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

    Neuronpedia

    INDEX
    Explanations

    strong descriptive adjectives

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that express intensity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idious
    -0.69
    FUL
    -0.66
     Fla
    -0.63
     Tanz
    -0.61
     objectively
    -0.60
    uitous
    -0.59
    volent
    -0.58
    letal
    -0.57
     legitimate
    -0.57
    _>
    -0.56
    POSITIVE LOGITS
    ties
    1.17
    ities
    1.15
    ness
    1.09
    nesses
    1.00
    izers
    0.95
    isers
    0.95
    tions
    0.94
    izations
    0.94
    itiz
    0.93
    ancies
    0.91
    Act Density 0.372%

    No Known Activations