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

    Neuronpedia

    INDEX
    Explanations

    header tags or labels commonly associated with content categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampp
    -0.17
    íķŃ
    -0.14
    èĻļ
    -0.14
    è§Ĵ
    -0.14
    ARIANT
    -0.14
    icity
    -0.13
    Bezier
    -0.13
    zac
    -0.13
    stery
    -0.13
     Nimbus
    -0.13
    POSITIVE LOGITS
    immel
    0.17
     Zw
    0.16
    idd
    0.15
     volta
    0.15
    achi
    0.14
    485
    0.14
    qrt
    0.14
    worth
    0.14
    appl
    0.13
    ella
    0.13
    Act Density 0.015%

    No Known Activations