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

    Neuronpedia

    INDEX
    Explanations

    negative qualifiers and expressions of capability or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ambda
    -0.16
    opot
    -0.16
     gear
    -0.15
    gear
    -0.15
    uo
    -0.15
    arel
    -0.14
    icz
    -0.14
    hue
    -0.14
    mmo
    -0.14
    owell
    -0.14
    POSITIVE LOGITS
    иденÑĤ
    0.16
     Stevenson
    0.15
    argin
    0.15
    vat
    0.15
    aky
    0.15
    CFG
    0.14
    yal
    0.14
    Variant
    0.14
    ya
    0.14
     ç§ĭ
    0.14
    Act Density 0.358%

    No Known Activations