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

    Neuronpedia

    INDEX
    Explanations

    numerical values or identifiers in a technical or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ($("#
    -0.84
     Majefty
    -0.84
     Cuthbert
    -0.84
    tershire
    -0.84
     Cuth
    -0.81
    ($("#
    -0.80
    ArrowToggle
    -0.80
     JComboBox
    -0.78
     RSITY
    -0.76
    ؤلاء
    -0.76
    POSITIVE LOGITS
    ↵
    1.32
    ↵↵
    1.17
    ↵↵↵
    0.99
    </tr>
    0.93
    ↵↵↵↵↵
    0.87
    [toxicity=0]
    0.84
    ↵↵↵↵
    0.82
    ↵↵↵↵↵↵
    0.82
    <eos>
    0.82
    hline
    0.80
    Act Density 0.034%

    No Known Activations