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

    Neuronpedia

    INDEX
    Explanations

    authorship indicators or references to authors in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apore
    -0.15
    mlin
    -0.15
    ander
    -0.14
    refixer
    -0.14
    каÑģ
    -0.14
    endar
    -0.14
    abyrin
    -0.14
    .microsoft
    -0.14
    andr
    -0.14
    spoken
    -0.13
    POSITIVE LOGITS
    onium
    0.15
    edd
    0.15
    burgh
    0.15
    --,
    0.14
    _FMT
    0.14
    edio
    0.14
    ÑĪиб
    0.14
    PARSE
    0.14
    .Fat
    0.14
    SizeMode
    0.14
    Act Density 0.004%

    No Known Activations