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

    Neuronpedia

    INDEX
    Explanations

    words with specific phonetic qualities or character patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asurement
    -0.15
     Garland
    -0.15
    enders
    -0.15
    jom
    -0.14
    andas
    -0.14
    สà¸ķ
    -0.14
     Hud
    -0.14
    anche
    -0.13
    <(),
    -0.13
     Gand
    -0.13
    POSITIVE LOGITS
    ICA
    0.16
    amon
    0.16
    affer
    0.15
     Fol
    0.15
    util
    0.15
    sz
    0.14
    path
    0.14
    erton
    0.14
    acus
    0.14
    rok
    0.14
    Act Density 0.068%

    No Known Activations