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

    Neuronpedia

    INDEX
    Explanations

    numerical values representing statistics or data measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ar
    -0.18
    atic
    -0.16
    ap
    -0.16
    alto
    -0.15
    oral
    -0.15
    ion
    -0.15
    fact
    -0.15
    itious
    -0.14
     regards
    -0.14
    urity
    -0.14
    POSITIVE LOGITS
    à¥įण
    0.17
    soever
    0.16
    rops
    0.16
    /false
    0.16
    sey
    0.16
    IDEOS
    0.15
    tember
    0.15
    ISIBLE
    0.14
    idian
    0.14
    tables
    0.14
    Act Density 0.266%

    No Known Activations