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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -1.49
    ↵
    -0.83
    ↵↵↵
    -0.83
    </h3>
    -0.79
     Wikimedijinoj
    -0.68
    }>
    -0.65
    </h4>
    -0.65
    </blockquote>
    -0.63
    Personendaten
    -0.63
    []
    -0.63
    POSITIVE LOGITS
     كومونز
    0.64
    umenical
    0.51
    Chham
    0.48
     муніципалі
    0.48
    geslacht
    0.46
    peteer
    0.46
    GraphicsUnit
    0.44
    robi
    0.44
    /^
    0.43
    пература
    0.43
    Act Density 0.450%

    No Known Activations