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

    Neuronpedia

    INDEX
    Explanations

    colons and related numeric expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    cabul
    -0.70
    imbawa
    -0.66
    vailability
    -0.63
     head
    -0.62
     Taw
    -0.60
    HasForeignKey
    -0.59
     ویکی‌پدیای
    -0.59
     deb
    -0.59
    matsu
    -0.59
    mies
    -0.57
    POSITIVE LOGITS
    ✨:
    1.44
    _:
    1.36
    []):
    1.36
    .:
    1.32
     $:
    1.31
    $:
    1.27
     *:
    1.27
    ®:
    1.27
    +:
    1.25
    !:
    1.24
    Act Density 1.925%

    No Known Activations