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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and separators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.17
    -
    -0.16
    __
    -0.14
    ÈĽ
    -0.14
    s
    -0.14
    "
    -0.14
    '
    -0.14
    /d
    -0.13
     of
    -0.13
    (
    -0.13
    POSITIVE LOGITS
     etc
    0.47
    etc
    0.41
     ÑĤоÑīо
    0.34
     ÙĪغÙĬر
    0.24
     atd
    0.24
     among
    0.23
     çŃī
    0.22
     amongst
    0.22
    among
    0.22
    ãģªãģ©
    0.21
    Act Density 0.452%

    No Known Activations