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

    Neuronpedia

    INDEX
    Explanations

    various punctuation marks and their associated contexts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dit
    -0.20
    ubb
    -0.15
    yonel
    -0.14
    uada
    -0.14
     док
    -0.14
    zig
    -0.14
    çu
    -0.13
    zl
    -0.13
    asje
    -0.13
    edy
    -0.13
    POSITIVE LOGITS
    s
    0.15
    enville
    0.15
    udic
    0.15
    MAND
    0.15
    _SWAP
    0.14
    aban
    0.14
    sian
    0.13
     ÐĹав
    0.13
    ity
    0.13
     коÑĤоÑĢ
    0.13
    Act Density 0.051%

    No Known Activations