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

    Neuronpedia

    INDEX
    Explanations

    elements related to non-English characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uld
    -0.17
    pp
    -0.17
    onn
    -0.17
    wed
    -0.17
    akit
    -0.16
    ad
    -0.15
    wal
    -0.15
     wed
    -0.15
    w
    -0.15
    pth
    -0.15
    POSITIVE LOGITS
    á»ķi
    0.17
    ahn
    0.17
    @nate
    0.15
    uci
    0.14
    unca
    0.14
    íħĶ
    0.14
    Ñĥг
    0.14
    rine
    0.14
    uke
    0.13
    argins
    0.13
    Act Density 0.124%

    No Known Activations