INDEX
Explanations
words related to a specific person named "Collins"
mentions of the name "Collins."
New Auto-Interp
Negative Logits
istic
-0.70
ilitation
-0.68
rous
-0.67
ifles
-0.66
fare
-0.64
gio
-0.64
rities
-0.63
iddled
-0.63
razil
-0.63
onies
-0.62
POSITIVE LOGITS
worth
1.27
hip
1.07
ively
0.94
'
0.93
ullivan
0.89
olson
0.84
terday
0.81
mount
0.81
bach
0.80
creen
0.79
Activations Density 0.029%