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

    Neuronpedia

    INDEX
    Explanations

    specific formatting characters and symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.95
     للاسماء
    -0.88
     snippetHide
    -0.85
    ArrowToggle
    -0.85
     ―――――
    -0.83
     HasFactory
    -0.82
    OGND
    -0.82
    WriteBarrier
    -0.79
    AndEndTag
    -0.78
    Дереккөздер
    -0.77
    POSITIVE LOGITS
    </strong>
    0.69
    </em>
    0.56
    </h2>
    0.56
    </h4>
    0.52
    ...
    0.51
    家伙
    0.50
    ↵
    0.50
     
    0.48
     complainant
    0.48
    _
    0.47
    Act Density 0.077%

    No Known Activations