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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "↵
    -0.45
    {↵
    -0.35
    ../
    -0.35
    '↵
    -0.34
    )↵
    -0.32
    ")↵
    -0.28
    }↵
    -0.27
    >↵
    -0.25
    ')↵
    -0.24
    ↵
    -0.22
    POSITIVE LOGITS
    _IW
    0.17
    eland
    0.15
    ilo
    0.14
    orsch
    0.14
    REA
    0.13
    amos
    0.13
     OE
    0.13
    okie
    0.13
    cie
    0.13
    raman
    0.13
    Act Density 0.086%

    No Known Activations