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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sections or segments in text, as well as special indicators used in formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    มาณ
    -0.83
    bleau
    -0.82
    expandindo
    -0.82
     Avent
    -0.80
    -0.78
    -0.78
    '},
    -0.78
    مصادر
    -0.76
     tartalomajánló
    -0.76
    osphere
    -0.75
    POSITIVE LOGITS
     Kershaw
    0.83
     Arteta
    0.79
     transcripts
    0.72
     Rivas
    0.72
     Tad
    0.70
    alanta
    0.70
     Scully
    0.69
    Tad
    0.69
    честве
    0.69
    יי
    0.68
    Act Density 0.334%

    No Known Activations