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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igon
    -0.18
    cete
    -0.18
    erset
    -0.15
    adan
    -0.15
    enderit
    -0.14
    istik
    -0.14
    /***/
    -0.14
    elease
    -0.14
    pson
    -0.14
    dsn
    -0.14
    POSITIVE LOGITS
    rens
    0.15
    ãĥ³ãĥķ
    0.14
    nob
    0.14
    =""/>↵
    0.14
    ern
    0.14
    ess
    0.14
    ween
    0.14
    room
    0.13
    Leaf
    0.13
    acha
    0.13
    Act Density 0.011%

    No Known Activations