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

    Neuronpedia

    INDEX
    Explanations

    placeholders in the text structure, indicating sections or content changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -1.04
     שוליים
    -0.84
    endpush
    -0.82
    +:+
    -0.80
    principalTable
    -0.80
     Wikimédia
    -0.77
     NSCoder
    -0.76
    olesale
    -0.75
    LikeLike
    -0.75
    Rohy
    -0.74
    POSITIVE LOGITS
    ↵↵
    0.76
     
    0.48
    .
    0.47
     The
    0.47
    ↵
    0.46
     the
    0.46
    ↵↵↵
    0.45
     ferner
    0.45
    etc
    0.45
     precum
    0.42
    Act Density 0.082%

    No Known Activations