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

    Neuronpedia

    INDEX
    Explanations

    punctuation and citation markers in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    中学
    -0.44
    himovic
    -0.44
     tom
    -0.42
    ど
    -0.42
     pla
    -0.41
    они
    -0.40
    ന
    -0.40
    utnik
    -0.40
    าหล
    -0.40
     vPvB
    -0.40
    POSITIVE LOGITS
    Datuak
    1.18
     myſelf
    1.00
    principalTable
    0.88
     تضيفلها
    0.85
    ſelf
    0.80
    WriteTagHelper
    0.77
     صوتيه
    0.76
     purpoſe
    0.75
    SpringRunner
    0.75
    #
    0.73
    Act Density 0.088%

    No Known Activations