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

    Neuronpedia

    INDEX
    Explanations

    references to uncertainty and ambiguity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essler
    -0.17
    landa
    -0.17
    ernals
    -0.15
    ères
    -0.14
    atsby
    -0.14
     Barg
    -0.14
    away
    -0.14
    arding
    -0.14
     Wolff
    -0.14
    vard
    -0.14
    POSITIVE LOGITS
    apis
    0.17
    iT
    0.15
    ATTLE
    0.15
    gettext
    0.15
    enor
    0.14
    prot
    0.14
    ichel
    0.14
    mploy
    0.14
    ertainty
    0.14
     reb
    0.14
    Act Density 0.008%

    No Known Activations