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

    Neuronpedia

    INDEX
    Explanations

    expressions of ability or potential

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    weder
    -0.68
    Kjelder
    -0.66
     nahilalakip
    -0.65
    :^(
    -0.61
     Audiodateien
    -0.61
    verwijspagina
    -0.61
    Примітки
    -0.58
     Normdatei
    -0.56
    TypedDataSet
    -0.56
    englanniksi
    -0.55
    POSITIVE LOGITS
    ViewFeatures
    0.64
     cappella
    0.63
     ويكيميديا
    0.60
    atigable
    0.60
    polazione
    0.60
    vitational
    0.56
    cillos
    0.56
    RefreshLayout
    0.56
    adaptiveStyles
    0.56
    __":
    0.54
    Act Density 0.039%

    No Known Activations