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

    Neuronpedia

    INDEX
    Explanations

    certain quantifiers and descriptors emphasizing quantity, significance, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zi
    -0.20
     Gür
    -0.15
     Affero
    -0.15
    éra
    -0.14
    raq
    -0.14
    deo
    -0.14
    æ¡£
    -0.14
    uje
    -0.14
     Kre
    -0.13
    enge
    -0.13
    POSITIVE LOGITS
    cken
    0.16
    ocab
    0.14
    ìĤ´
    0.13
    UCH
    0.13
    å¯Ĵ
    0.13
    chor
    0.13
    LETED
    0.13
    Gateway
    0.13
     canal
    0.13
    çĿĽ
    0.13
    Act Density 0.486%

    No Known Activations