions
ellar+2.086
yrinth+2.016
 Priv+1.722
 Balloon+1.710
 Klux+1.668
Neg logit contributions
 UCS-2.562
�士-2.502
UTF-2.481
osph-2.373
py-2.335
Token got
Token ID1392
Feature activation+9.85e+00

Pos logit contributions
ellar+5.548
yrinth+5.182
 drag+4.715
 Balloon+4.668
 Priv+4.645
Neg logit contributions
�士-7.365
 UCS-7.297
UTF-7.257
osph-6.941
py-6.699
Token his
Token ID465
Feature activation+8.85e+00

Pos logit contributions
ellar+5.770
yrinth+5.513
 drag+4.899
 Priv+4.820
 Balloon+4.765
Neg logit contributions
�士-7.662
UTF-7.641
 UCS-7.587
osph-7.323
py-6.980
Token best
Token ID1266
Feature activation+9.84e+00

Pos logit contributions
ellar+5.007
yrinth+4.591
 drag+4.212
 Balloon+4.145
 Priv+4.137
Neg logit contributions
�士-7.404
 UCS-7.127
UTF-7.104
osph-6.916
py-6.492
Token results
Token ID2482
Feature activation+1.39e+01

Pos logit contributions
ellar+5.510
yrinth+4.965
 drag+4.606
 Priv+4.494
night+4.395
Neg logit contributions
�士-8.112
 UCS-7.916
UTF-7.870
osph-7.653
py-7.321
Token at
Token ID379
Feature activation+6.78e+00

Pos logit contributions
ellar+6.882
yrinth+6.259
night+5.820
 drag+5.797
 Balloon+5.670
Neg logit contributions
�士-12.042
 UCS-11.237
UTF-11.033
osph-10.501
pu-10.074
Token night
Token ID1755
Feature activation+8.64e+00

Pos logit contributions
ellar+3.674
yrinth+3.540
 Balloon+3.072
 Priv+3.049
 drag+2.963
Neg logit contributions
UTF-5.803
�士-5.798
 UCS-5.648
osph-5.515
py-5.334
Token when
Token ID618
Feature activation+3.69e+00

Pos logit contributions
ellar+5.067
yrinth+4.886
 Balloon+4.244
[_+4.208
 drag+4.181
Neg logit contributions
�士-6.943
 UCS-6.855
UTF-6.684
osph-6.236
pu-6.108
Token the
Token ID262
Feature activation+3.62e+00

Pos logit contributions
ellar+2.304
yrinth+2.202
 Priv+1.875
 Balloon+1.866
 drag+1.829
Neg logit contributions
 UCS-2.999
�士-2.967
UTF-2.919
osph-2.798
py-2.767
Token airport
Token ID9003
Feature activation-6.44e-01

Pos logit contributions
ellar+2.691
yrinth+2.619
 Priv+2.293
 Balloon+2.292
 drag+2.268
Neg logit contributions
 UCS-2.493
�士-2.483
UTF-2.408
osph-2.289
py-2.251
Token we
Token ID356
Feature activation-3.69e-01

Pos logit contributions
 UCS+2.127
UTF+2.030
�士+2.020
osph+1.935
py+1.913
Neg logit contributions
ellar-1.900
yrinth-1.861
 Priv-1.550
 Balloon-1.532
 Klux-1.527
Token must
Token ID1276
Feature activation+1.37e+00

Pos logit contributions
 UCS+0.241
�士+0.232
UTF+0.232
osph+0.217
py+0.213
Neg logit contributions
ellar-0.295
yrinth-0.291
 Priv-0.252
 Balloon-0.248
 Klux-0.247
Token place
Token ID1295
Feature activation+1.26e+00

Pos logit contributions
ellar+0.920
yrinth+0.904
 Priv+0.763
 drag+0.747
 Balloon+0.747
Neg logit contributions
 UCS-1.061
�士-1.042
UTF-1.033
osph-0.967
py-0.959
Token it
Token ID340
Feature activation+4.34e+00

Pos logit contributions
ellar+0.825
yrinth+0.815
 Priv+0.692
 Balloon+0.670
 Klux+0.669
Neg logit contributions
 UCS-0.989
�士-0.971
UTF-0.967
osph-0.922
py-0.902
Token front
Token ID2166
Feature activation+2.81e+00

Pos logit contributions
yrinth+2.655
ellar+2.655
 Priv+2.247
 drag+2.220
 Klux+2.172
Neg logit contributions
 UCS-3.499
�士-3.464
UTF-3.436
osph-3.233
py-3.143
Token and
Token ID290
Feature activation+1.39e+01

Pos logit contributions
ellar+1.872
yrinth+1.822
 Priv+1.502
 drag+1.489
 Klux+1.467
Neg logit contributions
 UCS-2.229
�士-2.169
UTF-2.159
osph-2.029
py-1.975
Token center
Token ID3641
Feature activation-1.12e+00

Pos logit contributions
ellar+2.334
 drag+1.464
yrinth+1.028
 wing+0.876
 queens+0.833
Neg logit contributions
�士-16.803
UTF-16.367
 UCS-16.363
osph-15.807
-15.421
Token.
Token ID13
Feature activation-2.56e+00

Pos logit contributions
 UCS+0.839
UTF+0.806
�士+0.805
osph+0.766
py+0.755
Neg logit contributions
ellar-0.786
yrinth-0.773
 Priv-0.652
 Balloon-0.642
 Klux-0.639
Token Dec
Token ID4280
Feature activation+1.50e+00

Pos logit contributions
 UCS+1.910
UTF+1.815
�士+1.799
osph+1.714
py+1.705
Neg logit contributions
ellar-1.845
yrinth-1.814
 Klux-1.499
 Priv-1.493
 Balloon-1.482
Tokenades
Token ID2367
Feature activation-8.81e-01

Pos logit contributions
ellar+0.943
yrinth+0.916
 Priv+0.753
 Klux+0.738
 Balloon+0.732
Neg logit contributions
 UCS-1.245
�士-1.219
UTF-1.211
osph-1.134
py-1.121
Token ago
Token ID2084
Feature activation+2.46e-01

Pos logit contributions
 UCS+0.693
�士+0.669
UTF+0.668
osph+0.636
py+0.625
Neg logit contributions
ellar-0.589
yrinth-0.579
 Priv-0.485
 Balloon-0.477
 Klux-0.475
Token a
Token ID257
Feature activation+4.01e+00

Pos logit contributions
yrinth+3.019
ellar+2.999
 Priv+2.573
 Balloon+2.499
 Klux+2.468
Neg logit contributions
�士-4.285
UTF-4.258
 UCS-4.256
osph-4.064
py-3.936
Token lawsuit
Token ID8087
Feature activation+4.26e+00

Pos logit contributions
ellar+2.482
yrinth+2.455
 Priv+2.143
 Balloon+2.072
 Doodle+2.035
Neg logit contributions
�士-3.199
UTF-3.179
 UCS-3.174
osph-3.015
py-2.912
Token against
Token ID1028
Feature activation+3.41e+00

Pos logit contributions
ellar+2.874
yrinth+2.844
 Priv+2.478
 Balloon+2.405
 drag+2.377
Neg logit contributions
�士-3.166
 UCS-3.153
UTF-3.122
osph-2.932
py-2.865
Token New
Token ID968
Feature activation+3.24e+00

Pos logit contributions
ellar+2.189
yrinth+2.149
 Priv+1.878
 Balloon+1.802
 drag+1.780
Neg logit contributions
 UCS-2.649
�士-2.642
UTF-2.642
osph-2.520
py-2.435
Token York
Token ID1971
Feature activation+8.95e-01

Pos logit contributions
ellar+2.002
yrinth+1.941
 Priv+1.643
 Balloon+1.572
 Klux+1.560
Neg logit contributions
 UCS-2.704
UTF-2.639
�士-2.620
osph-2.507
py-2.440
Token Governor
Token ID10807
Feature activation+1.39e+01

Pos logit contributions
ellar+0.698
yrinth+0.683
 Priv+0.599
 Balloon+0.587
 Klux+0.585
Neg logit contributions
 UCS-0.600
UTF-0.583
�士-0.576
osph-0.546
py-0.532
Token Andrew
Token ID6858
Feature activation+4.45e+00

Pos logit contributions
ellar+8.384
 Priv+7.282
yrinth+7.120
[_+6.808
 Balloon+6.785
Neg logit contributions
 UCS-10.511
UTF-10.359
�士-10.293
osph-9.523
pu-9.503
Token Cuomo
Token ID32496
Feature activation+2.51e+00

Pos logit contributions
ellar+2.686
yrinth+2.518
 Priv+2.219
 Balloon+2.149
 Klux+2.087
Neg logit contributions
 UCS-3.767
�士-3.647
UTF-3.632
osph-3.487
py-3.392
Token;
Token ID26
Feature activation+2.45e+00

Pos logit contributions
ellar+1.771
yrinth+1.739
 Priv+1.511
 Balloon+1.471
 Klux+1.451
Neg logit contributions
 UCS-1.837
�士-1.791
UTF-1.775
osph-1.673
py-1.649
Token Janet
Token ID28111
Feature activation-3.89e+00

Pos logit contributions
ellar+1.657
yrinth+1.623
 Priv+1.405
 Balloon+1.362
 Klux+1.340
Neg logit contributions
 UCS-1.857
UTF-1.839
�士-1.827
osph-1.743
py-1.699
Token Di
Token ID6031
Feature activation-1.39e+00

Pos logit contributions
 UCS+2.971
UTF+2.834
�士+2.827
osph+2.709
py+2.680
Neg logit contributions
ellar-2.697
yrinth-2.664
 Priv-2.202
 Klux-2.175
 Balloon-2.173
Token laws
Token ID3657
Feature activation+2.93e+00

Pos logit contributions
ellar+2.814
yrinth+2.740
 Priv+2.369
 drag+2.286
 Klux+2.284
Neg logit contributions
�士-3.115
 UCS-3.105
UTF-3.072
osph-2.932
py-2.832
Token prohibiting
Token ID30363
Feature activation-1.94e+00

Pos logit contributions
ellar+1.970
yrinth+1.935
 Priv+1.664
 drag+1.620
 Balloon+1.611
Neg logit contributions
 UCS-2.244
�士-2.222
UTF-2.188
osph-2.050
py-2.017
Token needle
Token ID17598
Feature activation+5.14e+00

Pos logit contributions
 UCS+1.535
UTF+1.475
�士+1.469
osph+1.406
py+1.388
Neg logit contributions
ellar-1.299
yrinth-1.278
 Priv-1.061
 Balloon-1.047
 Klux-1.041
Token exchanges
Token ID14525
Feature activation+5.71e+00

Pos logit contributions
ellar+2.974
yrinth+2.800
 drag+2.476
 Priv+2.450
 Klux+2.361
Neg logit contributions
�士-4.352
 UCS-4.337
UTF-4.302
osph-4.033
py-3.922
Token and
Token ID290
Feature activation+3.33e+00

Pos logit contributions
ellar+3.631
yrinth+3.584
 Priv+3.127
 drag+3.106
 Balloon+2.992
Neg logit contributions
�士-4.494
 UCS-4.390
UTF-4.315
osph-4.011
py-3.902
Token sy
Token ID827
Feature activation+1.37e+01

Pos logit contributions
ellar+2.228
yrinth+2.163
 Priv+1.865
 drag+1.830
 Klux+1.801
Neg logit contributions
 UCS-2.547
�士-2.523
UTF-2.516
osph-2.400
py-2.325
Tokenringe
Token ID38229
Feature activation+1.18e+00

Pos logit contributions
ellar+4.036
yrinth+3.743
sted+2.550
ever+2.303
apor+2.188
Neg logit contributions
�士-15.808
UTF-15.411
 UCS-15.189
-13.904
osph-13.716
Token possession
Token ID7797
Feature activation+2.51e+00

Pos logit contributions
ellar+0.764
yrinth+0.739
 Priv+0.634
 Balloon+0.615
 drag+0.614
Neg logit contributions
 UCS-0.937
�士-0.925
UTF-0.918
osph-0.870
py-0.849
Token without
Token ID1231
Feature activation+2.94e+00

Pos logit contributions
ellar+1.712
yrinth+1.679
 Priv+1.442
 drag+1.410
 Balloon+1.401
Neg logit contributions
 UCS-1.905
�士-1.881
UTF-1.850
osph-1.740
py-1.703
Token prescriptions
Token ID34092
Feature activation+2.45e+00

Pos logit contributions
ellar+1.863
yrinth+1.836
 Priv+1.548
 Balloon+1.490
 drag+1.483
Neg logit contributions
�士-2.351
 UCS-2.340
UTF-2.311
osph-2.219
py-2.160
Token have
Token ID423
Feature activation+1.89e+00

Pos logit contributions
ellar+1.694
yrinth+1.661
 Priv+1.427
 drag+1.397
 Balloon+1.393
Neg logit contributions
 UCS-1.839
�士-1.822
UTF-1.784
osph-1.676
py-1.644
Token.
Token ID13
Feature activation+7.21e+00

Pos logit contributions
ellar+5.755
yrinth+5.049
 Priv+4.953
[_+4.826
---------+4.746
Neg logit contributions
�士-10.763
 UCS-9.378
UTF-9.158
senal-9.144
osph-9.060
Token View
Token ID3582
Feature activation+8.46e+00

Pos logit contributions
ellar+2.474
yrinth+2.220
 Priv+1.897
 Balloon+1.718
BW+1.639
Neg logit contributions
�士-7.717
 UCS-7.660
UTF-7.594
osph-7.423
py-7.149
Token all
Token ID477
Feature activation+1.19e+01

Pos logit contributions
ellar+4.715
yrinth+4.392
 Priv+4.064
 drag+4.045
BW+3.823
Neg logit contributions
�士-7.472
UTF-6.946
 UCS-6.920
osph-6.631
py-6.409
Token New
Token ID968
Feature activation+8.88e+00

Pos logit contributions
ellar+3.809
 Priv+3.561
 Balloon+3.019
yrinth+3.001
BW+2.912
Neg logit contributions
�士-12.950
osph-11.871
UTF-11.858
 UCS-11.677
senal-11.250
Token York
Token ID1971
Feature activation+4.68e+00

Pos logit contributions
ellar+4.254
yrinth+3.903
 Priv+3.784
BW+3.438
---------+3.429
Neg logit contributions
�士-8.528
UTF-7.798
 UCS-7.779
osph-7.502
pu-7.235
Token Times
Token ID3782
Feature activation+1.37e+01

Pos logit contributions
ellar+3.401
yrinth+3.267
 Priv+2.969
 Balloon+2.891
 Klux+2.864
Neg logit contributions
�士-3.349
 UCS-3.205
UTF-3.115
osph-3.002
py-2.871
Token newsletters
Token ID16983
Feature activation+3.17e+00

Pos logit contributions
ellar+4.012
 Priv+3.800
yrinth+3.529
 drag+3.250
---------+3.178
Neg logit contributions
�士-15.277
UTF-13.712
 UCS-13.612
osph-13.517
pu-13.089
Token.
Token ID13
Feature activation+9.27e+00

Pos logit contributions
ellar+2.238
yrinth+2.156
 Priv+1.874
 Balloon+1.828
---------+1.811
Neg logit contributions
�士-2.361
 UCS-2.358
UTF-2.266
osph-2.167
py-2.112
Token
Token ID198
Feature activation-6.33e-01

Pos logit contributions
ellar+4.789
yrinth+4.210
 Priv+4.014
---------+3.895
BW+3.849
Neg logit contributions
�士-8.942
 UCS-7.891
UTF-7.760
osph-7.754
senal-7.434
Token
Token ID198
Feature activation-8.69e-01

Pos logit contributions
 UCS+0.468
UTF+0.449
�士+0.427
py+0.423
osph+0.421
Neg logit contributions
yrinth-0.458
ellar-0.457
 Priv-0.376
 Klux-0.375
 Balloon-0.374
TokenFor
Token ID1890
Feature activation+1.15e+00

Pos logit contributions
 UCS+0.642
�士+0.618
UTF+0.614
osph+0.587
py+0.574
Neg logit contributions
ellar-0.623
yrinth-0.611
 Priv-0.519
 Balloon-0.510
 Klux-0.508
Token requests
Token ID7007
Feature activation+2.90e+00

Pos logit contributions
ellar+2.851
yrinth+2.843
 Priv+2.451
 Balloon+2.322
 Klux+2.303
Neg logit contributions
�士-4.158
 UCS-4.108
UTF-4.057
osph-3.905
py-3.820
Token for
Token ID329
Feature activation+8.85e+00

Pos logit contributions
ellar+1.840
yrinth+1.795
 Priv+1.540
 drag+1.486
 Klux+1.482
Neg logit contributions
 UCS-2.326
�士-2.296
UTF-2.234
osph-2.151
py-2.104
Token comment
Token ID2912
Feature activation-9.40e-02

Pos logit contributions
ellar+3.857
yrinth+3.530
 Priv+3.049
---------+2.904
 intrusion+2.866
Neg logit contributions
�士-8.267
osph-8.203
 UCS-8.199
UTF-8.111
py-7.805
Token and
Token ID290
Feature activation+5.12e+00

Pos logit contributions
 UCS+0.069
�士+0.067
UTF+0.066
osph+0.063
py+0.062
Neg logit contributions
ellar-0.068
yrinth-0.067
 Priv-0.057
 Balloon-0.056
 Klux-0.056
Token Boh
Token ID44366
Feature activation-8.91e-01

Pos logit contributions
yrinth+3.276
ellar+3.251
 Priv+2.988
 Balloon+2.771
---------+2.701
Neg logit contributions
�士-3.952
 UCS-3.947
UTF-3.891
osph-3.664
py-3.573
Tokenoli
Token ID11106
Feature activation+1.37e+01

Pos logit contributions
 UCS+0.627
�士+0.601
UTF+0.599
osph+0.559
py+0.552
Neg logit contributions
ellar-0.678
yrinth-0.666
 Priv-0.568
 Balloon-0.560
 Klux-0.558
Tokenub
Token ID549
Feature activation+2.13e+00

Pos logit contributions
ellar+6.051
yrinth+5.832
 Priv+4.992
BW+4.678
 Klux+4.671
Neg logit contributions
�士-13.087
 UCS-12.080
UTF-11.442
-10.762
osph-10.603
Tokenov
Token ID709
Feature activation+1.44e-01

Pos logit contributions
ellar+1.372
yrinth+1.343
 Priv+1.114
 Balloon+1.092
 Klux+1.087
Neg logit contributions
 UCS-1.730
�士-1.699
UTF-1.670
osph-1.582
py-1.558
Token could
Token ID714
Feature activation+5.45e+00

Pos logit contributions
ellar+0.094
yrinth+0.092
 Priv+0.077
 Balloon+0.075
 Klux+0.075
Neg logit contributions
 UCS-0.116
�士-0.112
UTF-0.112
osph-0.106
py-0.105
Token not
Token ID407
Feature activation+4.79e+00

Pos logit contributions
ellar+3.366
yrinth+3.194
 drag+2.713
 Priv+2.704
 Balloon+2.665
Neg logit contributions
�士-4.527
 UCS-4.499
UTF-4.413
osph-4.124
py-4.029
Token be
Token ID307
Feature activation-2.43e-01

Pos logit contributions
ellar+2.949
yrinth+2.819
 drag+2.401
 Priv+2.400
 Balloon+2.349
Neg logit contributions
 UCS-3.946
�士-3.911
UTF-3.849
osph-3.619
py-3.561
Token Simon
Token ID11288
Feature activation+9.38e+00

Pos logit contributions
ellar+0.630
yrinth+0.617
 Priv+0.537
 Balloon+0.525
 Doodle+0.517
Neg logit contributions
 UCS-0.653
�士-0.642
UTF-0.635
osph-0.608
py-0.589
Token Gerr
Token ID45140
Feature activation+3.80e+00

Pos logit contributions
ellar+5.493
yrinth+4.991
 Priv+4.692
 Balloon+4.531
 Doodle+4.380
Neg logit contributions
�士-7.759
UTF-7.501
 UCS-7.282
osph-6.959
py-6.728
Tokenans
Token ID504
Feature activation+3.06e+00

Pos logit contributions
ellar+3.230
yrinth+3.147
 Priv+2.755
 Balloon+2.712
 Klux+2.704
Neg logit contributions
 UCS-2.289
�士-2.209
UTF-2.184
osph-2.038
py-2.011
Token (
Token ID357
Feature activation+5.90e+00

Pos logit contributions
ellar+1.977
yrinth+1.903
 Priv+1.641
 Balloon+1.599
BW+1.587
Neg logit contributions
�士-2.425
 UCS-2.412
UTF-2.357
osph-2.276
py-2.201
TokenGreen
Token ID13719
Feature activation+1.01e+01

Pos logit contributions
ellar+3.564
yrinth+3.210
BW+3.019
 Priv+2.932
LG+2.919
Neg logit contributions
�士-5.005
 UCS-4.823
osph-4.654
UTF-4.437
py-4.362
TokenEdge
Token ID37021
Feature activation+1.37e+01

Pos logit contributions
ellar+3.679
yrinth+3.277
BW+2.700
 Priv+2.666
 drag+2.572
Neg logit contributions
�士-10.877
 UCS-10.587
UTF-10.130
osph-9.776
py-9.624
Token Cycling
Token ID25550
Feature activation+2.24e+00

Pos logit contributions
ellar+3.577
yrinth+2.782
 Priv+2.772
 Balloon+2.539
)--+2.452
Neg logit contributions
�士-15.410
UTF-14.333
osph-13.910
 UCS-13.853
py-13.391
Token Team
Token ID4816
Feature activation+3.41e+00

Pos logit contributions
ellar+1.232
yrinth+1.194
 Priv+0.975
 Balloon+0.949
 Klux+0.933
Neg logit contributions
 UCS-2.022
�士-1.987
UTF-1.964
osph-1.888
py-1.855
Token)
Token ID8
Feature activation+1.67e+00

Pos logit contributions
ellar+2.063
yrinth+1.958
 Priv+1.671
 Balloon+1.625
---------+1.620
Neg logit contributions
�士-2.901
 UCS-2.868
UTF-2.760
osph-2.662
py-2.587
Token s
Token ID264
Feature activation-1.51e+00

Pos logit contributions
ellar+1.246
yrinth+1.226
 Priv+1.060
 Balloon+1.038
 drag+1.027
Neg logit contributions
 UCS-1.167
UTF-1.127
�士-1.120
osph-1.071
py-1.054
Token.
Token ID13
Feature activation-1.47e+00

Pos logit contributions
 UCS+1.022
UTF+0.979
�士+0.921
py+0.914
osph+0.912
Neg logit contributions
yrinth-1.189
ellar-1.180
 Priv-0.993
 Klux-0.991
 Balloon-0.987
Token's
Token ID338
Feature activation+2.11e+00

Pos logit contributions
ellar+0.759
yrinth+0.742
 Priv+0.630
 Balloon+0.622
 drag+0.616
Neg logit contributions
 UCS-0.825
�士-0.799
UTF-0.796
osph-0.754
py-0.739
Token the
Token ID262
Feature activation+3.08e+00

Pos logit contributions
ellar+1.401
yrinth+1.366
 Priv+1.155
 drag+1.133
 Balloon+1.131
Neg logit contributions
 UCS-1.654
�士-1.618
UTF-1.610
osph-1.534
py-1.492
Token largest
Token ID4387
Feature activation+1.13e+01

Pos logit contributions
ellar+1.938
yrinth+1.888
 Priv+1.610
 Balloon+1.596
 drag+1.575
Neg logit contributions
 UCS-2.443
�士-2.440
UTF-2.413
osph-2.297
py-2.245
Token crocod
Token ID37565
Feature activation+4.73e+00

Pos logit contributions
ellar+6.087
yrinth+5.607
 drag+5.418
 intrusion+5.048
 Balloon+4.998
Neg logit contributions
�士-9.199
UTF-8.912
 UCS-8.765
osph-8.542
pu-8.079
Tokenile
Token ID576
Feature activation+8.80e+00

Pos logit contributions
ellar+2.714
yrinth+2.617
 Priv+2.014
 drag+1.991
---------+1.980
Neg logit contributions
 UCS-4.238
�士-4.157
UTF-4.096
osph-3.806
-3.780
Token ever
Token ID1683
Feature activation+1.36e+01

Pos logit contributions
ellar+4.823
yrinth+4.598
 drag+4.216
 intrusion+3.966
 Priv+3.943
Neg logit contributions
�士-7.449
UTF-7.099
 UCS-7.015
osph-6.854
pu-6.481
Token to
Token ID284
Feature activation+6.73e+00

Pos logit contributions
ellar+6.642
 drag+5.963
yrinth+5.721
 Priv+5.390
 queens+5.336
Neg logit contributions
�士-12.116
UTF-11.152
 UCS-10.944
osph-10.683
pu-10.039
Token be
Token ID307
Feature activation+5.86e+00

Pos logit contributions
ellar+4.241
yrinth+4.073
 drag+3.664
 Priv+3.502
 Balloon+3.450
Neg logit contributions
�士-5.306
 UCS-5.264
UTF-5.243
osph-4.834
py-4.792
Token taken
Token ID2077
Feature activation+5.65e+00

Pos logit contributions
ellar+3.383
yrinth+3.263
 drag+2.847
 Priv+2.776
 Balloon+2.720
Neg logit contributions
�士-4.933
 UCS-4.855
UTF-4.805
osph-4.609
py-4.449
Token alive
Token ID6776
Feature activation+7.54e+00

Pos logit contributions
ellar+3.606
yrinth+3.461
 drag+3.107
 Priv+3.086
 Balloon+3.049
Neg logit contributions
�士-4.460
 UCS-4.290
UTF-4.205
osph-4.054
pu-3.917
Token.
Token ID13
Feature activation+1.60e+00

Pos logit contributions
ellar+4.281
yrinth+4.133
 drag+3.675
 Balloon+3.610
 Priv+3.559
Neg logit contributions
�士-6.362
 UCS-6.025
UTF-5.935
osph-5.659
pu-5.528
Token a
Token ID257
Feature activation-1.19e+01

Pos logit contributions
 UCS+3.464
UTF+3.284
py+3.139
osph+3.054
pu+3.026
Neg logit contributions
yrinth-3.961
ellar-3.827
 Klux-3.154
 Priv-3.148
 Doodle-3.145
Token skillet
Token ID41306
Feature activation-1.26e+01

Pos logit contributions
 UCS+5.495
UTF+5.311
py+5.062
osph+4.802
pu+4.766
Neg logit contributions
yrinth-11.268
ellar-10.952
 Doodle-9.639
 Priv-9.583
 msec-9.473
Token over
Token ID625
Feature activation-6.01e+00

Pos logit contributions
 UCS+6.046
UTF+5.738
py+5.660
osph+5.363
pu+5.067
Neg logit contributions
yrinth-11.798
ellar-11.180
 Doodle-9.948
 Balloon-9.555
 Priv-9.418
Token medium
Token ID7090
Feature activation-7.76e+00

Pos logit contributions
 UCS+3.105
UTF+2.831
py+2.649
osph+2.638
pu+2.538
Neg logit contributions
yrinth-5.745
ellar-5.660
 Doodle-4.947
 Priv-4.854
 Balloon-4.786
Token-
Token ID12
Feature activation-1.11e+01

Pos logit contributions
 UCS+4.469
UTF+4.302
py+4.049
osph+3.951
pu+3.904
Neg logit contributions
yrinth-6.886
ellar-6.588
 Doodle-5.695
 Balloon-5.617
 Priv-5.606
Tokenhigh
Token ID8929
Feature activation-1.98e+01

Pos logit contributions
UTF+3.670
py+3.552
 UCS+3.478
pu+3.250
osph+3.117
Neg logit contributions
yrinth-11.868
ellar-11.715
 Doodle-11.264
 Balloon-10.600
 Priv-10.497
Token heat
Token ID4894
Feature activation-1.24e+01

Pos logit contributions
osph+4.371
py+4.361
UTF+4.358
 UCS+4.014
pu+3.603
Neg logit contributions
yrinth-22.110
ellar-20.360
 Doodle-18.976
idav-18.960
 eleph-18.613
Token.
Token ID13
Feature activation-9.85e+00

Pos logit contributions
 UCS+5.649
UTF+5.274
py+5.111
osph+4.736
pu+4.694
Neg logit contributions
yrinth-12.066
ellar-11.133
 eleph-10.501
 Klux-9.859
 Doodle-9.572
Token Place
Token ID8474
Feature activation-1.30e+01

Pos logit contributions
 UCS+7.531
py+7.119
UTF+7.070
osph+7.057
pu+6.763
Neg logit contributions
yrinth-6.666
ellar-6.432
 queens-5.045
BW-5.029
 Klux-4.962
Token f
Token ID277
Feature activation-1.19e+01

Pos logit contributions
 UCS+6.410
py+5.934
UTF+5.905
pu+5.634
osph+5.287
Neg logit contributions
yrinth-11.982
ellar-11.714
BW-9.805
 Priv-9.795
 Doodle-9.755
Tokenrit
Token ID799
Feature activation-7.59e+00

Pos logit contributions
pu+4.565
osph+4.561
UTF+4.522
py+4.516
 UCS+4.237
Neg logit contributions
yrinth-11.472
ellar-11.204
 eleph-10.755
 Doodle-10.666
 Balloon-10.441
Tokent
Token ID83
Feature activation-3.28e+00

Pos logit contributions
py+7.216
pu+6.901
UTF+6.744
 UCS+6.708
osph+6.629
Neg logit contributions
yrinth-8.434
ellar-7.951
 Balloon-6.948
 Priv-6.859
 eleph-6.857
Token crowd
Token ID4315
Feature activation-5.07e+00

Pos logit contributions
 UCS+2.282
UTF+2.167
osph+2.085
py+2.067
�士+2.035
Neg logit contributions
ellar-2.467
yrinth-2.465
 Balloon-2.061
 Priv-2.058
 Klux-2.022
Token the
Token ID262
Feature activation-9.13e+00

Pos logit contributions
 UCS+3.444
UTF+3.205
py+3.070
osph+3.000
pu+2.962
Neg logit contributions
yrinth-4.085
ellar-3.873
 Klux-3.290
 Balloon-3.240
 Priv-3.223
Token pan
Token ID3425
Feature activation-5.24e+00

Pos logit contributions
 UCS+4.034
py+3.734
UTF+3.620
pu+3.469
osph+3.360
Neg logit contributions
yrinth-9.397
ellar-8.837
 Doodle-7.749
idav-7.662
 Klux-7.657
Token;
Token ID26
Feature activation-7.56e+00

Pos logit contributions
 UCS+3.142
UTF+2.984
py+2.796
pu+2.687
osph+2.685
Neg logit contributions
yrinth-4.564
ellar-4.419
 Klux-3.738
 Balloon-3.715
 queens-3.660
Token only
Token ID691
Feature activation-1.86e+01

Pos logit contributions
 UCS+5.812
UTF+5.520
py+5.518
osph+5.338
pu+5.298
Neg logit contributions
yrinth-5.117
ellar-4.838
 Priv-4.017
 Klux-3.969
 Balloon-3.940
Token cook
Token ID4255
Feature activation-1.11e+01

Pos logit contributions
py+4.866
UTF+4.608
osph+4.476
 UCS+4.296
pu+3.608
Neg logit contributions
yrinth-19.620
ellar-18.215
 Priv-16.611
 Balloon-16.536
BW-16.368
Token about
Token ID546
Feature activation-5.97e+00

Pos logit contributions
 UCS+7.439
py+7.179
UTF+7.001
pu+6.759
osph+6.694
Neg logit contributions
yrinth-8.374
ellar-8.239
 Balloon-6.642
 Doodle-6.621
 Priv-6.580
Token 3
Token ID513
Feature activation-9.99e+00

Pos logit contributions
 UCS+3.412
UTF+3.107
py+2.966
pu+2.832
osph+2.768
Neg logit contributions
ellar-5.374
yrinth-5.346
 Klux-4.497
 Priv-4.473
 Doodle-4.401
Token f
Token ID277
Feature activation-1.29e+01

Pos logit contributions
 UCS+5.356
UTF+5.043
py+5.011
pu+4.799
osph+4.619
Neg logit contributions
yrinth-8.949
ellar-8.723
 Doodle-7.495
 Priv-7.349
BW-7.312
Tokenrit
Token ID799
Feature activation-6.33e+00

Pos logit contributions
py+5.109
pu+5.105
UTF+4.992
osph+4.892
 UCS+4.643
Neg logit contributions
yrinth-12.297
ellar-12.032
 eleph-11.619
 Doodle-11.515
 Balloon-11.256
TokenED
Token ID1961
Feature activation-9.51e-01

Pos logit contributions
 UCS+0.422
UTF+0.405
�士+0.394
osph+0.377
py+0.375
Neg logit contributions
yrinth-0.474
ellar-0.473
 Priv-0.398
 Klux-0.395
 Balloon-0.394
Token NET
Token ID30502
Feature activation+5.70e+00

Pos logit contributions
 UCS+0.746
UTF+0.720
�士+0.720
osph+0.689
py+0.677
Neg logit contributions
ellar-0.634
yrinth-0.623
 Priv-0.525
 Balloon-0.517
 Klux-0.509
Token CALL
Token ID42815
Feature activation-6.38e-01

Pos logit contributions
ellar+3.093
yrinth+2.807
 Priv+2.593
 Balloon+2.519
 Doodle+2.485
Neg logit contributions
�士-5.056
 UCS-4.920
UTF-4.857
osph-4.806
py-4.586
Token UPDATE
Token ID35717
Feature activation-3.99e+00

Pos logit contributions
 UCS+0.459
UTF+0.442
�士+0.442
osph+0.422
py+0.414
Neg logit contributions
ellar-0.466
yrinth-0.458
 Priv-0.392
 Balloon-0.387
 Klux-0.383
Token:
Token ID25
Feature activation-1.23e+00

Pos logit contributions
 UCS+2.630
UTF+2.472
py+2.273
�士+2.214
osph+2.208
Neg logit contributions
yrinth-3.321
ellar-3.228
 Klux-2.740
 Balloon-2.656
 Priv-2.653
Token 05
Token ID8870
Feature activation-1.68e+01

Pos logit contributions
 UCS+0.926
UTF+0.890
�士+0.888
osph+0.847
py+0.834
Neg logit contributions
ellar-0.868
yrinth-0.854
 Priv-0.720
 Balloon-0.710
 Klux-0.705
Token50
Token ID1120
Feature activation-1.48e+00

Pos logit contributions
 UCS+5.730
UTF+5.686
py+5.415
pu+5.077
+4.642
Neg logit contributions
yrinth-16.826
ellar-15.796
vernment-14.517
 intrusion-14.323
 Klux-14.222
Tokenz
Token ID89
Feature activation+1.33e+00

Pos logit contributions
 UCS+0.999
UTF+0.956
�士+0.927
osph+0.905
py+0.900
Neg logit contributions
ellar-1.154
yrinth-1.147
 Priv-0.975
 Balloon-0.967
 Klux-0.962
Token VOL
Token ID38570
Feature activation-1.45e+00

Pos logit contributions
ellar+0.911
yrinth+0.889
 Priv+0.777
 Balloon+0.758
BW+0.745
Neg logit contributions
 UCS-0.994
�士-0.980
UTF-0.974
osph-0.934
py-0.908
TokenUN
Token ID4944
Feature activation-1.70e+00

Pos logit contributions
 UCS+1.144
UTF+1.102
�士+1.095
osph+1.047
py+1.035
Neg logit contributions
ellar-0.973
yrinth-0.959
 Priv-0.795
 Balloon-0.784
 Klux-0.779
TokenTE
Token ID9328
Feature activation-1.92e+00

Pos logit contributions
 UCS+1.040
UTF+0.990
�士+0.988
osph+0.932
py+0.912
Neg logit contributions
ellar-1.432
yrinth-1.412
 Priv-1.228
 Balloon-1.214
 Klux-1.209
Token Le
Token ID1004
Feature activation-1.35e-01

Pos logit contributions
ellar+0.727
yrinth+0.707
 Priv+0.611
 Balloon+0.603
 Doodle+0.590
Neg logit contributions
 UCS-0.842
�士-0.837
UTF-0.820
osph-0.789
py-0.770
Tokena
Token ID64
Feature activation-6.22e+00

Pos logit contributions
 UCS+0.115
UTF+0.111
�士+0.109
osph+0.106
py+0.105
Neg logit contributions
ellar-0.082
yrinth-0.081
 Priv-0.066
 Balloon-0.065
 Klux-0.064
Token Suzuki
Token ID35807
Feature activation-4.72e+00

Pos logit contributions
 UCS+3.048
UTF+2.628
py+2.432
osph+2.357
�士+2.322
Neg logit contributions
yrinth-6.187
ellar-6.109
 Klux-5.253
BW-5.209
apor-5.179
Token,
Token ID11
Feature activation-5.56e+00

Pos logit contributions
 UCS+3.176
UTF+2.968
py+2.803
osph+2.711
pu+2.654
Neg logit contributions
yrinth-3.885
ellar-3.757
 Klux-3.181
 Priv-3.062
 Balloon-3.048
Token The
Token ID383
Feature activation-6.07e+00

Pos logit contributions
 UCS+3.675
UTF+3.316
py+3.149
osph+3.048
pu+3.007
Neg logit contributions
yrinth-4.677
ellar-4.505
 Klux-3.843
 queens-3.738
 intrusion-3.681
Token Chronicle
Token ID14160
Feature activation-1.63e+01

Pos logit contributions
 UCS+3.538
UTF+3.197
py+2.956
osph+2.893
�士+2.839
Neg logit contributions
yrinth-5.440
ellar-5.290
 Klux-4.540
 Balloon-4.443
 Priv-4.441
Token 4
Token ID604
Feature activation+1.44e+00

Pos logit contributions
 UCS+6.505
UTF+5.199
py+4.810
pu+4.212
osph+4.124
Neg logit contributions
yrinth-16.989
ellar-16.261
 eleph-14.757
 Klux-14.067
eatures-13.808
Token of
Token ID286
Feature activation-3.94e+00

Pos logit contributions
ellar+0.993
yrinth+0.974
 Priv+0.820
 Balloon+0.808
 Klux+0.802
Neg logit contributions
 UCS-1.108
�士-1.070
UTF-1.066
osph-1.016
py-0.999
Token 15
Token ID1315
Feature activation-3.37e+00

Pos logit contributions
 UCS+3.115
UTF+2.959
�士+2.776
py+2.761
osph+2.759
Neg logit contributions
yrinth-2.685
ellar-2.622
 Doodle-2.094
 Klux-2.084
 Priv-2.083
Token Photo
Token ID5555
Feature activation-8.10e+00

Pos logit contributions
 UCS+2.629
UTF+2.474
py+2.357
osph+2.342
�士+2.338
Neg logit contributions
yrinth-2.338
ellar-2.303
 Klux-1.860
BW-1.812
 Priv-1.804
Token:
Token ID25
Feature activation+7.10e-01

Pos logit contributions
 UCS+4.538
UTF+4.221
py+3.958
pu+3.856
+3.668
Neg logit contributions
yrinth-7.553
ellar-6.942
 eleph-6.189
 Klux-6.109
 Balloon-5.942
Token together
Token ID1978
Feature activation-7.08e+00

Pos logit contributions
 UCS+4.502
UTF+4.363
py+4.087
osph+4.057
pu+3.990
Neg logit contributions
ellar-3.848
yrinth-3.836
 Balloon-3.120
 Doodle-3.112
 Priv-3.079
Token.
Token ID13
Feature activation-9.17e+00

Pos logit contributions
 UCS+3.991
UTF+3.760
py+3.572
osph+3.370
pu+3.361
Neg logit contributions
yrinth-6.398
ellar-6.095
 Klux-5.332
 Doodle-5.167
 Priv-5.145
Token 4
Token ID604
Feature activation-7.29e+00

Pos logit contributions
 UCS+5.032
UTF+4.787
py+4.614
�士+4.587
osph+4.418
Neg logit contributions
ellar-8.024
yrinth-7.880
 Klux-6.883
 Balloon-6.820
 Priv-6.797
Token.
Token ID13
Feature activation-1.06e+01

Pos logit contributions
 UCS+4.103
UTF+3.950
py+3.737
pu+3.507
osph+3.447
Neg logit contributions
yrinth-6.669
ellar-6.340
 Klux-5.511
 eleph-5.419
 Doodle-5.351
Token Make
Token ID6889
Feature activation-1.35e+01

Pos logit contributions
 UCS+7.320
UTF+7.104
py+6.902
�士+6.899
osph+6.702
Neg logit contributions
ellar-7.756
yrinth-7.588
 msec-6.176
 Klux-6.155
 queens-6.109
Token 6
Token ID718
Feature activation-1.55e+01

Pos logit contributions
 UCS+4.786
py+4.109
UTF+3.863
pu+3.706
osph+3.606
Neg logit contributions
ellar-14.122
yrinth-14.011
BW-12.132
 Klux-11.991
 Priv-11.924
Token p
Token ID279
Feature activation-4.12e+00

Pos logit contributions
py+5.075
 UCS+4.679
pu+4.566
pi+3.883
UTF+3.868
Neg logit contributions
yrinth-16.399
ellar-15.921
BW-13.949
 eleph-13.842
 Klux-13.749
Tokenatt
Token ID1078
Feature activation-7.95e+00

Pos logit contributions
 UCS+2.492
py+2.385
UTF+2.372
osph+2.348
pu+2.333
Neg logit contributions
yrinth-3.358
ellar-3.324
 Priv-2.964
 Doodle-2.925
 Balloon-2.888
Tokenies
Token ID444
Feature activation-3.30e+00

Pos logit contributions
 UCS+3.013
py+2.908
UTF+2.733
osph+2.687
pu+2.646
Neg logit contributions
yrinth-8.148
ellar-8.008
 Priv-7.164
 Doodle-7.112
 Balloon-7.075
Token.
Token ID13
Feature activation-7.63e+00

Pos logit contributions
 UCS+2.136
UTF+2.013
py+1.899
osph+1.871
�士+1.850
Neg logit contributions
yrinth-2.692
ellar-2.682
 Klux-2.240
 Priv-2.229
 Balloon-2.210
Token 5
Token ID642
Feature activation-6.70e+00

Pos logit contributions
 UCS+5.060
UTF+4.990
�士+4.806
osph+4.722
py+4.718
Neg logit contributions
ellar-5.752
yrinth-5.629
 Klux-4.750
 Priv-4.741
 Balloon-4.709
Token not
Token ID407
Feature activation+5.18e+00

Pos logit contributions
 UCS+4.485
UTF+4.205
py+4.145
osph+4.048
pu+3.841
Neg logit contributions
yrinth-6.393
ellar-6.282
 Klux-5.487
 Priv-5.390
 Balloon-5.320
Token deep
Token ID2769
Feature activation-1.01e+01

Pos logit contributions
ellar+3.199
yrinth+3.161
 drag+2.662
 Priv+2.625
---------+2.603
Neg logit contributions
�士-4.323
 UCS-4.148
UTF-4.016
osph-3.932
py-3.762
Token fried
Token ID23018
Feature activation-8.64e+00

Pos logit contributions
 UCS+4.500
UTF+4.155
py+4.131
osph+3.850
pu+3.796
Neg logit contributions
yrinth-9.758
ellar-9.608
 Priv-8.382
 Balloon-8.305
 Doodle-8.163
Token.
Token ID13
Feature activation-6.00e+00

Pos logit contributions
 UCS+4.601
UTF+4.346
py+4.139
osph+3.925
pu+3.855
Neg logit contributions
yrinth-7.842
ellar-7.562
 Klux-6.542
 Priv-6.431
 Doodle-6.413
Token 6
Token ID718
Feature activation-6.43e+00

Pos logit contributions
 UCS+3.510
UTF+3.348
�士+3.273
py+3.150
osph+3.141
Neg logit contributions
ellar-5.157
yrinth-5.086
 Klux-4.378
 Priv-4.363
 Balloon-4.357
Token.
Token ID13
Feature activation-1.53e+01

Pos logit contributions
 UCS+3.768
UTF+3.628
py+3.390
pu+3.232
osph+3.212
Neg logit contributions
yrinth-5.724
ellar-5.514
 Klux-4.748
 Balloon-4.646
 Doodle-4.632
Token Drain
Token ID36024
Feature activation-8.77e-01

Pos logit contributions
 UCS+6.436
UTF+6.061
py+5.432
osph+5.317
pu+5.082
Neg logit contributions
yrinth-14.298
ellar-14.072
 Klux-12.340
 hoops-12.273
 eleph-12.166
Token on
Token ID319
Feature activation-9.72e-01

Pos logit contributions
 UCS+0.555
UTF+0.528
�士+0.520
osph+0.497
py+0.489
Neg logit contributions
ellar-0.724
yrinth-0.715
 Priv-0.615
 Balloon-0.609
 Klux-0.608
Token a
Token ID257
Feature activation-7.08e+00

Pos logit contributions
 UCS+0.751
UTF+0.718
�士+0.698
osph+0.681
py+0.678
Neg logit contributions
ellar-0.669
yrinth-0.666
 Priv-0.547
 Balloon-0.542
 Klux-0.541
Token paper
Token ID3348
Feature activation-4.34e+00

Pos logit contributions
 UCS+5.453
UTF+5.051
py+4.966
osph+4.847
pu+4.820
Neg logit contributions
yrinth-5.031
ellar-4.756
BW-3.827
 Priv-3.809
 Klux-3.803
Token towel
Token ID24808
Feature activation-4.06e+00

Pos logit contributions
 UCS+3.232
UTF+3.055
�士+2.930
py+2.926
osph+2.921
Neg logit contributions
yrinth-3.088
ellar-3.060
 Priv-2.517
 Balloon-2.487
 Klux-2.484
Token?
Token ID30
Feature activation-6.25e+00

Pos logit contributions
 UCS+1.164
UTF+1.117
py+1.043
osph+1.036
�士+1.030
Neg logit contributions
yrinth-1.359
ellar-1.353
 Klux-1.130
 Balloon-1.129
 Priv-1.114
Token No
Token ID1400
Feature activation-5.22e+00

Pos logit contributions
 UCS+4.035
UTF+3.711
py+3.602
pu+3.476
osph+3.377
Neg logit contributions
yrinth-5.268
ellar-5.065
 Klux-4.341
 queens-4.130
BW-4.127
Token more
Token ID517
Feature activation-7.31e+00

Pos logit contributions
 UCS+3.301
UTF+3.001
py+2.891
osph+2.888
pu+2.781
Neg logit contributions
yrinth-4.411
ellar-4.226
 Balloon-3.640
 Klux-3.597
 Priv-3.591
Token bad
Token ID2089
Feature activation-3.15e+00

Pos logit contributions
 UCS+3.480
py+3.137
UTF+3.003
pu+2.966
bul+2.830
Neg logit contributions
yrinth-7.227
ellar-6.976
 Balloon-6.097
 Klux-6.057
idav-6.013
Token news
Token ID1705
Feature activation-8.82e+00

Pos logit contributions
 UCS+1.456
UTF+1.314
osph+1.215
py+1.197
�士+1.157
Neg logit contributions
yrinth-3.206
ellar-3.184
 Balloon-2.767
 Klux-2.759
 Priv-2.740
Token pl
Token ID458
Feature activation-1.52e+01

Pos logit contributions
 UCS+4.197
UTF+3.759
py+3.708
osph+3.653
pu+3.459
Neg logit contributions
yrinth-8.396
ellar-8.383
 Klux-7.137
 Balloon-7.120
 Doodle-7.045
Tokens
Token ID82
Feature activation-8.17e-01

Pos logit contributions
py+5.797
pu+5.604
 UCS+5.485
UTF+5.262
pi+5.147
Neg logit contributions
yrinth-14.946
ellar-14.396
 eleph-14.368
 Doodle-13.329
 conclud-12.917
Token.
Token ID13
Feature activation-7.94e+00

Pos logit contributions
 UCS+0.557
UTF+0.533
�士+0.508
osph+0.499
py+0.498
Neg logit contributions
yrinth-0.636
ellar-0.635
 Priv-0.532
 Klux-0.530
 Balloon-0.529
Token Writer
Token ID26606
Feature activation+2.31e+00

Pos logit contributions
 UCS+6.028
UTF+5.698
�士+5.539
py+5.465
osph+5.384
Neg logit contributions
ellar-5.401
yrinth-5.314
 Klux-4.327
----------4.227
 Priv-4.217
Token "
Token ID366
Feature activation-1.97e+00

Pos logit contributions
ellar+1.581
yrinth+1.550
 Priv+1.323
 Balloon+1.305
BW+1.289
Neg logit contributions
 UCS-1.754
�士-1.725
UTF-1.697
osph-1.625
py-1.594
TokenI
Token ID40
Feature activation-8.65e-01

Pos logit contributions
 UCS+1.465
UTF+1.414
�士+1.399
osph+1.340
py+1.326
Neg logit contributions
ellar-1.400
yrinth-1.379
 Priv-1.162
 Balloon-1.142
 Klux-1.141
Token.
Token ID13
Feature activation-2.84e+00

Pos logit contributions
 UCS+2.335
UTF+2.207
py+2.079
osph+2.069
pu+1.992
Neg logit contributions
yrinth-3.035
ellar-2.999
 Balloon-2.526
 Priv-2.518
 Klux-2.518
Token 3
Token ID513
Feature activation-3.95e+00

Pos logit contributions
 UCS+2.096
UTF+2.019
�士+2.005
osph+1.913
py+1.895
Neg logit contributions
ellar-2.046
yrinth-2.007
 Priv-1.692
 Balloon-1.672
 Klux-1.670
Token.
Token ID13
Feature activation-9.99e+00

Pos logit contributions
 UCS+2.493
UTF+2.400
py+2.247
osph+2.185
pu+2.144
Neg logit contributions
yrinth-3.327
ellar-3.249
 Klux-2.757
 Priv-2.722
 Balloon-2.718
Token In
Token ID554
Feature activation-8.75e+00

Pos logit contributions
 UCS+5.916
UTF+5.593
�士+5.414
py+5.379
osph+5.352
Neg logit contributions
ellar-8.357
yrinth-8.242
 msec-6.898
 Klux-6.861
 queens-6.816
Token a
Token ID257
Feature activation-9.92e+00

Pos logit contributions
 UCS+5.385
UTF+5.000
py+4.868
pu+4.675
osph+4.663
Neg logit contributions
yrinth-7.223
ellar-7.000
 Doodle-5.894
 Priv-5.862
BW-5.771
Token large
Token ID1588
Feature activation-1.52e+01

Pos logit contributions
 UCS+4.197
UTF+3.708
py+3.364
pu+3.190
osph+3.137
Neg logit contributions
yrinth-10.394
ellar-10.169
 Doodle-9.089
 Priv-8.866
BW-8.697
Token bowl
Token ID9396
Feature activation-7.85e+00

Pos logit contributions
 UCS+7.063
UTF+6.952
py+6.243
pu+6.153
osph+6.037
Neg logit contributions
yrinth-14.285
ellar-13.236
 Doodle-11.498
 eleph-11.418
 Priv-11.268
Token,
Token ID11
Feature activation-1.26e+01

Pos logit contributions
 UCS+4.692
UTF+4.404
py+4.367
osph+4.239
pu+4.099
Neg logit contributions
yrinth-6.612
ellar-6.357
 Klux-5.421
 Balloon-5.383
 Priv-5.382
Token combine
Token ID12082
Feature activation-8.92e+00

Pos logit contributions
 UCS+3.721
osph+3.357
UTF+3.344
py+3.224
pu+2.906
Neg logit contributions
ellar-13.713
yrinth-13.699
 Priv-11.991
 Balloon-11.831
 Doodle-11.716
Token the
Token ID262
Feature activation-1.50e+01

Pos logit contributions
 UCS+5.625
UTF+5.061
py+4.862
osph+4.755
pu+4.676
Neg logit contributions
yrinth-7.489
ellar-7.109
 Priv-6.040
 Balloon-5.954
BW-5.933
Token broccoli
Token ID44653
Feature activation-1.18e+01

Pos logit contributions
 UCS+2.263
UTF+1.514
py+1.188
pu+0.882
 broccoli+0.782
Neg logit contributions
yrinth-18.902
ellar-18.346
 Doodle-16.595
 Priv-16.439
IFT-16.133
Tokenters
Token ID1010
Feature activation-5.70e+00

Pos logit contributions
 UCS+4.374
UTF+4.154
py+4.101
osph+4.039
pu+3.946
Neg logit contributions
yrinth-4.764
ellar-4.719
 Balloon-4.000
 Priv-3.963
 Doodle-3.879
Token at
Token ID379
Feature activation-1.69e+00

Pos logit contributions
 UCS+3.615
py+3.373
UTF+3.372
osph+3.192
pu+3.154
Neg logit contributions
yrinth-4.720
ellar-4.585
 Klux-3.926
 Doodle-3.890
 Priv-3.853
Token a
Token ID257
Feature activation-3.24e+00

Pos logit contributions
 UCS+1.256
UTF+1.200
py+1.139
�士+1.130
osph+1.126
Neg logit contributions
yrinth-1.220
ellar-1.212
 Priv-0.992
 Klux-0.987
 Balloon-0.981
Token time
Token ID640
Feature activation-5.18e+00

Pos logit contributions
 UCS+2.455
UTF+2.331
py+2.271
osph+2.259
pu+2.173
Neg logit contributions
yrinth-2.275
ellar-2.250
 Priv-1.837
 Klux-1.806
 Balloon-1.802
Token),
Token ID828
Feature activation-9.34e+00

Pos logit contributions
 UCS+2.952
UTF+2.734
osph+2.627
py+2.538
pu+2.451
Neg logit contributions
yrinth-4.581
ellar-4.535
 Priv-3.934
 Klux-3.878
BW-3.857
Token reduce
Token ID4646
Feature activation-1.51e+01

Pos logit contributions
 UCS+4.125
UTF+3.828
osph+3.810
py+3.668
pu+3.414
Neg logit contributions
yrinth-9.333
ellar-9.267
 Balloon-8.105
BW-8.100
 Klux-8.070
Token heat
Token ID4894
Feature activation-8.89e+00

Pos logit contributions
 UCS+3.884
UTF+3.486
py+3.477
osph+3.189
pu+2.862
Neg logit contributions
yrinth-17.603
ellar-16.449
 Doodle-14.880
idav-14.648
 Balloon-14.491
Token to
Token ID284
Feature activation-4.88e+00

Pos logit contributions
 UCS+4.904
UTF+4.506
py+4.368
osph+4.173
pu+4.137
Neg logit contributions
yrinth-8.209
ellar-7.783
 Klux-6.698
 Balloon-6.598
 Doodle-6.597
Token low
Token ID1877
Feature activation-5.36e+00

Pos logit contributions
 UCS+2.651
UTF+2.458
py+2.333
osph+2.314
pu+2.212
Neg logit contributions
yrinth-4.475
ellar-4.470
 Priv-3.840
 Doodle-3.837
 Balloon-3.800
Token and
Token ID290
Feature activation-1.49e+01

Pos logit contributions
 UCS+3.344
UTF+3.137
py+3.010
osph+2.895
pu+2.874
Neg logit contributions
yrinth-4.535
ellar-4.421
 Klux-3.734
 Balloon-3.708
 Doodle-3.706
Token cook
Token ID4255
Feature activation-1.37e+01

Pos logit contributions
 UCS+4.509
py+4.431
osph+4.352
UTF+4.352
pu+3.741
Neg logit contributions
yrinth-15.154
ellar-14.620
 Priv-13.302
BW-13.029
 Balloon-12.993
Token?
Token ID30
Feature activation-4.74e+00

Pos logit contributions
 UCS+1.916
UTF+1.846
py+1.701
pu+1.661
osph+1.657
Neg logit contributions
yrinth-2.441
ellar-2.396
 Klux-2.020
 Balloon-2.006
 Priv-1.966
Token No
Token ID1400
Feature activation-3.17e+00

Pos logit contributions
 UCS+3.205
UTF+2.991
py+2.848
pu+2.735
osph+2.712
Neg logit contributions
yrinth-3.866
ellar-3.731
 Klux-3.170
BW-3.036
 queens-3.026
Token more
Token ID517
Feature activation-7.03e+00

Pos logit contributions
 UCS+2.138
UTF+1.989
osph+1.883
py+1.881
pu+1.800
Neg logit contributions
yrinth-2.529
ellar-2.458
 Balloon-2.104
 Priv-2.071
 Klux-2.063
Token bad
Token ID2089
Feature activation-8.56e-01

Pos logit contributions
 UCS+3.367
py+2.979
UTF+2.921
pu+2.812
bul+2.775
Neg logit contributions
yrinth-6.918
ellar-6.619
 Balloon-5.839
 Klux-5.812
idav-5.711
Token news
Token ID1705
Feature activation-1.03e+01

Pos logit contributions
 UCS+0.424
UTF+0.393
�士+0.372
osph+0.363
py+0.357
Neg logit contributions
ellar-0.831
yrinth-0.828
 Balloon-0.718
 Priv-0.717
 Klux-0.714
Token pl
Token ID458
Feature activation-1.50e+01

Pos logit contributions
 UCS+4.648
UTF+4.181
py+4.035
osph+4.028
pu+3.781
Neg logit contributions
yrinth-9.957
ellar-9.789
 Klux-8.429
 Doodle-8.391
 Balloon-8.363
Tokens
Token ID82
Feature activation-2.31e+00

Pos logit contributions
py+5.789
UTF+5.412
pu+5.389
 UCS+5.367
pi+4.926
Neg logit contributions
yrinth-14.801
 eleph-14.253
ellar-14.127
 Doodle-13.153
 conclud-12.797
Token.
Token ID13
Feature activation-3.00e+00

Pos logit contributions
 UCS+1.517
UTF+1.448
py+1.350
osph+1.332
�士+1.325
Neg logit contributions
yrinth-1.876
ellar-1.848
 Klux-1.558
 Balloon-1.541
 Priv-1.537
Token
Token ID198
Feature activation-8.36e-01

Pos logit contributions
 UCS+2.294
UTF+2.204
�士+2.187
osph+2.088
py+2.071
Neg logit contributions
ellar-2.075
yrinth-2.040
 Priv-1.699
 Klux-1.682
 Balloon-1.677
Token
Token ID198
Feature activation-1.30e+00

Pos logit contributions
 UCS+0.620
UTF+0.595
�士+0.569
py+0.561
osph+0.559
Neg logit contributions
yrinth-0.602
ellar-0.601
 Priv-0.496
 Klux-0.495
 Balloon-0.492
TokenGood
Token ID10248
Feature activation+8.45e-01

Pos logit contributions
 UCS+0.977
UTF+0.938
�士+0.936
osph+0.892
py+0.878
Neg logit contributions
ellar-0.921
yrinth-0.906
 Priv-0.763
 Balloon-0.752
 Klux-0.749
Token a
Token ID257
Feature activation-9.92e+00

Pos logit contributions
 UCS+5.385
UTF+5.000
py+4.868
pu+4.675
osph+4.663
Neg logit contributions
yrinth-7.223
ellar-7.000
 Doodle-5.894
 Priv-5.862
BW-5.771
Token large
Token ID1588
Feature activation-1.52e+01

Pos logit contributions
 UCS+4.197
UTF+3.708
py+3.364
pu+3.190
osph+3.137
Neg logit contributions
yrinth-10.394
ellar-10.169
 Doodle-9.089
 Priv-8.866
BW-8.697
Token bowl
Token ID9396
Feature activation-7.85e+00

Pos logit contributions
 UCS+7.063
UTF+6.952
py+6.243
pu+6.153
osph+6.037
Neg logit contributions
yrinth-14.285
ellar-13.236
 Doodle-11.498
 eleph-11.418
 Priv-11.268
Token,
Token ID11
Feature activation-1.26e+01

Pos logit contributions
 UCS+4.692
UTF+4.404
py+4.367
osph+4.239
pu+4.099
Neg logit contributions
yrinth-6.612
ellar-6.357
 Klux-5.421
 Balloon-5.383
 Priv-5.382
Token combine
Token ID12082
Feature activation-8.92e+00

Pos logit contributions
 UCS+3.721
osph+3.357
UTF+3.344
py+3.224
pu+2.906
Neg logit contributions
ellar-13.713
yrinth-13.699
 Priv-11.991
 Balloon-11.831
 Doodle-11.716
Token the
Token ID262
Feature activation-1.50e+01

Pos logit contributions
 UCS+5.625
UTF+5.061
py+4.862
osph+4.755
pu+4.676
Neg logit contributions
yrinth-7.489
ellar-7.109
 Priv-6.040
 Balloon-5.954
BW-5.933
Token broccoli
Token ID44653
Feature activation-1.18e+01

Pos logit contributions
 UCS+2.263
UTF+1.514
py+1.188
pu+0.882
 broccoli+0.782
Neg logit contributions
yrinth-18.902
ellar-18.346
 Doodle-16.595
 Priv-16.439
IFT-16.133
Token pieces
Token ID5207
Feature activation-1.12e+01

Pos logit contributions
 UCS+7.793
UTF+6.964
py+6.868
pu+6.620
osph+6.598
Neg logit contributions
yrinth-9.113
ellar-8.815
 Balloon-7.327
 Doodle-7.318
BW-7.185
Token with
Token ID351
Feature activation-5.71e+00

Pos logit contributions
 UCS+5.400
py+4.776
UTF+4.560
osph+4.458
pu+4.351
Neg logit contributions
yrinth-10.492
ellar-10.286
 Doodle-8.930
 Klux-8.717
 Priv-8.688
Token all
Token ID477
Feature activation-6.40e+00

Pos logit contributions
 UCS+3.529
UTF+3.244
py+3.063
osph+2.997
pu+2.928
Neg logit contributions
yrinth-4.878
ellar-4.791
 Klux-4.077
 Priv-4.056
 Doodle-4.056
Token the
Token ID262
Feature activation-6.40e+00

Pos logit contributions
 UCS+4.174
UTF+3.865
py+3.711
osph+3.608
pu+3.529
Neg logit contributions
yrinth-5.277
ellar-4.989
 Klux-4.288
 Balloon-4.211
BW-4.178
Token.
Token ID764
Feature activation+5.85e+00

Pos logit contributions
ellar+4.037
yrinth+3.677
 Priv+3.410
 drag+3.322
[_+3.276
Neg logit contributions
�士-6.266
 UCS-5.770
UTF-5.660
osph-5.561
py-5.203
Token normal
Token ID3487
Feature activation+6.38e+00

Pos logit contributions
ellar+3.672
yrinth+3.665
 drag+3.084
 Priv+3.002
 Balloon+2.936
Neg logit contributions
 UCS-4.525
UTF-4.501
�士-4.435
osph-4.262
-4.127
Token *
Token ID1635
Feature activation-3.11e+00

Pos logit contributions
ellar+2.963
yrinth+2.738
 Priv+2.321
 drag+2.295
BW+2.252
Neg logit contributions
�士-6.291
 UCS-6.017
UTF-5.883
osph-5.734
py-5.467
Token 1
Token ID352
Feature activation+2.51e+00

Pos logit contributions
 UCS+2.214
UTF+2.092
osph+1.991
py+1.977
�士+1.962
Neg logit contributions
ellar-2.333
yrinth-2.329
 Priv-1.916
 Klux-1.911
 Balloon-1.904
Token ;
Token ID2162
Feature activation-3.44e-01

Pos logit contributions
ellar+1.572
yrinth+1.528
 Priv+1.285
 Balloon+1.254
 Klux+1.237
Neg logit contributions
 UCS-2.067
�士-2.031
UTF-2.000
osph-1.922
py-1.880
Token }
Token ID1782
Feature activation-1.49e+01

Pos logit contributions
 UCS+0.239
UTF+0.227
�士+0.223
osph+0.214
py+0.213
Neg logit contributions
ellar-0.262
yrinth-0.260
 Priv-0.220
 Klux-0.218
 Balloon-0.217
Token
Token ID198
Feature activation-6.34e+00

Pos logit contributions
 UCS+8.225
py+7.560
UTF+7.507
osph+7.131
�士+6.759
Neg logit contributions
yrinth-11.804
ellar-11.714
 Klux-10.254
 Balloon-9.985
BW-9.871
Token
Token ID198
Feature activation-4.84e+00

Pos logit contributions
 UCS+3.957
UTF+3.760
py+3.659
pu+3.432
osph+3.370
Neg logit contributions
yrinth-5.442
ellar-5.164
 Klux-4.497
 eleph-4.434
 Doodle-4.370
TokenThe
Token ID464
Feature activation-2.81e+00

Pos logit contributions
 UCS+3.365
UTF+3.292
�士+3.162
py+3.105
osph+3.080
Neg logit contributions
ellar-3.623
yrinth-3.568
 Priv-3.047
 Balloon-3.027
 Klux-2.991
Token result
Token ID1255
Feature activation+1.65e+00

Pos logit contributions
 UCS+2.196
UTF+2.094
�士+2.081
osph+2.000
py+1.982
Neg logit contributions
ellar-1.912
yrinth-1.879
 Priv-1.555
 Klux-1.543
 Balloon-1.538
Token pushes
Token ID20070
Feature activation-7.53e+00

Pos logit contributions
ellar+1.091
yrinth+1.067
 Priv+0.898
 Balloon+0.889
---------+0.875
Neg logit contributions
 UCS-1.295
�士-1.276
UTF-1.251
osph-1.197
py-1.162
Token),
Token ID828
Feature activation-9.34e+00

Pos logit contributions
 UCS+2.952
UTF+2.734
osph+2.627
py+2.538
pu+2.451
Neg logit contributions
yrinth-4.581
ellar-4.535
 Priv-3.934
 Klux-3.878
BW-3.857
Token reduce
Token ID4646
Feature activation-1.51e+01

Pos logit contributions
 UCS+4.125
UTF+3.828
osph+3.810
py+3.668
pu+3.414
Neg logit contributions
yrinth-9.333
ellar-9.267
 Balloon-8.105
BW-8.100
 Klux-8.070
Token heat
Token ID4894
Feature activation-8.89e+00

Pos logit contributions
 UCS+3.884
UTF+3.486
py+3.477
osph+3.189
pu+2.862
Neg logit contributions
yrinth-17.603
ellar-16.449
 Doodle-14.880
idav-14.648
 Balloon-14.491
Token to
Token ID284
Feature activation-4.88e+00

Pos logit contributions
 UCS+4.904
UTF+4.506
py+4.368
osph+4.173
pu+4.137
Neg logit contributions
yrinth-8.209
ellar-7.783
 Klux-6.698
 Balloon-6.598
 Doodle-6.597
Token low
Token ID1877
Feature activation-5.36e+00

Pos logit contributions
 UCS+2.651
UTF+2.458
py+2.333
osph+2.314
pu+2.212
Neg logit contributions
yrinth-4.475
ellar-4.470
 Priv-3.840
 Doodle-3.837
 Balloon-3.800
Token and
Token ID290
Feature activation-1.49e+01

Pos logit contributions
 UCS+3.344
UTF+3.137
py+3.010
osph+2.895
pu+2.874
Neg logit contributions
yrinth-4.535
ellar-4.421
 Klux-3.734
 Balloon-3.708
 Doodle-3.706
Token cook
Token ID4255
Feature activation-1.37e+01

Pos logit contributions
 UCS+4.509
py+4.431
osph+4.352
UTF+4.352
pu+3.741
Neg logit contributions
yrinth-15.154
ellar-14.620
 Priv-13.302
BW-13.029
 Balloon-12.993
Token f
Token ID277
Feature activation-1.19e+01

Pos logit contributions
 UCS+6.434
py+6.043
UTF+5.974
pu+5.569
osph+5.399
Neg logit contributions
yrinth-12.708
ellar-12.326
 Priv-10.518
 Doodle-10.419
BW-10.392
Tokenrit
Token ID799
Feature activation-6.50e+00

Pos logit contributions
UTF+4.630
py+4.616
pu+4.589
osph+4.545
 UCS+4.362
Neg logit contributions
yrinth-11.328
ellar-11.082
 eleph-10.629
 Doodle-10.513
 Balloon-10.399
Tokenters
Token ID1010
Feature activation-7.74e+00

Pos logit contributions
 UCS+4.521
UTF+4.290
py+4.218
osph+4.167
pu+4.056
Neg logit contributions
yrinth-4.814
ellar-4.779
 Balloon-4.081
 Priv-4.042
BW-3.932
Token on
Token ID319
Feature activation-4.52e+00

Pos logit contributions
 UCS+3.786
UTF+3.471
py+3.453
pu+3.191
osph+3.191
Neg logit contributions
yrinth-7.432
ellar-7.263
 Klux-6.335
 Doodle-6.228
 Priv-6.214
Token of
Token ID286
Feature activation-1.33e+00

Pos logit contributions
ellar+2.216
yrinth+2.152
 Priv+1.821
 Balloon+1.783
 drag+1.750
Neg logit contributions
 UCS-2.744
�士-2.712
UTF-2.671
osph-2.550
py-2.497
Token the
Token ID262
Feature activation-1.95e+00

Pos logit contributions
 UCS+1.042
UTF+1.003
�士+1.000
osph+0.956
py+0.943
Neg logit contributions
ellar-0.888
yrinth-0.873
 Priv-0.728
 Balloon-0.717
 Klux-0.713
Token passport
Token ID17981
Feature activation-2.75e-01

Pos logit contributions
 UCS+1.547
UTF+1.484
�士+1.479
osph+1.412
py+1.395
Neg logit contributions
ellar-1.293
yrinth-1.275
 Priv-1.050
 Klux-1.039
 Balloon-1.038
Token,
Token ID11
Feature activation-4.53e+00

Pos logit contributions
 UCS+0.206
�士+0.198
UTF+0.198
osph+0.188
py+0.185
Neg logit contributions
ellar-0.195
yrinth-0.191
 Priv-0.162
 Balloon-0.160
 Klux-0.158
Token whichever
Token ID26204
Feature activation-1.02e+01

Pos logit contributions
 UCS+3.189
UTF+2.999
�士+2.943
osph+2.842
py+2.829
Neg logit contributions
ellar-3.385
yrinth-3.374
 Klux-2.813
 Priv-2.759
 Balloon-2.756
Token comes
Token ID2058
Feature activation-1.48e+01

Pos logit contributions
 UCS+6.643
UTF+6.092
�士+5.705
osph+5.658
py+5.652
Neg logit contributions
yrinth-8.032
ellar-7.865
 Klux-6.569
BW-6.548
----------6.476
Token sooner
Token ID14556
Feature activation-5.20e+00

Pos logit contributions
 UCS+7.765
UTF+7.303
py+6.838
osph+6.796
�士+6.730
Neg logit contributions
yrinth-12.529
ellar-12.073
BW-10.383
 Doodle-10.264
 Priv-10.143
Token in
Token ID287
Feature activation-5.41e+00

Pos logit contributions
 UCS+3.491
UTF+3.341
�士+3.221
osph+3.174
py+3.135
Neg logit contributions
ellar-4.024
yrinth-3.987
 Priv-3.384
 Klux-3.350
 Doodle-3.323
Token case
Token ID1339
Feature activation+3.21e-01

Pos logit contributions
 UCS+4.008
UTF+3.807
�士+3.713
osph+3.577
py+3.547
Neg logit contributions
ellar-3.831
yrinth-3.783
 Klux-3.166
 Priv-3.147
 Balloon-3.112
Token the
Token ID262
Feature activation-5.23e+00

Pos logit contributions
ellar+0.215
yrinth+0.210
 Priv+0.177
 Balloon+0.173
 Klux+0.171
Neg logit contributions
 UCS-0.253
�士-0.244
UTF-0.244
osph-0.234
py-0.230
Token individual
Token ID1981
Feature activation-2.14e+00

Pos logit contributions
 UCS+4.105
UTF+3.909
�士+3.855
osph+3.677
py+3.667
Neg logit contributions
ellar-3.443
yrinth-3.441
 Klux-2.806
 Priv-2.760
 Balloon-2.749
Token with
Token ID351
Feature activation-5.71e+00

Pos logit contributions
 UCS+5.400
py+4.776
UTF+4.560
osph+4.458
pu+4.351
Neg logit contributions
yrinth-10.492
ellar-10.286
 Doodle-8.930
 Klux-8.717
 Priv-8.688
Token all
Token ID477
Feature activation-6.40e+00

Pos logit contributions
 UCS+3.529
UTF+3.244
py+3.063
osph+2.997
pu+2.928
Neg logit contributions
yrinth-4.878
ellar-4.791
 Klux-4.077
 Priv-4.056
 Doodle-4.056
Token the
Token ID262
Feature activation-6.40e+00

Pos logit contributions
 UCS+4.174
UTF+3.865
py+3.711
osph+3.608
pu+3.529
Neg logit contributions
yrinth-5.277
ellar-4.989
 Klux-4.288
 Balloon-4.211
BW-4.178
Token other
Token ID584
Feature activation-5.77e+00

Pos logit contributions
 UCS+4.132
UTF+3.805
osph+3.614
py+3.607
pu+3.466
Neg logit contributions
yrinth-5.269
ellar-5.070
 Balloon-4.285
 Klux-4.279
 Doodle-4.271
Token ingredients
Token ID9391
Feature activation-5.32e+00

Pos logit contributions
 UCS+4.946
UTF+4.741
osph+4.473
py+4.450
�士+4.329
Neg logit contributions
yrinth-3.445
ellar-3.275
 Doodle-2.679
 Priv-2.674
BW-2.664
Token and
Token ID290
Feature activation-1.48e+01

Pos logit contributions
 UCS+3.298
UTF+3.075
py+2.971
osph+2.899
pu+2.824
Neg logit contributions
yrinth-4.479
ellar-4.350
 Klux-3.712
 Doodle-3.710
 Balloon-3.687
Token mix
Token ID5022
Feature activation-6.74e+00

Pos logit contributions
osph+7.215
 UCS+7.175
py+7.166
UTF+6.698
pu+6.308
Neg logit contributions
yrinth-12.385
ellar-12.351
 eleph-10.603
idav-10.526
 Priv-10.415
Token well
Token ID880
Feature activation-7.31e+00

Pos logit contributions
 UCS+5.321
UTF+5.092
py+4.860
osph+4.746
pu+4.630
Neg logit contributions
yrinth-4.472
ellar-4.410
 Doodle-3.584
 Balloon-3.530
 Priv-3.507
Token until
Token ID1566
Feature activation-7.99e+00

Pos logit contributions
 UCS+3.911
UTF+3.650
osph+3.573
py+3.203
pu+3.186
Neg logit contributions
yrinth-6.552
ellar-6.290
 Priv-5.550
 Klux-5.524
BW-5.512
Token the
Token ID262
Feature activation-8.03e+00

Pos logit contributions
 UCS+4.992
UTF+4.543
py+4.410
osph+4.360
pu+4.172
Neg logit contributions
yrinth-6.667
ellar-6.319
 Priv-5.448
 Klux-5.398
 Balloon-5.369
Token mixture
Token ID11710
Feature activation-8.79e+00

Pos logit contributions
 UCS+4.588
UTF+4.154
py+4.135
osph+4.102
pu+3.824
Neg logit contributions
yrinth-6.884
ellar-6.754
 Priv-5.780
 Klux-5.727
 Doodle-5.717
Token fever
Token ID17372
Feature activation+1.37e+00

Pos logit contributions
 UCS+0.903
UTF+0.866
�士+0.864
osph+0.821
py+0.807
Neg logit contributions
ellar-0.945
yrinth-0.930
 Priv-0.792
 Balloon-0.782
 Klux-0.778
Token
Token ID447
Feature activation-8.12e-01

Pos logit contributions
ellar+0.946
yrinth+0.935
 Priv+0.789
 Balloon+0.779
 Klux+0.768
Neg logit contributions
 UCS-1.027
�士-1.006
UTF-0.994
osph-0.944
py-0.923
Token
Token ID251
Feature activation-3.03e+00

Pos logit contributions
 UCS+0.748
UTF+0.723
�士+0.720
osph+0.693
py+0.685
Neg logit contributions
ellar-0.435
yrinth-0.426
 Priv-0.337
 Balloon-0.331
 Klux-0.328
Token or
Token ID393
Feature activation-4.43e+00

Pos logit contributions
 UCS+2.233
UTF+2.137
�士+2.105
osph+2.025
py+2.015
Neg logit contributions
ellar-2.186
yrinth-2.153
 Priv-1.801
 Balloon-1.781
 Klux-1.780
Token something
Token ID1223
Feature activation-9.31e+00

Pos logit contributions
 UCS+3.212
UTF+3.034
�士+2.998
osph+2.904
py+2.872
Neg logit contributions
ellar-3.268
yrinth-3.206
 Priv-2.685
 Balloon-2.650
 Klux-2.647
Token like
Token ID588
Feature activation-1.47e+01

Pos logit contributions
 UCS+6.124
UTF+5.829
�士+5.570
py+5.542
osph+5.453
Neg logit contributions
ellar-7.146
yrinth-7.041
 Priv-5.968
 Klux-5.845
 Balloon-5.822
Token that
Token ID326
Feature activation-5.05e+00

Pos logit contributions
 UCS+8.001
UTF+7.185
�士+6.910
py+6.775
osph+6.640
Neg logit contributions
ellar-12.241
yrinth-11.953
 Priv-10.142
----------10.050
 Doodle-9.970
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
 UCS+3.478
UTF+3.343
�士+3.274
osph+3.142
py+3.135
Neg logit contributions
ellar-3.853
yrinth-3.786
 Priv-3.222
 Balloon-3.186
 Klux-3.186
Token That
Token ID1320
Feature activation+1.77e+00

Pos logit contributions
ellar+0.073
yrinth+0.072
 Priv+0.062
 Balloon+0.061
 Klux+0.060
Neg logit contributions
 UCS-0.079
�士-0.077
UTF-0.076
osph-0.073
py-0.071
Token
Token ID447
Feature activation+4.80e-02

Pos logit contributions
ellar+1.324
yrinth+1.310
 Priv+1.122
 Balloon+1.105
 Klux+1.097
Neg logit contributions
 UCS-1.233
�士-1.192
UTF-1.180
osph-1.116
py-1.082
Token
Token ID247
Feature activation+4.17e-02

Pos logit contributions
ellar+0.024
yrinth+0.023
 Priv+0.018
 Balloon+0.017
 Klux+0.017
Neg logit contributions
 UCS-0.046
UTF-0.045
�士-0.045
osph-0.043
py-0.043
Token,
Token ID11
Feature activation-3.16e+00

Pos logit contributions
 UCS+3.728
UTF+3.561
�士+3.511
osph+3.394
py+3.357
Neg logit contributions
ellar-3.676
yrinth-3.640
 Priv-3.034
 Klux-3.000
 Balloon-2.986
Token 2017
Token ID2177
Feature activation-3.76e+00

Pos logit contributions
 UCS+2.311
UTF+2.214
�士+2.204
osph+2.103
py+2.077
Neg logit contributions
ellar-2.291
yrinth-2.252
 Priv-1.897
 Balloon-1.873
 Klux-1.869
Token ma
Token ID17266
Feature activation-6.72e-01

Pos logit contributions
 UCS+2.746
UTF+2.619
�士+2.596
osph+2.487
py+2.460
Neg logit contributions
ellar-2.723
yrinth-2.685
 Priv-2.256
 Klux-2.223
 Balloon-2.222
Token N
Token ID399
Feature activation-6.81e+00

Pos logit contributions
 UCS+0.490
�士+0.471
UTF+0.470
osph+0.445
py+0.439
Neg logit contributions
ellar-0.488
yrinth-0.480
 Priv-0.409
 Balloon-0.403
 Klux-0.401
Tokenā
Token ID10235
Feature activation-7.99e+00

Pos logit contributions
 UCS+5.235
UTF+5.068
�士+4.958
osph+4.853
py+4.780
Neg logit contributions
ellar-4.503
yrinth-4.482
 Priv-3.734
 Balloon-3.647
 Klux-3.603
Tokenn
Token ID77
Feature activation-1.43e+01

Pos logit contributions
 UCS+5.907
UTF+5.638
�士+5.558
osph+5.492
pu+5.485
Neg logit contributions
ellar-5.438
yrinth-5.362
 Priv-4.427
 Klux-4.359
BW-4.341
Tokenā
Token ID10235
Feature activation-6.86e+00

Pos logit contributions
 UCS+10.067
pu+9.779
UTF+9.620
osph+9.619
py+9.515
Neg logit contributions
yrinth-9.161
ellar-8.973
 Klux-7.201
 Priv-7.178
BW-7.145
Tokenk
Token ID74
Feature activation-7.60e+00

Pos logit contributions
 UCS+5.126
UTF+4.883
�士+4.813
osph+4.724
pu+4.701
Neg logit contributions
ellar-4.730
yrinth-4.660
 Priv-3.820
 Klux-3.785
BW-3.736
Tokenuli
Token ID32176
Feature activation-3.07e+00

Pos logit contributions
 UCS+5.283
UTF+5.062
�士+4.930
osph+4.891
py+4.801
Neg logit contributions
ellar-5.518
yrinth-5.493
 Priv-4.624
 Balloon-4.562
 Klux-4.560
Token,
Token ID11
Feature activation-3.14e+00

Pos logit contributions
 UCS+2.258
UTF+2.165
�士+2.147
osph+2.060
py+2.029
Neg logit contributions
ellar-2.209
yrinth-2.176
 Priv-1.824
 Balloon-1.800
 Klux-1.796
Token Hawai
Token ID10847
Feature activation+1.77e+00

Pos logit contributions
 UCS+2.327
UTF+2.229
�士+2.216
osph+2.121
py+2.092
Neg logit contributions
ellar-2.251
yrinth-2.214
 Priv-1.859
 Balloon-1.833
 Klux-1.830
Tokenali
Token ID7344
Feature activation-2.65e-01

Pos logit contributions
 UCS+6.977
UTF+6.740
py+6.735
osph+6.715
�士+6.521
Neg logit contributions
ellar-6.156
yrinth-6.127
 Priv-5.264
 Balloon-5.256
 Klux-5.142
Token (
Token ID357
Feature activation-2.37e+00

Pos logit contributions
 UCS+0.196
UTF+0.188
�士+0.188
osph+0.179
py+0.176
Neg logit contributions
ellar-0.190
yrinth-0.187
 Priv-0.158
 Balloon-0.155
 Klux-0.155
Tokenve
Token ID303
Feature activation+1.19e+00

Pos logit contributions
 UCS+1.790
UTF+1.724
�士+1.716
osph+1.640
py+1.619
Neg logit contributions
ellar-1.651
yrinth-1.625
 Priv-1.366
 Balloon-1.346
 Klux-1.339
Tokenget
Token ID1136
Feature activation-1.42e+00

Pos logit contributions
ellar+0.536
yrinth+0.519
 Priv+0.384
 Balloon+0.377
 Klux+0.373
Neg logit contributions
 UCS-1.205
�士-1.181
UTF-1.169
osph-1.119
py-1.093
Tokenarian
Token ID3699
Feature activation+1.09e+00

Pos logit contributions
 UCS+1.054
UTF+1.012
�士+1.009
osph+0.963
py+0.948
Neg logit contributions
ellar-1.009
yrinth-0.994
 Priv-0.839
 Balloon-0.827
 Klux-0.824
Token pl
Token ID458
Feature activation-1.43e+01

Pos logit contributions
ellar+0.724
yrinth+0.709
 Priv+0.595
 Balloon+0.581
 Klux+0.577
Neg logit contributions
 UCS-0.870
�士-0.841
UTF-0.838
osph-0.795
py-0.783
Tokenatter
Token ID1436
Feature activation-3.73e+00

Pos logit contributions
osph+7.333
py+7.244
 UCS+7.209
UTF+7.136
atin+6.911
Neg logit contributions
yrinth-11.141
ellar-10.802
 Priv-10.290
 Doodle-10.166
 Balloon-10.157
Token)
Token ID8
Feature activation-2.89e+00

Pos logit contributions
 UCS+2.667
UTF+2.555
�士+2.512
osph+2.440
py+2.415
Neg logit contributions
ellar-2.753
yrinth-2.711
 Priv-2.288
 Klux-2.268
 Balloon-2.259
Token consisting
Token ID17747
Feature activation-8.74e-01

Pos logit contributions
 UCS+2.046
UTF+1.963
�士+1.936
osph+1.865
py+1.847
Neg logit contributions
ellar-2.159
yrinth-2.130
 Priv-1.795
 Balloon-1.780
 Klux-1.775
Token of
Token ID286
Feature activation-4.62e+00

Pos logit contributions
 UCS+0.672
UTF+0.645
�士+0.643
osph+0.614
py+0.605
Neg logit contributions
ellar-0.602
yrinth-0.592
 Priv-0.496
 Balloon-0.489
 Klux-0.486
Token s
Token ID264
Feature activation-1.12e-01

Pos logit contributions
 UCS+3.283
UTF+3.140
�士+3.096
osph+2.978
py+2.953
Neg logit contributions
ellar-3.402
yrinth-3.372
 Priv-2.805
 Klux-2.788
 Balloon-2.786
Token _
Token ID4808
Feature activation-2.77e+00

Pos logit contributions
 UCS+1.129
UTF+1.087
�士+1.084
osph+1.037
py+1.022
Neg logit contributions
ellar-0.939
yrinth-0.923
 Priv-0.767
 Balloon-0.755
 Klux-0.751
TokenP
Token ID47
Feature activation+2.72e-01

Pos logit contributions
 UCS+1.732
UTF+1.654
�士+1.642
osph+1.553
py+1.529
Neg logit contributions
ellar-2.296
yrinth-2.269
 Priv-1.963
 Balloon-1.938
 Klux-1.934
Tokenulse
Token ID9615
Feature activation+2.85e+00

Pos logit contributions
ellar+0.247
yrinth+0.244
 Priv+0.214
 Balloon+0.212
 Klux+0.211
Neg logit contributions
 UCS-0.149
UTF-0.141
�士-0.141
osph-0.131
py-0.129
TokenAmount
Token ID31264
Feature activation+6.60e+00

Pos logit contributions
ellar+1.912
yrinth+1.831
 Priv+1.597
BW+1.585
 Balloon+1.578
Neg logit contributions
 UCS-2.197
�士-2.193
UTF-2.072
osph-2.013
py-1.953
Token;
Token ID26
Feature activation-9.03e+00

Pos logit contributions
ellar+3.879
yrinth+3.764
[_+3.248
 Priv+3.172
 Balloon+3.165
Neg logit contributions
 UCS-5.350
�士-5.281
UTF-5.097
osph-4.920
py-4.792
Token }
Token ID1782
Feature activation-1.42e+01

Pos logit contributions
 UCS+6.162
UTF+5.585
�士+5.405
py+5.270
pu+5.205
Neg logit contributions
yrinth-6.806
ellar-6.779
 Klux-5.820
BW-5.626
----------5.590
Token 1
Token ID352
Feature activation-5.26e+00

Pos logit contributions
 UCS+9.289
UTF+8.199
py+8.022
osph+7.682
pu+7.681
Neg logit contributions
ellar-10.509
yrinth-10.322
 Klux-8.858
idav-8.382
BW-8.353
Token 2
Token ID362
Feature activation-1.05e+00

Pos logit contributions
 UCS+3.535
UTF+3.267
py+3.091
osph+3.048
�士+2.987
Neg logit contributions
yrinth-4.184
ellar-4.158
 Klux-3.467
 Priv-3.444
BW-3.401
Token 3
Token ID513
Feature activation-7.21e+00

Pos logit contributions
 UCS+0.825
UTF+0.790
�士+0.780
osph+0.751
py+0.744
Neg logit contributions
ellar-0.703
yrinth-0.689
 Priv-0.572
 Klux-0.565
 Balloon-0.564
Token 4
Token ID604
Feature activation-7.04e-01

Pos logit contributions
 UCS+5.071
UTF+4.688
�士+4.623
py+4.445
osph+4.415
Neg logit contributions
ellar-5.457
yrinth-5.282
 Klux-4.573
BW-4.539
 Priv-4.506
Token 5
Token ID642
Feature activation-6.01e+00

Pos logit contributions
 UCS+0.509
�士+0.493
UTF+0.492
osph+0.466
py+0.459
Neg logit contributions
ellar-0.514
yrinth-0.507
 Priv-0.431
 Balloon-0.425
 Klux-0.419
Token up
Token ID510
Feature activation-6.42e+00

Pos logit contributions
 UCS+3.242
UTF+3.006
py+2.901
osph+2.868
�士+2.826
Neg logit contributions
yrinth-3.407
ellar-3.391
 Priv-2.809
 Klux-2.793
 Balloon-2.783
Token some
Token ID617
Feature activation-3.82e+00

Pos logit contributions
 UCS+4.372
UTF+4.141
py+3.988
osph+3.844
pu+3.795
Neg logit contributions
yrinth-4.955
ellar-4.849
 Balloon-4.036
 Klux-3.985
 Doodle-3.959
Token got
Token ID1392
Feature activation-2.48e+00

Pos logit contributions
 UCS+2.776
UTF+2.636
�士+2.557
py+2.522
osph+2.481
Neg logit contributions
ellar-2.803
yrinth-2.788
 Balloon-2.318
 Priv-2.304
 Doodle-2.280
Tokencha
Token ID11693
Feature activation+1.06e+00

Pos logit contributions
 UCS+1.321
UTF+1.258
�士+1.179
py+1.178
osph+1.163
Neg logit contributions
ellar-2.270
yrinth-2.263
 Priv-1.960
 Balloon-1.941
 Doodle-1.938
Token's
Token ID338
Feature activation-5.95e+00

Pos logit contributions
ellar+0.737
yrinth+0.721
 Priv+0.613
 Balloon+0.601
 Klux+0.599
Neg logit contributions
 UCS-0.796
�士-0.774
UTF-0.766
osph-0.730
py-0.717
Token I
Token ID314
Feature activation-1.42e+01

Pos logit contributions
 UCS+3.472
UTF+3.253
py+3.100
osph+2.988
pu+2.883
Neg logit contributions
ellar-5.150
yrinth-5.135
 Klux-4.315
 Balloon-4.314
BW-4.259
Token encountered
Token ID12956
Feature activation-4.54e+00

Pos logit contributions
 UCS+5.331
UTF+4.811
osph+4.790
py+4.517
ansen+4.300
Neg logit contributions
ellar-13.004
yrinth-12.774
BW-11.807
 Balloon-11.779
 Doodle-11.370
Token.
Token ID13
Feature activation-8.25e+00

Pos logit contributions
 UCS+2.844
UTF+2.707
py+2.547
osph+2.485
pu+2.426
Neg logit contributions
yrinth-3.795
ellar-3.734
 Klux-3.155
 Balloon-3.124
 Doodle-3.116
Token Assuming
Token ID33238
Feature activation-1.83e+00

Pos logit contributions
 UCS+5.100
UTF+4.911
�士+4.695
osph+4.414
py+4.408
Neg logit contributions
ellar-6.677
yrinth-6.604
BW-5.645
 Klux-5.639
----------5.564
Token you
Token ID345
Feature activation+2.26e+00

Pos logit contributions
 UCS+1.290
UTF+1.228
�士+1.178
py+1.155
osph+1.152
Neg logit contributions
ellar-1.386
yrinth-1.377
 Priv-1.155
 Balloon-1.148
 Klux-1.146
Token already
Token ID1541
Feature activation+5.08e+00

Pos logit contributions
ellar+1.233
yrinth+1.202
 Priv+0.964
 Balloon+0.939
 Klux+0.935
Neg logit contributions
 UCS-2.051
�士-2.006
UTF-1.984
osph-1.909
py-1.872
Token very
Token ID845
Feature activation+8.26e-01

Pos logit contributions
ellar+2.613
yrinth+2.583
 drag+2.183
 Priv+2.164
 Klux+2.136
Neg logit contributions
 UCS-4.150
�士-4.113
UTF-4.075
osph-3.911
py-3.779
Token poorly
Token ID13455
Feature activation+3.93e+00

Pos logit contributions
ellar+0.435
yrinth+0.426
 Priv+0.339
 Balloon+0.330
 Klux+0.329
Neg logit contributions
 UCS-0.764
�士-0.740
UTF-0.740
osph-0.712
py-0.702
Token when
Token ID618
Feature activation+6.58e-01

Pos logit contributions
ellar+2.565
yrinth+2.519
 Priv+2.170
 drag+2.124
 Balloon+2.107
Neg logit contributions
�士-3.059
 UCS-3.053
UTF-2.943
osph-2.804
py-2.730
Token voters
Token ID4446
Feature activation+1.37e+00

Pos logit contributions
ellar+0.451
yrinth+0.441
 Priv+0.376
 Balloon+0.364
 Klux+0.363
Neg logit contributions
 UCS-0.504
�士-0.487
UTF-0.486
osph-0.463
py-0.458
Token are
Token ID389
Feature activation+4.34e+00

Pos logit contributions
ellar+0.965
yrinth+0.940
 Priv+0.802
 Balloon+0.788
 drag+0.786
Neg logit contributions
 UCS-1.020
�士-0.992
UTF-0.987
osph-0.926
py-0.915
Token asked
Token ID1965
Feature activation+7.47e+00

Pos logit contributions
ellar+2.682
yrinth+2.625
 Priv+2.258
 drag+2.199
 Klux+2.152
Neg logit contributions
 UCS-3.514
�士-3.404
UTF-3.398
osph-3.214
py-3.195
Token about
Token ID546
Feature activation+4.85e+00

Pos logit contributions
ellar+4.517
yrinth+4.398
 drag+3.881
 Priv+3.861
---------+3.717
Neg logit contributions
 UCS-5.754
�士-5.738
UTF-5.659
osph-5.465
py-5.260
Token her
Token ID607
Feature activation+2.79e+00

Pos logit contributions
ellar+2.833
yrinth+2.761
 Priv+2.373
 drag+2.275
 Klux+2.218
Neg logit contributions
 UCS-4.012
�士-3.998
UTF-3.979
osph-3.793
py-3.707
Token honesty
Token ID24345
Feature activation+5.20e+00

Pos logit contributions
ellar+1.907
yrinth+1.876
 Priv+1.619
 Balloon+1.568
---------+1.562
Neg logit contributions
 UCS-2.087
�士-2.075
UTF-2.031
osph-1.942
py-1.895
Token and
Token ID290
Feature activation+2.42e+00

Pos logit contributions
ellar+3.310
yrinth+3.259
 Priv+2.827
 drag+2.743
---------+2.741
Neg logit contributions
 UCS-4.065
�士-4.017
UTF-3.917
osph-3.710
py-3.636
Token trust
Token ID3774
Feature activation+7.21e+00

Pos logit contributions
ellar+1.510
yrinth+1.478
 Priv+1.251
 Balloon+1.198
 drag+1.197
Neg logit contributions
 UCS-1.972
UTF-1.928
�士-1.928
osph-1.837
py-1.809
Token also
Token ID635
Feature activation+4.82e+00

Pos logit contributions
ellar+0.225
yrinth+0.222
 Priv+0.186
 Balloon+0.184
 drag+0.181
Neg logit contributions
 UCS-0.253
�士-0.245
UTF-0.244
osph-0.231
py-0.226
Token tended
Token ID19960
Feature activation+2.79e+00

Pos logit contributions
ellar+3.172
yrinth+3.111
 drag+2.718
 Balloon+2.673
 Priv+2.655
Neg logit contributions
 UCS-3.694
�士-3.682
UTF-3.613
osph-3.360
py-3.261
Token to
Token ID284
Feature activation+5.85e+00

Pos logit contributions
ellar+1.907
yrinth+1.842
 drag+1.560
 Balloon+1.539
 Priv+1.520
Neg logit contributions
 UCS-2.159
�士-2.100
UTF-2.068
osph-1.955
py-1.931
Token corro
Token ID26132
Feature activation-3.02e+00

Pos logit contributions
ellar+3.907
yrinth+3.761
 drag+3.477
 Balloon+3.247
 Priv+3.238
Neg logit contributions
�士-4.506
 UCS-4.423
UTF-4.370
osph-3.999
pu-3.890
Tokende
Token ID2934
Feature activation-6.09e-01

Pos logit contributions
 UCS+1.919
UTF+1.816
py+1.759
osph+1.749
�士+1.741
Neg logit contributions
ellar-2.457
yrinth-2.421
 Priv-2.084
BW-2.055
 Balloon-2.054
Token quickly
Token ID2952
Feature activation+6.95e+00

Pos logit contributions
 UCS+0.454
�士+0.437
UTF+0.436
osph+0.415
py+0.408
Neg logit contributions
ellar-0.433
yrinth-0.425
 Priv-0.360
 Balloon-0.355
 Klux-0.352
Token,
Token ID11
Feature activation+5.56e+00

Pos logit contributions
ellar+4.130
yrinth+3.900
 drag+3.450
 Balloon+3.385
 Priv+3.336
Neg logit contributions
�士-5.793
 UCS-5.612
UTF-5.451
osph-5.093
pu-5.005
Token short
Token ID1790
Feature activation+5.28e+00

Pos logit contributions
ellar+3.554
yrinth+3.428
 drag+2.960
 Priv+2.932
 Balloon+2.923
Neg logit contributions
 UCS-4.321
�士-4.303
UTF-4.222
osph-3.977
py-3.897
Tokenening
Token ID3101
Feature activation+8.46e-02

Pos logit contributions
ellar+3.472
yrinth+3.398
 Balloon+2.909
 drag+2.906
 Priv+2.846
Neg logit contributions
 UCS-3.978
�士-3.968
UTF-3.882
osph-3.693
py-3.631
Token the
Token ID262
Feature activation-1.61e+00

Pos logit contributions
ellar+0.056
yrinth+0.055
 Priv+0.046
 Balloon+0.046
 drag+0.045
Neg logit contributions
 UCS-0.067
�士-0.065
UTF-0.064
osph-0.061
py-0.061
Token life
Token ID1204
Feature activation-2.80e+00

Pos logit contributions
 UCS+1.222
UTF+1.172
�士+1.167
osph+1.116
py+1.100
Neg logit contributions
ellar-1.121
yrinth-1.104
 Priv-0.927
 Balloon-0.912
 Klux-0.911
Token x
Token ID2124
Feature activation+4.17e+00

Pos logit contributions
ellar+3.808
yrinth+3.653
 Priv+3.202
 Balloon+3.107
 drag+3.018
Neg logit contributions
�士-6.945
 UCS-6.841
UTF-6.782
osph-6.601
py-6.342
Token.
Token ID13
Feature activation+7.67e+00

Pos logit contributions
ellar+2.818
yrinth+2.673
 Priv+2.352
---------+2.316
 Balloon+2.297
Neg logit contributions
�士-3.228
 UCS-3.165
UTF-3.027
osph-2.939
py-2.819
Tokenx
Token ID87
Feature activation+9.49e+00

Pos logit contributions
ellar+3.832
yrinth+3.596
 Klux+2.959
BW+2.906
---------+2.899
Neg logit contributions
�士-7.203
 UCS-7.035
UTF-6.651
osph-6.415
-6.168
Token.
Token ID13
Feature activation+9.65e+00

Pos logit contributions
ellar+5.297
yrinth+4.621
---------+4.458
[_+4.445
 Priv+4.428
Neg logit contributions
�士-8.604
 UCS-7.737
UTF-7.450
osph-7.389
senal-7.260
Tokenx
Token ID87
Feature activation+1.07e+01

Pos logit contributions
ellar+4.444
yrinth+4.360
 Klux+3.457
BW+3.374
 Priv+3.358
Neg logit contributions
 UCS-8.908
�士-8.616
UTF-8.459
osph-8.185
-7.784
Token.
Token ID13
Feature activation+8.66e+00

Pos logit contributions
ellar+5.635
yrinth+4.957
[_+4.859
---------+4.845
 Priv+4.843
Neg logit contributions
�士-9.639
 UCS-8.722
osph-8.560
UTF-8.534
senal-8.150
Token78
Token ID3695
Feature activation-3.70e+00

Pos logit contributions
ellar+4.313
yrinth+4.283
[_+3.452
 Klux+3.448
---------+3.424
Neg logit contributions
 UCS-7.737
UTF-7.433
�士-7.412
osph-7.223
-6.701
Token 115
Token ID12279
Feature activation+1.14e+00

Pos logit contributions
 UCS+2.351
UTF+2.231
�士+2.197
osph+2.092
py+2.070
Neg logit contributions
ellar-3.050
yrinth-3.004
 Priv-2.564
 Klux-2.559
 Balloon-2.557
Token16
Token ID1433
Feature activation+9.46e+00

Pos logit contributions
ellar+0.917
yrinth+0.891
 Priv+0.782
 Balloon+0.767
---------+0.764
Neg logit contributions
 UCS-0.733
�士-0.711
UTF-0.696
osph-0.672
py-0.646
Token72
Token ID4761
Feature activation+8.46e+00

Pos logit contributions
ellar+5.933
yrinth+5.382
 Priv+5.131
---------+5.103
 Balloon+5.073
Neg logit contributions
�士-7.188
 UCS-6.848
osph-6.731
UTF-6.658
py-6.082
Token x
Token ID2124
Feature activation+4.49e+00

Pos logit contributions
ellar+3.820
yrinth+3.755
 Priv+3.250
 Balloon+3.086
 drag+3.045
Neg logit contributions
�士-7.643
 UCS-7.603
UTF-7.491
osph-7.301
py-7.106
Token is
Token ID318
Feature activation+1.05e+00

Pos logit contributions
 UCS+2.800
UTF+2.696
�士+2.669
osph+2.565
py+2.532
Neg logit contributions
ellar-2.673
yrinth-2.633
 Priv-2.209
 Balloon-2.182
 Klux-2.181
Token strongly
Token ID7634
Feature activation+1.56e+00

Pos logit contributions
ellar+0.721
yrinth+0.708
 Priv+0.604
 Balloon+0.589
 drag+0.579
Neg logit contributions
 UCS-0.799
�士-0.780
UTF-0.776
osph-0.743
py-0.726
Token influenced
Token ID12824
Feature activation-7.37e+00

Pos logit contributions
ellar+1.034
yrinth+1.013
 Priv+0.858
 Balloon+0.837
 Klux+0.822
Neg logit contributions
 UCS-1.212
�士-1.178
UTF-1.173
osph-1.129
py-1.097
Token by
Token ID416
Feature activation-8.06e+00

Pos logit contributions
 UCS+5.196
UTF+4.991
�士+4.957
osph+4.730
py+4.715
Neg logit contributions
ellar-5.346
yrinth-5.255
 Priv-4.408
 Balloon-4.403
 Doodle-4.399
Token the
Token ID262
Feature activation-2.31e+00

Pos logit contributions
 UCS+5.880
UTF+5.508
�士+5.436
py+5.207
osph+5.170
Neg logit contributions
ellar-5.784
yrinth-5.673
 Klux-4.671
 Balloon-4.634
 Doodle-4.613
Token story
Token ID1621
Feature activation+7.09e+00

Pos logit contributions
 UCS+1.780
UTF+1.706
�士+1.697
osph+1.621
py+1.602
Neg logit contributions
ellar-1.596
yrinth-1.570
 Priv-1.307
 Balloon-1.292
 Klux-1.290
Token of
Token ID286
Feature activation-3.39e-02

Pos logit contributions
yrinth+4.360
ellar+4.318
 Priv+3.752
 Balloon+3.575
 drag+3.563
Neg logit contributions
 UCS-5.513
UTF-5.467
�士-5.467
osph-5.231
py-5.056
Token George
Token ID4502
Feature activation+1.26e+00

Pos logit contributions
 UCS+0.025
�士+0.024
UTF+0.024
osph+0.023
py+0.023
Neg logit contributions
ellar-0.024
yrinth-0.024
 Priv-0.020
 Balloon-0.020
 Klux-0.020
Token W
Token ID370
Feature activation+5.69e+00

Pos logit contributions
ellar+0.831
yrinth+0.802
 Priv+0.701
 Balloon+0.689
 Klux+0.674
Neg logit contributions
 UCS-0.985
�士-0.969
UTF-0.966
osph-0.919
py-0.898
Token.
Token ID13
Feature activation+5.08e+00

Pos logit contributions
ellar+3.685
yrinth+3.611
 Priv+3.048
 Klux+3.018
 Balloon+3.018
Neg logit contributions
 UCS-4.390
UTF-4.245
�士-4.119
py-3.965
osph-3.953
Token Bush
Token ID5511
Feature activation+2.20e+00

Pos logit contributions
ellar+2.068
yrinth+1.934
 Priv+1.608
 Balloon+1.531
 Klux+1.520
Neg logit contributions
 UCS-5.179
�士-5.107
UTF-5.066
osph-4.898
py-4.816
Token've
Token ID1053
Feature activation+3.16e+00

Pos logit contributions
ellar+3.269
yrinth+3.208
 drag+2.852
 Priv+2.783
 Balloon+2.718
Neg logit contributions
�士-3.785
 UCS-3.756
UTF-3.669
osph-3.442
py-3.369
Token spoke
Token ID5158
Feature activation-1.35e+00

Pos logit contributions
ellar+2.127
yrinth+2.074
 Priv+1.800
 Balloon+1.764
 drag+1.756
Neg logit contributions
 UCS-2.416
�士-2.395
UTF-2.337
osph-2.217
py-2.158
Token,
Token ID11
Feature activation-5.64e-01

Pos logit contributions
 UCS+0.990
UTF+0.953
�士+0.943
osph+0.902
py+0.891
Neg logit contributions
ellar-0.971
yrinth-0.958
 Priv-0.805
 Klux-0.794
 Balloon-0.794
Token "
Token ID366
Feature activation+3.56e+00

Pos logit contributions
 UCS+0.429
UTF+0.413
�士+0.412
osph+0.393
py+0.387
Neg logit contributions
ellar-0.392
yrinth-0.386
 Priv-0.325
 Balloon-0.320
 Klux-0.317
TokenBel
Token ID12193
Feature activation+8.99e+00

Pos logit contributions
ellar+2.368
yrinth+2.328
---------+1.986
BW+1.981
 Priv+1.973
Neg logit contributions
 UCS-2.737
�士-2.677
UTF-2.538
osph-2.525
py-2.382
Tokenieve
Token ID12311
Feature activation+8.80e+00

Pos logit contributions
yrinth+4.079
ellar+3.874
apor+3.195
 Priv+3.176
 drag+3.115
Neg logit contributions
�士-8.367
 UCS-8.285
UTF-8.063
osph-7.617
-7.409
Token me
Token ID502
Feature activation+1.83e-01

Pos logit contributions
ellar+4.867
yrinth+4.630
 Priv+3.924
 Balloon+3.836
 drag+3.792
Neg logit contributions
�士-7.287
 UCS-7.230
UTF-7.104
osph-6.992
pu-6.723
Token,
Token ID11
Feature activation+7.51e-01

Pos logit contributions
ellar+0.126
yrinth+0.125
 Priv+0.106
 Balloon+0.105
---------+0.103
Neg logit contributions
 UCS-0.139
�士-0.134
UTF-0.133
osph-0.128
py-0.125
Token Anna
Token ID11735
Feature activation-3.05e+00

Pos logit contributions
ellar+0.536
yrinth+0.528
 Priv+0.450
 Balloon+0.445
 Klux+0.436
Neg logit contributions
 UCS-0.553
�士-0.535
UTF-0.533
osph-0.508
py-0.497
Token.
Token ID13
Feature activation+2.70e+00

Pos logit contributions
 UCS+2.155
UTF+2.068
�士+2.051
osph+1.949
py+1.938
Neg logit contributions
ellar-2.280
yrinth-2.245
 Priv-1.901
 Klux-1.880
 Balloon-1.876
Token If
Token ID1002
Feature activation+3.47e+00

Pos logit contributions
ellar+1.857
yrinth+1.813
 Priv+1.611
 Balloon+1.590
 Doodle+1.546
Neg logit contributions
 UCS-1.986
�士-1.968
UTF-1.928
osph-1.881
py-1.797
Token Ireland
Token ID7517
Feature activation+1.79e-01

Pos logit contributions
ellar+1.567
yrinth+1.543
 Priv+1.302
 Balloon+1.267
 drag+1.255
Neg logit contributions
 UCS-1.967
�士-1.908
UTF-1.904
osph-1.817
py-1.794
Token
Token ID447
Feature activation-1.52e+00

Pos logit contributions
ellar+0.125
yrinth+0.122
 Priv+0.103
 Balloon+0.102
 Klux+0.101
Neg logit contributions
 UCS-0.136
�士-0.131
UTF-0.131
osph-0.124
py-0.122
Token
Token ID247
Feature activation-2.64e-01

Pos logit contributions
 UCS+1.478
UTF+1.440
�士+1.433
osph+1.389
py+1.370
Neg logit contributions
ellar-0.726
yrinth-0.713
 Priv-0.543
 Balloon-0.532
 Klux-0.524
Tokens
Token ID82
Feature activation-1.42e+00

Pos logit contributions
 UCS+0.191
UTF+0.184
�士+0.184
osph+0.174
py+0.170
Neg logit contributions
ellar-0.193
yrinth-0.191
 Priv-0.162
 Balloon-0.159
 Klux-0.159
Token national
Token ID2260
Feature activation-1.94e-02

Pos logit contributions
 UCS+1.100
UTF+1.056
�士+1.045
osph+1.006
py+0.992
Neg logit contributions
ellar-0.968
yrinth-0.951
 Priv-0.789
 Balloon-0.782
 Klux-0.781
Token accounts
Token ID5504
Feature activation+1.34e+00

Pos logit contributions
 UCS+0.014
�士+0.014
UTF+0.014
osph+0.013
py+0.013
Neg logit contributions
ellar-0.014
yrinth-0.014
 Priv-0.012
 Balloon-0.011
 Klux-0.011
Token will
Token ID481
Feature activation-3.27e+00

Pos logit contributions
ellar+0.946
yrinth+0.933
 Priv+0.794
 Balloon+0.782
 drag+0.776
Neg logit contributions
 UCS-0.998
�士-0.962
UTF-0.960
osph-0.904
py-0.887
Token also
Token ID635
Feature activation-1.72e+00

Pos logit contributions
 UCS+2.374
UTF+2.257
�士+2.216
osph+2.191
py+2.155
Neg logit contributions
ellar-2.369
yrinth-2.335
 Priv-1.955
 Klux-1.949
 Balloon-1.923
Token provide
Token ID2148
Feature activation+1.99e+00

Pos logit contributions
 UCS+1.212
UTF+1.156
�士+1.147
osph+1.105
py+1.088
Neg logit contributions
ellar-1.293
yrinth-1.274
 Priv-1.080
 Klux-1.068
 Balloon-1.066
Token few
Token ID1178
Feature activation-3.57e+00

Pos logit contributions
ellar+1.311
yrinth+1.278
 Priv+1.080
 drag+1.058
 Balloon+1.053
Neg logit contributions
 UCS-1.565
�士-1.526
UTF-1.520
osph-1.454
py-1.420
Token answers
Token ID7429
Feature activation-8.94e-01

Pos logit contributions
 UCS+2.674
UTF+2.558
�士+2.533
osph+2.422
py+2.413
Neg logit contributions
ellar-2.490
yrinth-2.483
 Priv-2.075
 Balloon-2.066
 Klux-2.063
Token remarkable
Token ID11004
Feature activation-1.05e+00

Pos logit contributions
ellar+0.051
yrinth+0.050
 Priv+0.043
 Balloon+0.042
 Klux+0.042
Neg logit contributions
 UCS-0.058
UTF-0.056
�士-0.056
osph-0.053
py-0.052
Token with
Token ID351
Feature activation+6.31e+00

Pos logit contributions
 UCS+0.784
UTF+0.754
�士+0.752
osph+0.716
py+0.705
Neg logit contributions
ellar-0.744
yrinth-0.732
 Priv-0.618
 Balloon-0.609
 Klux-0.606
Token regard
Token ID2754
Feature activation+2.63e+00

Pos logit contributions
ellar+3.809
yrinth+3.744
 Priv+3.220
 Balloon+3.178
 drag+3.122
Neg logit contributions
�士-5.031
 UCS-5.022
UTF-4.911
osph-4.778
py-4.549
Token to
Token ID284
Feature activation+4.49e+00

Pos logit contributions
ellar+1.845
yrinth+1.779
 Priv+1.529
 Balloon+1.500
 drag+1.497
Neg logit contributions
�士-1.967
 UCS-1.966
UTF-1.897
osph-1.805
py-1.766
Token common
Token ID2219
Feature activation+3.34e+00

Pos logit contributions
ellar+2.790
yrinth+2.742
 Priv+2.373
 Balloon+2.336
 drag+2.318
Neg logit contributions
 UCS-3.547
�士-3.544
UTF-3.501
osph-3.346
py-3.209
Token species
Token ID4693
Feature activation+1.93e-01

Pos logit contributions
ellar+2.251
yrinth+2.204
 Priv+1.886
 Balloon+1.842
 drag+1.820
Neg logit contributions
 UCS-2.561
�士-2.516
UTF-2.468
osph-2.344
py-2.264
Token,
Token ID11
Feature activation-8.31e-01

Pos logit contributions
ellar+0.129
yrinth+0.126
 Priv+0.106
 Balloon+0.104
 Klux+0.102
Neg logit contributions
 UCS-0.152
�士-0.148
UTF-0.148
osph-0.140
py-0.137
Token wildlife
Token ID15599
Feature activation-1.32e+00

Pos logit contributions
 UCS+0.642
UTF+0.618
�士+0.618
osph+0.589
py+0.579
Neg logit contributions
ellar-0.567
yrinth-0.557
 Priv-0.468
 Balloon-0.461
 Klux-0.457
Token video
Token ID2008
Feature activation+2.73e+00

Pos logit contributions
 UCS+1.007
UTF+0.971
�士+0.970
osph+0.922
py+0.908
Neg logit contributions
ellar-0.919
yrinth-0.903
 Priv-0.761
 Balloon-0.749
 Klux-0.744
Token of
Token ID286
Feature activation+6.77e+00

Pos logit contributions
ellar+1.898
yrinth+1.841
 Priv+1.593
 drag+1.558
 Balloon+1.554
Neg logit contributions
 UCS-2.037
�士-2.020
UTF-1.981
osph-1.856
py-1.819
Token the
Token ID262
Feature activation+6.27e+00

Pos logit contributions
ellar+3.971
yrinth+3.915
 Priv+3.364
 drag+3.354
 Balloon+3.301
Neg logit contributions
�士-5.470
UTF-5.404
 UCS-5.402
osph-5.162
py-4.879
Token huge
Token ID3236
Feature activation+2.09e+00

Pos logit contributions
ellar+1.091
yrinth+1.058
 Priv+0.926
 drag+0.908
 Balloon+0.902
Neg logit contributions
 UCS-1.154
�士-1.150
UTF-1.124
osph-1.070
py-1.041
Token portion
Token ID6903
Feature activation+1.19e+00

Pos logit contributions
ellar+1.403
yrinth+1.355
 Priv+1.197
 drag+1.178
 Balloon+1.152
Neg logit contributions
 UCS-1.586
�士-1.577
UTF-1.554
osph-1.482
py-1.450
Token of
Token ID286
Feature activation+2.59e+00

Pos logit contributions
ellar+0.804
yrinth+0.783
 Priv+0.661
 Balloon+0.648
 Klux+0.641
Neg logit contributions
 UCS-0.934
�士-0.913
UTF-0.899
osph-0.857
py-0.842
Token its
Token ID663
Feature activation+4.65e+00

Pos logit contributions
ellar+1.557
yrinth+1.525
 Priv+1.289
 Balloon+1.248
 drag+1.246
Neg logit contributions
 UCS-2.149
�士-2.128
UTF-2.102
osph-2.025
py-1.975
Token revenue
Token ID6426
Feature activation+3.11e+00

Pos logit contributions
ellar+2.897
yrinth+2.803
 Priv+2.504
 drag+2.460
 Doodle+2.383
Neg logit contributions
�士-3.689
 UCS-3.609
UTF-3.554
osph-3.437
pu-3.311
Token from
Token ID422
Feature activation-4.62e-01

Pos logit contributions
ellar+2.029
yrinth+1.980
 Priv+1.682
 drag+1.653
 Balloon+1.634
Neg logit contributions
 UCS-2.434
�士-2.416
UTF-2.355
osph-2.209
pu-2.166
Token online
Token ID2691
Feature activation+1.49e+00

Pos logit contributions
 UCS+0.360
�士+0.348
UTF+0.348
osph+0.332
py+0.326
Neg logit contributions
ellar-0.311
yrinth-0.305
 Priv-0.257
 Balloon-0.253
 Klux-0.250
Token ads
Token ID9011
Feature activation-2.86e+00

Pos logit contributions
ellar+0.955
yrinth+0.939
 Priv+0.791
 Balloon+0.778
 drag+0.773
Neg logit contributions
 UCS-1.201
�士-1.174
UTF-1.170
osph-1.115
py-1.089
Token,
Token ID11
Feature activation+5.99e-01

Pos logit contributions
 UCS+2.127
UTF+2.043
�士+2.028
osph+1.941
py+1.919
Neg logit contributions
ellar-2.039
yrinth-2.006
 Priv-1.693
 Balloon-1.669
 Klux-1.667
Token Google
Token ID3012
Feature activation-2.98e+00

Pos logit contributions
ellar+0.421
yrinth+0.415
 Priv+0.354
 Balloon+0.348
 Doodle+0.343
Neg logit contributions
 UCS-0.446
UTF-0.433
�士-0.433
osph-0.412
py-0.403
Token has
Token ID468
Feature activation+1.63e-01

Pos logit contributions
 UCS+2.252
UTF+2.158
�士+2.139
osph+2.048
py+2.027
Neg logit contributions
ellar-2.095
yrinth-2.065
 Priv-1.724
 Klux-1.701
 Balloon-1.696
Tokena
Token ID64
Feature activation+7.24e+00

Pos logit contributions
ellar+1.937
yrinth+1.898
 Priv+1.601
 Balloon+1.544
---------+1.543
Neg logit contributions
 UCS-2.448
�士-2.376
UTF-2.347
osph-2.247
py-2.183
Token measure
Token ID3953
Feature activation+4.49e+00

Pos logit contributions
ellar+4.286
yrinth+4.234
 Priv+3.746
 drag+3.685
 Balloon+3.568
Neg logit contributions
�士-5.830
 UCS-5.754
UTF-5.698
osph-5.393
py-5.195
Token that
Token ID326
Feature activation+5.65e+00

Pos logit contributions
ellar+2.889
yrinth+2.791
 Priv+2.487
 Balloon+2.341
 drag+2.326
Neg logit contributions
 UCS-3.543
�士-3.471
UTF-3.461
osph-3.292
py-3.229
Token itself
Token ID2346
Feature activation+1.86e+00

Pos logit contributions
ellar+3.501
yrinth+3.447
 Priv+3.068
 Balloon+2.933
 drag+2.893
Neg logit contributions
 UCS-4.411
�士-4.355
UTF-4.337
osph-4.149
py-4.040
Token stretched
Token ID19110
Feature activation-3.29e+00

Pos logit contributions
ellar+1.210
yrinth+1.195
 Priv+1.018
 Balloon+0.993
 drag+0.988
Neg logit contributions
 UCS-1.465
�士-1.428
UTF-1.417
osph-1.349
py-1.317
Token the
Token ID262
Feature activation+1.14e+00

Pos logit contributions
 UCS+2.606
UTF+2.515
�士+2.489
osph+2.388
py+2.365
Neg logit contributions
ellar-2.161
yrinth-2.138
 Priv-1.746
 Balloon-1.729
 Klux-1.727
Token bounds
Token ID22303
Feature activation-2.20e+00

Pos logit contributions
ellar+0.740
yrinth+0.726
 Priv+0.610
 Balloon+0.599
 Klux+0.591
Neg logit contributions
 UCS-0.911
�士-0.879
UTF-0.876
osph-0.837
py-0.826
Token of
Token ID286
Feature activation-7.08e-01

Pos logit contributions
 UCS+1.642
UTF+1.582
�士+1.578
osph+1.503
py+1.486
Neg logit contributions
ellar-1.554
yrinth-1.532
 Priv-1.287
 Balloon-1.269
 Klux-1.269
Token democratic
Token ID10518
Feature activation+6.13e-01

Pos logit contributions
 UCS+0.595
UTF+0.574
�士+0.572
osph+0.549
py+0.541
Neg logit contributions
ellar-0.436
yrinth-0.428
 Priv-0.352
 Balloon-0.345
 Klux-0.343
Token legitimacy
Token ID22726
Feature activation+8.89e-01

Pos logit contributions
ellar+0.375
yrinth+0.365
 Priv+0.304
 Balloon+0.298
 Klux+0.293
Neg logit contributions
 UCS-0.517
�士-0.500
UTF-0.499
osph-0.478
py-0.471
Token.
Token ID13
Feature activation+1.39e+00

Pos logit contributions
ellar+0.621
yrinth+0.606
 Priv+0.519
 Balloon+0.509
 Klux+0.503
Neg logit contributions
 UCS-0.670
�士-0.648
UTF-0.641
osph-0.611
py-0.597
Token about
Token ID546
Feature activation-3.67e+00

Pos logit contributions
ellar+2.182
yrinth+2.131
 Priv+1.826
 drag+1.791
 Balloon+1.786
Neg logit contributions
�士-2.543
 UCS-2.529
UTF-2.464
osph-2.344
py-2.266
Token that
Token ID326
Feature activation-4.52e+00

Pos logit contributions
 UCS+2.843
UTF+2.705
�士+2.646
osph+2.558
py+2.549
Neg logit contributions
ellar-2.527
yrinth-2.504
 Priv-2.034
 Klux-2.023
 Balloon-2.017
Token day
Token ID1110
Feature activation+3.95e+00

Pos logit contributions
 UCS+3.359
UTF+3.177
�士+3.086
py+2.992
osph+2.984
Neg logit contributions
ellar-3.250
yrinth-3.239
 Priv-2.643
 Klux-2.633
 Balloon-2.609
Token's
Token ID338
Feature activation+1.51e+00

Pos logit contributions
ellar+2.636
yrinth+2.571
 Priv+2.199
 Balloon+2.175
---------+2.163
Neg logit contributions
�士-3.009
 UCS-2.996
UTF-2.941
osph-2.791
py-2.703
Token game
Token ID983
Feature activation+6.21e+00

Pos logit contributions
ellar+0.964
yrinth+0.946
 Priv+0.803
 Balloon+0.785
 Doodle+0.780
Neg logit contributions
 UCS-1.207
�士-1.194
UTF-1.180
osph-1.129
py-1.102
Token to
Token ID284
Feature activation-3.84e-01

Pos logit contributions
ellar+3.922
yrinth+3.771
 Priv+3.284
---------+3.269
 drag+3.249
Neg logit contributions
�士-4.909
 UCS-4.788
UTF-4.684
osph-4.493
pu-4.317
Token be
Token ID307
Feature activation-5.56e+00

Pos logit contributions
 UCS+0.295
UTF+0.284
�士+0.284
osph+0.270
py+0.266
Neg logit contributions
ellar-0.264
yrinth-0.260
 Priv-0.218
 Balloon-0.215
 Klux-0.214
Token played
Token ID2826
Feature activation+1.17e+00

Pos logit contributions
 UCS+4.135
UTF+3.920
�士+3.878
py+3.735
osph+3.718
Neg logit contributions
ellar-3.918
yrinth-3.884
 Priv-3.174
 Balloon-3.140
 Klux-3.129
Token in
Token ID287
Feature activation+2.14e+00

Pos logit contributions
ellar+0.800
yrinth+0.781
 Priv+0.667
 Balloon+0.659
 Klux+0.650
Neg logit contributions
 UCS-0.890
�士-0.877
UTF-0.860
osph-0.822
py-0.801
Token freezing
Token ID20884
Feature activation+7.93e-01

Pos logit contributions
ellar+1.413
yrinth+1.385
 Priv+1.186
 Balloon+1.178
 drag+1.165
Neg logit contributions
 UCS-1.645
�士-1.642
UTF-1.620
osph-1.559
py-1.511
Token temperatures
Token ID10101
Feature activation-2.44e+00

Pos logit contributions
ellar+0.529
yrinth+0.517
 Priv+0.438
 Balloon+0.434
 Klux+0.427
Neg logit contributions
 UCS-0.617
�士-0.605
UTF-0.600
osph-0.572
py-0.562
Token {
Token ID1391
Feature activation-6.24e+00

Pos logit contributions
 UCS+2.868
UTF+2.745
�士+2.703
osph+2.589
py+2.579
Neg logit contributions
ellar-2.676
yrinth-2.636
 Priv-2.208
 Klux-2.187
 Balloon-2.176
Token1
Token ID16
Feature activation-5.00e-01

Pos logit contributions
 UCS+4.655
UTF+4.473
�士+4.354
py+4.239
osph+4.194
Neg logit contributions
ellar-4.343
yrinth-4.270
 Priv-3.602
 Klux-3.560
 Balloon-3.507
Token,
Token ID11
Feature activation-6.25e+00

Pos logit contributions
 UCS+0.384
�士+0.371
UTF+0.370
osph+0.353
py+0.346
Neg logit contributions
ellar-0.343
yrinth-0.336
 Priv-0.282
 Balloon-0.279
 Klux-0.276
Token6
Token ID21
Feature activation-1.55e+00

Pos logit contributions
 UCS+4.154
UTF+3.939
�士+3.835
osph+3.676
py+3.664
Neg logit contributions
ellar-4.876
yrinth-4.807
 Priv-4.092
 Klux-4.050
 Balloon-4.007
Token}
Token ID92
Feature activation-8.21e+00

Pos logit contributions
 UCS+1.118
UTF+1.075
�士+1.074
osph+1.021
py+1.000
Neg logit contributions
ellar-1.135
yrinth-1.116
 Priv-0.946
 Balloon-0.937
 Klux-0.929
Token has
Token ID468
Feature activation-6.60e+00

Pos logit contributions
 UCS+5.817
UTF+5.527
�士+5.255
py+5.224
osph+5.177
Neg logit contributions
ellar-5.858
yrinth-5.826
 Klux-4.892
 Priv-4.870
 Balloon-4.777
Token valid
Token ID4938
Feature activation-5.25e+00

Pos logit contributions
 UCS+4.874
UTF+4.635
�士+4.496
osph+4.330
py+4.293
Neg logit contributions
ellar-4.607
yrinth-4.564
 Priv-3.798
 Klux-3.791
BW-3.752
Token N
Token ID399
Feature activation-4.82e+00

Pos logit contributions
 UCS+3.970
UTF+3.818
�士+3.693
osph+3.561
py+3.540
Neg logit contributions
ellar-3.612
yrinth-3.565
 Klux-3.000
 Priv-2.980
 Balloon-2.926
TokenNs
Token ID47503
Feature activation-6.55e+00

Pos logit contributions
 UCS+3.858
UTF+3.750
�士+3.674
osph+3.535
py+3.504
Neg logit contributions
ellar-3.102
yrinth-3.073
 Priv-2.555
 Balloon-2.509
 Klux-2.500
Token at
Token ID379
Feature activation-4.78e+00

Pos logit contributions
 UCS+4.638
UTF+4.420
�士+4.177
py+4.120
osph+4.116
Neg logit contributions
ellar-4.779
yrinth-4.778
 Klux-4.025
 Priv-3.985
BW-3.892
Token {
Token ID1391
Feature activation-7.08e+00

Pos logit contributions
 UCS+3.600
UTF+3.434
�士+3.365
osph+3.232
py+3.215
Neg logit contributions
ellar-3.340
yrinth-3.289
 Priv-2.754
 Klux-2.731
BW-2.687
Token,
Token ID11
Feature activation-1.85e+00

Pos logit contributions
 UCS+3.670
UTF+3.511
�士+3.407
osph+3.317
py+3.303
Neg logit contributions
ellar-3.702
yrinth-3.672
 Klux-3.115
 Priv-3.104
 Balloon-3.058
Token so
Token ID523
Feature activation+1.30e+00

Pos logit contributions
 UCS+1.406
UTF+1.347
�士+1.338
osph+1.280
py+1.266
Neg logit contributions
ellar-1.297
yrinth-1.277
 Priv-1.067
 Klux-1.055
 Balloon-1.052
Token far
Token ID1290
Feature activation+2.09e+00

Pos logit contributions
ellar+0.784
yrinth+0.763
 Priv+0.629
 Balloon+0.617
 Klux+0.606
Neg logit contributions
 UCS-1.108
�士-1.087
UTF-1.077
osph-1.032
py-1.011
Token it
Token ID340
Feature activation-1.52e+00

Pos logit contributions
ellar+1.370
yrinth+1.342
 Priv+1.141
 Balloon+1.130
 Doodle+1.097
Neg logit contributions
 UCS-1.641
�士-1.607
UTF-1.598
osph-1.530
py-1.488
Token appears
Token ID3568
Feature activation+1.44e+00

Pos logit contributions
 UCS+1.174
UTF+1.129
�士+1.127
osph+1.076
py+1.060
Neg logit contributions
ellar-1.035
yrinth-1.018
 Priv-0.852
 Balloon-0.840
 Klux-0.835
Token as
Token ID355
Feature activation-7.68e+00

Pos logit contributions
ellar+0.988
yrinth+0.965
 Priv+0.826
 Balloon+0.816
 drag+0.793
Neg logit contributions
 UCS-1.096
�士-1.074
UTF-1.071
osph-1.021
py-0.993
Token though
Token ID996
Feature activation+1.71e+00

Pos logit contributions
 UCS+4.139
UTF+3.788
�士+3.713
py+3.574
osph+3.466
Neg logit contributions
ellar-6.926
yrinth-6.888
 Klux-6.010
 Balloon-5.908
BW-5.881
Token Ubuntu
Token ID14949
Feature activation-2.79e-01

Pos logit contributions
ellar+1.154
yrinth+1.128
 Priv+0.964
 Balloon+0.952
 Doodle+0.927
Neg logit contributions
 UCS-1.313
�士-1.291
UTF-1.284
osph-1.225
py-1.191
Token and
Token ID290
Feature activation+2.60e+00

Pos logit contributions
 UCS+0.213
UTF+0.206
�士+0.206
osph+0.196
py+0.193
Neg logit contributions
ellar-0.192
yrinth-0.188
 Priv-0.159
 Balloon-0.156
 Klux-0.154
Token its
Token ID663
Feature activation+2.39e+00

Pos logit contributions
ellar+1.736
yrinth+1.695
 Priv+1.466
 Balloon+1.439
 drag+1.403
Neg logit contributions
 UCS-1.987
�士-1.977
UTF-1.960
osph-1.877
py-1.819
Token community
Token ID2055
Feature activation-2.16e+00

Pos logit contributions
ellar+1.601
yrinth+1.530
 Priv+1.337
 Balloon+1.302
 Doodle+1.288
Neg logit contributions
�士-1.833
 UCS-1.830
UTF-1.808
osph-1.732
py-1.676
Token it
Token ID340
Feature activation+1.32e+00

Pos logit contributions
 UCS+2.807
UTF+2.655
�士+2.622
osph+2.534
py+2.504
Neg logit contributions
ellar-2.828
yrinth-2.765
 Klux-2.308
 Priv-2.304
 Balloon-2.288
Token is
Token ID318
Feature activation-1.56e+00

Pos logit contributions
ellar+0.915
yrinth+0.906
 Priv+0.760
 Balloon+0.748
 Klux+0.739
Neg logit contributions
 UCS-0.998
�士-0.967
UTF-0.959
osph-0.906
py-0.888
Token one
Token ID530
Feature activation-5.33e+00

Pos logit contributions
 UCS+1.197
UTF+1.152
�士+1.151
osph+1.096
py+1.080
Neg logit contributions
ellar-1.079
yrinth-1.062
 Priv-0.892
 Balloon-0.878
 Klux-0.873
Token of
Token ID286
Feature activation+1.05e-01

Pos logit contributions
 UCS+3.784
UTF+3.605
�士+3.558
osph+3.426
py+3.402
Neg logit contributions
ellar-3.929
yrinth-3.859
 Priv-3.275
 Klux-3.266
 Balloon-3.240
Token the
Token ID262
Feature activation-6.60e-01

Pos logit contributions
ellar+0.070
yrinth+0.069
 Priv+0.058
 Balloon+0.057
---------+0.056
Neg logit contributions
 UCS-0.082
UTF-0.079
�士-0.079
osph-0.076
py-0.074
Token few
Token ID1178
Feature activation-2.30e+00

Pos logit contributions
 UCS+0.496
UTF+0.478
�士+0.477
osph+0.454
py+0.446
Neg logit contributions
ellar-0.464
yrinth-0.457
 Priv-0.386
 Balloon-0.380
 Klux-0.377
Token that
Token ID326
Feature activation-3.68e+00

Pos logit contributions
 UCS+1.870
UTF+1.800
�士+1.793
osph+1.719
py+1.698
Neg logit contributions
ellar-1.476
yrinth-1.449
 Priv-1.196
 Balloon-1.178
 Klux-1.173
Token my
Token ID616
Feature activation-3.32e+00

Pos logit contributions
 UCS+2.622
UTF+2.498
�士+2.470
osph+2.372
py+2.346
Neg logit contributions
ellar-2.737
yrinth-2.677
 Priv-2.267
 Klux-2.255
 Balloon-2.247
Token closest
Token ID11706
Feature activation+9.23e-01

Pos logit contributions
 UCS+2.441
UTF+2.327
�士+2.310
osph+2.211
py+2.190
Neg logit contributions
ellar-2.403
yrinth-2.361
 Priv-1.981
 Klux-1.969
 Balloon-1.960
Token gaming
Token ID7776
Feature activation-2.62e+00

Pos logit contributions
ellar+0.647
yrinth+0.633
 Priv+0.543
 Balloon+0.528
 Klux+0.521
Neg logit contributions
 UCS-0.692
UTF-0.673
�士-0.671
osph-0.641
py-0.625
Token mates
Token ID27973
Feature activation-1.16e+00

Pos logit contributions
 UCS+1.947
UTF+1.861
�士+1.855
osph+1.768
py+1.750
Neg logit contributions
ellar-1.867
yrinth-1.839
 Priv-1.542
 Balloon-1.526
 Klux-1.522
Token will
Token ID481
Feature activation-2.49e+00

Pos logit contributions
 UCS+2.375
UTF+2.252
�士+2.226
osph+2.129
py+2.123
Neg logit contributions
ellar-2.914
yrinth-2.866
 Priv-2.461
 Klux-2.435
 Balloon-2.426
Token also
Token ID635
Feature activation-7.68e-01

Pos logit contributions
 UCS+1.743
UTF+1.659
�士+1.640
osph+1.579
py+1.565
Neg logit contributions
ellar-1.881
yrinth-1.851
 Priv-1.574
 Klux-1.561
 Balloon-1.546
Token need
Token ID761
Feature activation-3.60e-01

Pos logit contributions
 UCS+0.516
UTF+0.494
�士+0.494
osph+0.466
py+0.457
Neg logit contributions
ellar-0.603
yrinth-0.594
 Priv-0.511
 Balloon-0.505
 Klux-0.500
Token to
Token ID284
Feature activation-3.05e+00

Pos logit contributions
 UCS+0.268
UTF+0.258
�士+0.256
osph+0.245
py+0.240
Neg logit contributions
ellar-0.258
yrinth-0.252
 Priv-0.213
 Balloon-0.210
 Klux-0.209
Token detach
Token ID48224
Feature activation-2.72e+00

Pos logit contributions
 UCS+2.224
UTF+2.124
�士+2.095
osph+2.027
py+2.006
Neg logit contributions
ellar-2.213
yrinth-2.181
 Priv-1.829
 Klux-1.813
 Balloon-1.803
Token the
Token ID262
Feature activation-5.19e+00

Pos logit contributions
 UCS+2.107
UTF+2.025
�士+2.020
osph+1.929
py+1.902
Neg logit contributions
ellar-1.852
yrinth-1.822
 Priv-1.523
 Balloon-1.500
 Klux-1.495
Token cables
Token ID18018
Feature activation-2.14e+00

Pos logit contributions
 UCS+3.987
UTF+3.770
�士+3.746
osph+3.587
py+3.584
Neg logit contributions
ellar-3.561
yrinth-3.519
 Klux-2.886
 Priv-2.878
 Doodle-2.837
Token leading
Token ID3756
Feature activation-1.89e+00

Pos logit contributions
 UCS+1.583
UTF+1.516
�士+1.505
osph+1.440
py+1.426
Neg logit contributions
ellar-1.530
yrinth-1.509
 Priv-1.267
 Balloon-1.250
 Klux-1.250
Token to
Token ID284
Feature activation-1.02e-01

Pos logit contributions
 UCS+1.374
UTF+1.319
�士+1.316
osph+1.251
py+1.230
Neg logit contributions
ellar-1.379
yrinth-1.356
 Priv-1.150
 Balloon-1.135
 Klux-1.128
Token the
Token ID262
Feature activation-2.35e+00

Pos logit contributions
 UCS+0.081
UTF+0.079
�士+0.078
osph+0.075
py+0.073
Neg logit contributions
ellar-0.068
yrinth-0.066
 Priv-0.056
 Balloon-0.055
 drag-0.054
Token traction
Token ID23692
Feature activation-1.99e+00

Pos logit contributions
 UCS+1.821
UTF+1.746
�士+1.739
osph+1.663
py+1.643
Neg logit contributions
ellar-1.608
yrinth-1.582
 Priv-1.316
 Klux-1.298
 Balloon-1.297
Token?
Token ID30
Feature activation-2.81e+00

Pos logit contributions
 UCS+3.657
UTF+3.475
�士+3.404
py+3.310
osph+3.287
Neg logit contributions
yrinth-3.903
ellar-3.887
 Priv-3.256
 Klux-3.251
 Balloon-3.232
Token Think
Token ID11382
Feature activation+3.76e+00

Pos logit contributions
 UCS+2.107
UTF+2.010
�士+1.990
osph+1.898
py+1.894
Neg logit contributions
ellar-1.995
yrinth-1.973
 Klux-1.628
 Priv-1.624
 Balloon-1.609
Token again
Token ID757
Feature activation+5.04e+00

Pos logit contributions
ellar+1.948
yrinth+1.876
 Priv+1.521
 Balloon+1.508
BW+1.468
Neg logit contributions
 UCS-3.473
�士-3.382
UTF-3.368
osph-3.248
py-3.166
Token.
Token ID13
Feature activation+3.61e-01

Pos logit contributions
ellar+3.317
yrinth+3.243
 Priv+2.834
 Balloon+2.778
 Doodle+2.759
Neg logit contributions
�士-3.777
 UCS-3.761
UTF-3.669
osph-3.536
py-3.372
Token Here
Token ID3423
Feature activation-3.66e+00

Pos logit contributions
ellar+0.243
yrinth+0.238
 Priv+0.205
 Balloon+0.200
 Doodle+0.197
Neg logit contributions
 UCS-0.278
�士-0.271
UTF-0.270
osph-0.258
py-0.251
Token's
Token ID338
Feature activation-2.09e+00

Pos logit contributions
 UCS+2.684
UTF+2.557
�士+2.549
osph+2.438
py+2.410
Neg logit contributions
ellar-2.632
yrinth-2.599
 Priv-2.177
 Balloon-2.156
 Klux-2.154
Token how
Token ID703
Feature activation-1.30e+00

Pos logit contributions
 UCS+1.580
UTF+1.512
�士+1.507
osph+1.440
py+1.421
Neg logit contributions
ellar-1.464
yrinth-1.442
 Priv-1.205
 Balloon-1.190
 Klux-1.187
Token Wales
Token ID11769
Feature activation+3.06e+00

Pos logit contributions
 UCS+0.980
UTF+0.943
�士+0.941
osph+0.897
py+0.883
Neg logit contributions
ellar-0.911
yrinth-0.896
 Priv-0.755
 Balloon-0.744
 Klux-0.740
Token lined
Token ID16566
Feature activation-2.00e-01

Pos logit contributions
ellar+2.096
yrinth+2.049
 Priv+1.751
 Balloon+1.732
 drag+1.732
Neg logit contributions
 UCS-2.303
�士-2.248
UTF-2.245
osph-2.113
py-2.044
Token up
Token ID510
Feature activation+4.09e+00

Pos logit contributions
 UCS+0.162
�士+0.157
UTF+0.157
osph+0.150
py+0.147
Neg logit contributions
ellar-0.129
yrinth-0.126
 Priv-0.105
 Balloon-0.103
 Klux-0.103
Token for
Token ID329
Feature activation+2.80e-01

Pos logit contributions
ellar+2.644
yrinth+2.567
 Priv+2.259
 drag+2.202
 Balloon+2.194
Neg logit contributions
�士-3.198
 UCS-3.112
UTF-3.088
osph-2.971
pu-2.816
Token loans
Token ID10021
Feature activation-1.21e+00

Pos logit contributions
ellar+3.044
yrinth+2.984
 Priv+2.738
 Balloon+2.620
 drag+2.554
Neg logit contributions
�士-2.986
 UCS-2.983
UTF-2.917
osph-2.732
py-2.671
Token are
Token ID389
Feature activation+5.20e+00

Pos logit contributions
 UCS+0.842
UTF+0.803
�士+0.797
osph+0.764
py+0.752
Neg logit contributions
ellar-0.916
yrinth-0.903
 Priv-0.766
 Balloon-0.756
 Klux-0.756
Token Vi
Token ID16049
Feature activation+3.34e+00

Pos logit contributions
ellar+3.393
yrinth+3.348
 Priv+3.052
 Balloon+2.875
 drag+2.817
Neg logit contributions
�士-3.938
 UCS-3.898
UTF-3.888
osph-3.665
py-3.583
Tokenaches
Token ID3694
Feature activation+3.44e+00

Pos logit contributions
ellar+2.133
yrinth+2.083
 Priv+1.743
 Klux+1.707
 Balloon+1.698
Neg logit contributions
 UCS-2.708
�士-2.648
UTF-2.577
osph-2.426
py-2.402
Tokenlav
Token ID18809
Feature activation+5.06e+00

Pos logit contributions
ellar+1.065
yrinth+1.005
 Priv+0.683
 Balloon+0.598
 Klux+0.594
Neg logit contributions
 UCS-3.914
�士-3.840
UTF-3.822
osph-3.681
py-3.590
Token Pl
Token ID1345
Feature activation-1.16e+01

Pos logit contributions
ellar+3.388
yrinth+3.317
 Priv+2.970
 Balloon+2.833
 drag+2.734
Neg logit contributions
 UCS-3.784
�士-3.746
UTF-3.707
osph-3.437
py-3.354
Tokenak
Token ID461
Feature activation-5.97e-01

Pos logit contributions
 UCS+8.544
osph+8.504
UTF+8.321
py+8.286
pu+7.979
Neg logit contributions
yrinth-6.980
ellar-6.952
 Doodle-5.880
 Balloon-5.864
 Priv-5.759
Tokenas
Token ID292
Feature activation+1.19e+00

Pos logit contributions
 UCS+0.454
�士+0.439
UTF+0.436
osph+0.408
py+0.402
Neg logit contributions
ellar-0.418
yrinth-0.414
 Priv-0.347
 Balloon-0.340
 Klux-0.339
Tokenov
Token ID709
Feature activation+1.04e+00

Pos logit contributions
ellar+0.792
yrinth+0.775
 Priv+0.655
 Balloon+0.637
 Klux+0.632
Neg logit contributions
 UCS-0.940
�士-0.913
UTF-0.905
osph-0.851
py-0.833
Token,
Token ID11
Feature activation+5.12e+00

Pos logit contributions
ellar+0.699
yrinth+0.680
 Priv+0.582
 Balloon+0.567
 Klux+0.554
Neg logit contributions
 UCS-0.820
�士-0.791
UTF-0.790
osph-0.743
py-0.731
Token Vol
Token ID4709
Feature activation-4.13e+00

Pos logit contributions
ellar+3.195
yrinth+3.169
 Priv+2.850
 Balloon+2.676
 drag+2.640
Neg logit contributions
 UCS-3.989
�士-3.969
UTF-3.944
osph-3.696
py-3.645
Token is
Token ID318
Feature activation-5.01e+00

Pos logit contributions
 UCS+7.023
UTF+6.742
�士+6.532
osph+6.323
py+6.196
Neg logit contributions
ellar-7.470
yrinth-7.421
 Doodle-6.171
BW-6.064
 Balloon-6.029
Token now
Token ID783
Feature activation-6.56e+00

Pos logit contributions
 UCS+3.792
UTF+3.597
�士+3.585
osph+3.432
py+3.392
Neg logit contributions
ellar-3.496
yrinth-3.440
 Priv-2.805
 Klux-2.793
BW-2.789
Token the
Token ID262
Feature activation-7.88e+00

Pos logit contributions
 UCS+4.834
UTF+4.571
�士+4.564
osph+4.357
py+4.309
Neg logit contributions
ellar-4.645
yrinth-4.592
 Balloon-3.748
 Priv-3.736
BW-3.729
Token Party
Token ID3615
Feature activation-1.03e+01

Pos logit contributions
 UCS+5.397
�士+5.095
UTF+5.009
osph+4.900
py+4.789
Neg logit contributions
yrinth-5.863
ellar-5.842
BW-4.828
 Priv-4.767
----------4.765
Token of
Token ID286
Feature activation-7.95e+00

Pos logit contributions
 UCS+6.623
�士+6.357
UTF+6.293
osph+6.028
py+5.921
Neg logit contributions
yrinth-7.722
ellar-7.704
BW-6.485
 Balloon-6.436
 Doodle-6.409
Token Trump
Token ID1301
Feature activation-1.36e+01

Pos logit contributions
 UCS+5.831
UTF+5.504
�士+5.454
osph+5.217
py+5.198
Neg logit contributions
ellar-5.555
yrinth-5.495
BW-4.567
----------4.488
 Doodle-4.422
Token.
Token ID13
Feature activation-5.47e+00

Pos logit contributions
 UCS+8.155
UTF+7.567
�士+7.336
osph+7.243
py+7.155
Neg logit contributions
yrinth-10.445
ellar-10.369
 Doodle-8.572
 Klux-8.546
BW-8.538
Token
Token ID447
Feature activation-1.99e-01

Pos logit contributions
 UCS+4.011
UTF+3.803
�士+3.736
py+3.574
osph+3.552
Neg logit contributions
ellar-3.998
yrinth-3.948
 Klux-3.254
 Balloon-3.197
 Priv-3.182
Token
Token ID251
Feature activation-5.83e+00

Pos logit contributions
 UCS+0.169
UTF+0.162
�士+0.159
osph+0.155
py+0.153
Neg logit contributions
ellar-0.120
yrinth-0.119
 Priv-0.097
 Balloon-0.095
 Klux-0.094
Token
Token ID198
Feature activation-3.32e+00

Pos logit contributions
 UCS+4.258
UTF+4.042
�士+3.962
py+3.791
osph+3.787
Neg logit contributions
ellar-4.247
yrinth-4.187
 Klux-3.441
 Balloon-3.412
 Doodle-3.400
Token
Token ID198
Feature activation-1.65e-01

Pos logit contributions
 UCS+2.300
UTF+2.196
py+2.081
osph+2.015
pu+2.000
Neg logit contributions
yrinth-2.619
ellar-2.545
 Klux-2.146
 Balloon-2.121
 Doodle-2.103
Token again
Token ID757
Feature activation-3.58e+00

Pos logit contributions
ellar+1.338
yrinth+1.274
 Priv+0.992
 Balloon+0.946
---------+0.941
Neg logit contributions
 UCS-2.973
�士-2.956
UTF-2.900
osph-2.788
py-2.748
Token that
Token ID326
Feature activation-3.55e+00

Pos logit contributions
 UCS+2.374
UTF+2.228
py+2.121
osph+2.113
�士+2.087
Neg logit contributions
yrinth-2.835
ellar-2.827
 Klux-2.388
 Priv-2.367
 Balloon-2.364
Token the
Token ID262
Feature activation-4.88e+00

Pos logit contributions
 UCS+2.572
UTF+2.428
py+2.291
�士+2.284
osph+2.284
Neg logit contributions
yrinth-2.627
ellar-2.590
 Klux-2.156
 Priv-2.140
 Balloon-2.132
Token old
Token ID1468
Feature activation-8.69e+00

Pos logit contributions
 UCS+3.541
UTF+3.406
�士+3.277
osph+3.176
py+3.171
Neg logit contributions
ellar-3.560
yrinth-3.548
 Priv-2.939
 Balloon-2.939
 Klux-2.916
Token address
Token ID2209
Feature activation-9.83e+00

Pos logit contributions
 UCS+6.022
UTF+5.738
py+5.447
osph+5.432
pu+5.268
Neg logit contributions
yrinth-6.459
ellar-6.341
BW-5.271
 Klux-5.268
 Balloon-5.231
Token https
Token ID3740
Feature activation-1.21e+01

Pos logit contributions
 UCS+6.569
UTF+6.247
�士+6.052
py+5.845
osph+5.733
Neg logit contributions
ellar-7.440
yrinth-7.312
 Klux-6.249
----------6.109
 Doodle-6.108
Token://
Token ID1378
Feature activation-1.15e+01

Pos logit contributions
 UCS+6.251
UTF+6.165
py+5.577
pu+5.474
osph+5.406
Neg logit contributions
yrinth-10.621
ellar-10.023
 Balloon-8.956
 Doodle-8.775
 Klux-8.769
Token.
Token ID764
Feature activation-6.42e+00

Pos logit contributions
 UCS+7.376
UTF+7.111
�士+6.831
py+6.614
osph+6.520
Neg logit contributions
yrinth-8.748
ellar-8.727
 Klux-7.346
 Balloon-7.317
BW-7.249
Tokennice
Token ID44460
Feature activation-1.95e+00

Pos logit contributions
 UCS+3.294
UTF+3.150
�士+3.031
py+2.978
osph+2.885
Neg logit contributions
ellar-6.018
yrinth-5.926
 Priv-5.214
 Balloon-5.173
 Klux-5.126
Tokenhash
Token ID17831
Feature activation+3.19e+00

Pos logit contributions
 UCS+1.400
UTF+1.357
�士+1.304
osph+1.295
py+1.290
Neg logit contributions
ellar-1.426
yrinth-1.416
 Priv-1.201
 Balloon-1.191
 Doodle-1.168
Token.
Token ID13
Feature activation+1.37e+00

Pos logit contributions
ellar+2.200
yrinth+2.110
 Priv+1.855
 Balloon+1.801
---------+1.794
Neg logit contributions
�士-2.421
 UCS-2.388
UTF-2.298
osph-2.215
py-2.132
Token days
Token ID1528
Feature activation+2.72e+00

Pos logit contributions
 UCS+0.026
�士+0.026
UTF+0.025
osph+0.024
py+0.024
Neg logit contributions
ellar-0.022
yrinth-0.021
 Priv-0.018
 Balloon-0.018
 Klux-0.017
Token,
Token ID11
Feature activation-2.00e+00

Pos logit contributions
ellar+1.825
yrinth+1.773
 Priv+1.516
 Balloon+1.501
 drag+1.484
Neg logit contributions
 UCS-2.092
�士-2.065
UTF-2.022
osph-1.929
py-1.872
Token implementing
Token ID15427
Feature activation-4.91e+00

Pos logit contributions
 UCS+1.473
UTF+1.408
�士+1.394
osph+1.335
py+1.321
Neg logit contributions
ellar-1.450
yrinth-1.427
 Priv-1.200
 Klux-1.186
 Balloon-1.185
Token methods
Token ID5050
Feature activation-3.98e+00

Pos logit contributions
 UCS+3.697
UTF+3.506
�士+3.448
osph+3.309
py+3.305
Neg logit contributions
ellar-3.442
yrinth-3.376
 Klux-2.807
 Priv-2.782
 Balloon-2.771
Token add
Token ID751
Feature activation-8.65e+00

Pos logit contributions
 UCS+2.835
UTF+2.704
�士+2.656
osph+2.563
py+2.560
Neg logit contributions
ellar-2.933
yrinth-2.905
 Klux-2.435
 Priv-2.435
 Balloon-2.424
TokenPoints
Token ID40710
Feature activation-1.19e+01

Pos logit contributions
 UCS+6.546
UTF+6.377
�士+6.127
py+6.082
osph+5.985
Neg logit contributions
ellar-5.691
yrinth-5.645
 Balloon-4.628
 Klux-4.590
 Priv-4.511
Token(
Token ID7
Feature activation-1.31e+00

Pos logit contributions
 UCS+7.780
UTF+7.671
py+7.365
�士+7.268
osph+7.026
Neg logit contributions
ellar-8.636
yrinth-8.572
 Klux-7.205
 Doodle-7.022
 Balloon-7.020
Tokenuser
Token ID7220
Feature activation-1.41e-01

Pos logit contributions
 UCS+1.035
�士+0.995
UTF+0.994
osph+0.950
py+0.934
Neg logit contributions
ellar-0.873
yrinth-0.859
 Priv-0.716
 Balloon-0.705
 Klux-0.700
Token,
Token ID11
Feature activation-1.98e+00

Pos logit contributions
 UCS+0.108
�士+0.104
UTF+0.103
osph+0.099
py+0.097
Neg logit contributions
ellar-0.096
yrinth-0.095
 Priv-0.080
 Balloon-0.079
 Klux-0.078
Token points
Token ID2173
Feature activation-5.20e+00

Pos logit contributions
 UCS+1.502
UTF+1.443
�士+1.439
osph+1.373
py+1.353
Neg logit contributions
ellar-1.385
yrinth-1.363
 Priv-1.145
 Balloon-1.129
 Klux-1.124
Token)
Token ID8
Feature activation-7.27e+00

Pos logit contributions
 UCS+3.894
UTF+3.782
�士+3.693
py+3.577
osph+3.558
Neg logit contributions
ellar-3.598
yrinth-3.571
 Priv-2.966
 Klux-2.941
 Doodle-2.910
Token},
Token ID5512
Feature activation-7.99e+00

Pos logit contributions
 UCS+2.801
UTF+2.662
�士+2.637
osph+2.501
py+2.481
Neg logit contributions
ellar-3.398
yrinth-3.359
 Priv-2.894
 Klux-2.845
 Balloon-2.841
Token {{
Token ID22935
Feature activation-6.74e+00

Pos logit contributions
 UCS+5.127
UTF+4.813
�士+4.652
py+4.474
osph+4.451
Neg logit contributions
ellar-6.336
yrinth-6.256
 Priv-5.334
 Klux-5.321
BW-5.209
Token1
Token ID16
Feature activation-1.94e+00

Pos logit contributions
 UCS+4.433
UTF+4.330
�士+4.155
py+4.060
osph+4.013
Neg logit contributions
ellar-5.204
yrinth-5.140
 Priv-4.430
 Balloon-4.332
 Doodle-4.308
Token,
Token ID11
Feature activation-7.17e+00

Pos logit contributions
 UCS+1.451
UTF+1.392
�士+1.378
osph+1.321
py+1.306
Neg logit contributions
ellar-1.376
yrinth-1.358
 Priv-1.143
 Balloon-1.123
 Klux-1.123
Token 6
Token ID718
Feature activation-3.33e+00

Pos logit contributions
 UCS+4.621
UTF+4.365
�士+4.175
py+4.022
osph+3.992
Neg logit contributions
ellar-5.754
yrinth-5.647
 Klux-4.776
 Priv-4.765
 Doodle-4.665
Token},
Token ID5512
Feature activation-1.26e+01

Pos logit contributions
 UCS+1.868
UTF+1.768
�士+1.758
osph+1.646
py+1.621
Neg logit contributions
ellar-2.975
yrinth-2.940
 Priv-2.577
 Balloon-2.544
 Klux-2.539
Token {
Token ID1391
Feature activation-1.02e+01

Pos logit contributions
 UCS+7.679
UTF+7.028
�士+6.941
py+6.641
osph+6.473
Neg logit contributions
ellar-9.891
yrinth-9.630
 Klux-8.362
 Priv-8.303
BW-8.164
Token1
Token ID16
Feature activation-2.01e+00

Pos logit contributions
 UCS+6.504
UTF+6.355
�士+6.086
py+5.953
osph+5.821
Neg logit contributions
ellar-7.749
yrinth-7.713
 Priv-6.656
 Klux-6.506
 Balloon-6.469
Token,
Token ID11
Feature activation-8.46e+00

Pos logit contributions
 UCS+1.426
UTF+1.365
py+1.289
�士+1.280
osph+1.277
Neg logit contributions
yrinth-1.506
ellar-1.493
 Priv-1.250
 Klux-1.243
 Balloon-1.228
Token 7
Token ID767
Feature activation-1.15e+00

Pos logit contributions
 UCS+4.941
UTF+4.593
�士+4.364
py+4.241
osph+4.166
Neg logit contributions
ellar-7.247
yrinth-7.137
 Klux-6.121
 Priv-6.069
BW-5.954
Token},
Token ID5512
Feature activation-9.30e+00

Pos logit contributions
 UCS+0.660
�士+0.628
UTF+0.628
osph+0.590
py+0.573
Neg logit contributions
ellar-1.017
yrinth-1.001
 Priv-0.874
 Balloon-0.868
 Klux-0.861