INDEX
Explanations
mentions of a specific person named Kent
mentions of the name "Kent."
New Auto-Interp
Negative Logits
xual
-0.87
behavi
-0.74
Versions
-0.74
Ø©
-0.73
CTR
-0.71
llah
-0.69
sparing
-0.67
primates
-0.67
FACE
-0.66
SHIP
-0.66
POSITIVE LOGITS
ucky
1.43
uck
1.07
rell
0.99
etsu
0.91
aro
0.90
ersen
0.89
rust
0.88
ronics
0.87
uba
0.87
anooga
0.84
Activations Density 0.021%