INDEX
Explanations
expressions of frustration or dissatisfaction related to appearance or self-image.
The neuron fires on casual, first-person discourse markers—especially the phrase “let’s face it” (and similar “let’s…” preambles) that signal a speaker’s aside or opinion.
New Auto-Interp
Negative Logits
011
-0.07
Machine
-0.07
ß
-0.07
Nearly
-0.06
ený
-0.06
KER
-0.06
off
-0.06
nj
-0.06
HQ
-0.06
เคล
-0.06
POSITIVE LOGITS
bottleneck
0.07
}.{0.07
imize
0.07
Satoshi
0.07
Cowboy
0.07
나는
0.06
Portály
0.06
stereotype
0.06
imageUrl
0.06
overlay
0.06
Activations Density 0.007%