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

    Neuronpedia

    INDEX
    Explanations

    references to aspects or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sz
    -0.19
    dy
    -0.18
    DonaldTrump
    -0.15
    ãģ¾ãģŁ
    -0.15
    maker
    -0.14
    hammer
    -0.14
    night
    -0.14
    ses
    -0.14
    rup
    -0.14
    avic
    -0.14
    POSITIVE LOGITS
    ual
    0.19
    pects
    0.17
    aspect
    0.16
    ureka
    0.15
     aspect
    0.15
    ually
    0.15
    urnal
    0.15
     ÐĴики
    0.15
    ihad
    0.15
    icular
    0.15
    Act Density 0.015%

    No Known Activations