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

    Neuronpedia

    INDEX
    Explanations

    text formatting functions and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ustil
    -0.17
    leme
    -0.15
    .dom
    -0.14
    ilis
    -0.14
    ooky
    -0.14
    omial
    -0.14
    okoj
    -0.14
    hood
    -0.14
    izm
    -0.14
    oku
    -0.14
    POSITIVE LOGITS
    wald
    0.17
    extr
    0.17
     extr
    0.16
    ometr
    0.15
    ä½³
    0.14
     Late
    0.14
    QUI
    0.14
    ucc
    0.14
    ongan
    0.14
     Tiếng
    0.14
    Act Density 0.029%

    No Known Activations