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

    Neuronpedia

    INDEX
    Explanations

    affirmative and negative responses to questions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.68
    SharedCtor
    -0.68
    Synonymes
    -0.67
    enterOuterAlt
    -0.65
     titolo
    -0.56
     thrombosis
    -0.56
    WithIOException
    -0.55
     Sodom
    -0.55
     nakalista
    -0.54
     Castelo
    -0.54
    POSITIVE LOGITS
    ViewInit
    0.77
     going
    0.77
     getting
    0.76
     sure
    0.76
     looking
    0.75
    \"");
    0.75
     youre
    0.73
     Himo
    0.73
     trying
    0.72
     thinking
    0.70
    Act Density 0.191%

    No Known Activations