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

    Neuronpedia

    INDEX
    Explanations

    instances of significant numbers or measurements in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -1.13
    хьтан
    -0.79
     незавершена
    -0.75
     ModelExpression
    -0.72
     BrowserModule
    -0.70
    ectoria
    -0.68
     հղումներ
    -0.67
     calldata
    -0.65
     الرياضيه
    -0.65
     Munch
    -0.65
    POSITIVE LOGITS
    </blockquote>
    0.87
    endphp
    0.84
    ↵↵↵↵↵↵↵
    0.77
    ↵↵↵↵↵
    0.75
    ↵↵↵↵
    0.70
    <eos>
    0.70
    ↵↵↵↵↵↵↵↵↵
    0.67
    ↵↵↵↵↵↵
    0.66
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.65
    ↵↵↵↵↵↵↵↵
    0.63
    Act Density 0.008%

    No Known Activations