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

    Neuronpedia

    INDEX
    Explanations

    slashes or dividers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lijk
    -0.17
    alog
    -0.17
    ubat
    -0.16
    lag
    -0.16
    nox
    -0.15
    cky
    -0.14
    leta
    -0.14
    xiety
    -0.14
     bet
    -0.14
    ized
    -0.14
    POSITIVE LOGITS
    Ë
    0.18
    SWG
    0.16
     ydk
    0.15
    νη
    0.15
    gle
    0.14
    ìĬµ
    0.14
    buz
    0.14
     Sentinel
    0.14
    iddy
    0.14
    453
    0.13
    Act Density 0.022%

    No Known Activations