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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote processes or transitions through time or stages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ao
    -0.16
     laut
    -0.15
    deaux
    -0.15
    TT
    -0.15
    tt
    -0.14
    oa
    -0.14
    kus
    -0.14
    ivist
    -0.14
    lasses
    -0.14
    AO
    -0.14
    POSITIVE LOGITS
    CLUDED
    0.17
    orget
    0.16
    anno
    0.15
    EDA
    0.15
    venta
    0.15
    letcher
    0.15
    perator
    0.14
    assage
    0.14
    CLUDING
    0.14
    imson
    0.14
    Act Density 0.136%

    No Known Activations