INDEX
Explanations
the name "Bob" appearing in the text
mentions of the name "Bob."
New Auto-Interp
Negative Logits
vetting
-0.63
plural
-0.56
drift
-0.55
Reloaded
-0.55
TY
-0.54
Gauntlet
-0.54
regard
-0.54
POLIT
-0.54
duty
-0.53
ylum
-0.53
POSITIVE LOGITS
bie
1.31
bi
1.10
cats
1.09
cat
1.09
bies
1.07
bing
1.04
Dylan
1.01
bers
1.01
bles
1.00
ble
0.99
Activations Density 0.017%