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

    Neuronpedia

    INDEX
    Explanations

    punctuation patterns typically used in code or structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ici
    -0.17
     ragaz
    -0.14
    ç¥
    -0.14
    isle
    -0.13
     Dual
    -0.13
     Manus
    -0.13
    TA
    -0.13
    cou
    -0.13
    ique
    -0.13
     resp
    -0.13
    POSITIVE LOGITS
    aÄŁ
    0.16
    vla
    0.15
    å¼ı
    0.14
    zÄĻ
    0.14
    eer
    0.14
    åĭ
    0.14
    emd
    0.13
    echa
    0.13
    egis
    0.13
    uong
    0.13
    Act Density 0.259%

    No Known Activations