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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating usage or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding "to"

    np_acts-logits-general · gemini-2.0-flash

    infinitive verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     using
    -0.82
    Use
    -0.77
    using
    -0.73
     Utilizing
    -0.72
    use
    -0.72
     Use
    -0.71
     Verwendung
    -0.70
    Using
    -0.70
     menggunakan
    -0.70
     USING
    -0.69
    POSITIVE LOGITS
    ImageContext
    0.64
     estekak
    0.62
    drawSprites
    0.60
    󠁣
    0.59
    InSection
    0.58
    ensively
    0.56
    Personendaten
    0.55
    '}>
    0.55
    ในการ
    0.54
     contextes
    0.54
    Act Density 0.414%

    No Known Activations