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

    Neuronpedia

    INDEX
    Explanations

    references to uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STANCE
    -0.16
    itu
    -0.16
    ëĮĢë¡ľ
    -0.16
    actories
    -0.15
    ULA
    -0.15
    뢰
    -0.15
    omat
    -0.15
    igest
    -0.15
    acic
    -0.15
    ahan
    -0.14
    POSITIVE LOGITS
    ertainty
    0.30
    anny
    0.29
    outh
    0.27
    ertain
    0.22
    ount
    0.20
    ork
    0.20
    ERT
    0.20
    irc
    0.20
    ategorized
    0.19
    ou
    0.18
    Act Density 0.010%

    No Known Activations