INDEX
Explanations
mentions of the name "Colin" followed by another word
instances of the name "Colin" in various contexts
New Auto-Interp
Negative Logits
cffff
-0.78
llan
-0.76
roxy
-0.69
linger
-0.69
wered
-0.69
mith
-0.69
stood
-0.68
iller
-0.67
visor
-0.64
nomine
-0.64
POSITIVE LOGITS
Kaepernick
1.09
ossus
0.92
ãĤ¡
0.90
onel
0.89
urrent
0.87
orsche
0.79
our
0.79
Powell
0.78
oqu
0.78
bert
0.77
Activations Density 0.054%