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

    Neuronpedia

    INDEX
    Explanations

    references to societal stability and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     priorit
    -0.16
    rega
    -0.15
    andest
    -0.15
    afort
    -0.14
    иÑħ
    -0.14
    zman
    -0.13
    anca
    -0.13
    طر
    -0.13
     Sup
    -0.13
    itaire
    -0.13
    POSITIVE LOGITS
    ovat
    0.13
    unsupported
    0.13
     Broadcasting
    0.13
     dominating
    0.13
    leh
    0.13
    ols
    0.13
     outpost
    0.12
     mpfr
    0.12
     semiclass
    0.12
    aron
    0.12
    Act Density 0.023%

    No Known Activations