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

    Neuronpedia

    INDEX
    Explanations

    patterns of punctuation and special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ，
    -0.85
    ‘
    -0.82
    、
    -0.81
    。
    -0.72
    ↵
    -0.70
    s
    -0.70
    ！
    -0.69
    2
    -0.69
    ,
    -0.67
    er
    -0.66
    POSITIVE LOGITS
     дописавши
    0.95
     *
    0.94
     https
    0.88
     Мексичка
    0.87
     виправивши
    0.85
     http
    0.83
     Pingback
    0.82
     שוליים
    0.81
     ※
    0.79
     ‍
    0.78
    Act Density 0.310%

    No Known Activations