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

    Neuronpedia

    INDEX
    Explanations

    terms related to the effect or influence on various subjects or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    'gc
    -0.18
    ÃĹ↵↵
    -0.16
    aten
    -0.16
    esen
    -0.16
    γκα
    -0.15
    ruba
    -0.15
    ukan
    -0.14
    wdx
    -0.14
    esses
    -0.14
    ARIANT
    -0.14
    POSITIVE LOGITS
    etto
    0.17
     sino
    0.17
    tright
    0.16
    nom
    0.15
    heet
    0.15
    ss
    0.15
    ICI
    0.14
    olla
    0.14
    QT
    0.14
    cff
    0.14
    Act Density 0.021%

    No Known Activations