Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of conversational expressions and colloquial language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ་་
    -0.97
     ―――――
    -0.94
    IntoConstraints
    -0.91
    NUMX
    -0.91
    tvguidetime
    -0.88
     ſind
    -0.88
     useAppContext
    -0.88
    .³
    -0.86
     createContext
    -0.85
     ─
    -0.84
    POSITIVE LOGITS
     
    0.88
     I
    0.70
     m
    0.61
     nice
    0.59
    ..
    0.58
     i
    0.58
     you
    0.55
     .
    0.54
     We
    0.54
     in
    0.53
    Act Density 0.197%

    No Known Activations