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

    Neuronpedia

    INDEX
    Explanations

    disjoint conversational elements or punctuation marks that break up the flow of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.60
    postmedia
    -0.59
     quitté
    -0.54
     înainte
    -0.51
     ويكيپيديا
    -0.50
     rile
    -0.50
    quilla
    -0.49
     kepercayaan
    -0.48
    ってお
    -0.47
     mandatario
    -0.47
    POSITIVE LOGITS
     which
    0.85
    SourceChecksum
    0.83
     reminiscent
    0.82
    which
    0.77
     capable
    0.77
     designed
    0.75
     whose
    0.73
     مرئيه
    0.73
    whose
    0.70
     intended
    0.69
    Act Density 0.429%

    No Known Activations