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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eah
    -0.19
    e
    -0.18
    eo
    -0.15
    ej
    -0.14
    ections
    -0.14
    ezi
    -0.14
    ecek
    -0.14
    elem
    -0.14
    edly
    -0.14
    Č
    -0.14
    POSITIVE LOGITS
    ëĭ¤ëĬĶ
    0.16
    haps
    0.16
    ized
    0.16
    loor
    0.15
    bies
    0.14
    ious
    0.14
    üst
    0.14
    ÑģÑı
    0.14
    edBy
    0.13
    ous
    0.13
    Act Density 0.287%

    No Known Activations