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

    Neuronpedia

    INDEX
    Explanations

    colons or other punctuation marks at the beginning of lines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ¦ľ
    -0.16
    atsu
    -0.15
    edly
    -0.14
    209
    -0.14
    spot
    -0.14
    .uni
    -0.13
    hausen
    -0.13
    keit
    -0.13
    Ñıж
    -0.13
    cih
    -0.13
    POSITIVE LOGITS
    nodoc
    0.17
    bos
    0.16
    olec
    0.15
    iban
    0.15
    ade
    0.15
    istrovstvÃŃ
    0.15
    oyer
    0.14
    emand
    0.14
     PIXEL
    0.13
    argout
    0.13
    Act Density 0.075%

    No Known Activations