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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to API and document management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     he
    -0.58
     just
    -0.57
    </b>
    -0.55
     even
    -0.53
    ","
    -0.50
     .
    -0.50
     ",
    -0.49
     of
    -0.49
    <eos>
    -0.49
    </u>
    -0.49
    POSITIVE LOGITS
    _
    1.56
    \_
    0.99
    ſelf
    0.89
     متعلقه
    0.88
    IsMutable
    0.87
     שוליים
    0.87
    IntoConstraints
    0.86
     ་་
    0.83
    neſs
    0.82
     فريبيس
    0.82
    Act Density 1.276%

    No Known Activations