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

    Neuronpedia

    INDEX
    Explanations

    references to letters and correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gn
    -0.15
    emaker
    -0.15
    sym
    -0.15
    ot
    -0.14
    orsk
    -0.14
    ément
    -0.14
    esser
    -0.14
    soc
    -0.14
    erala
    -0.14
     collapsed
    -0.13
    POSITIVE LOGITS
    lies
    0.19
    ystone
    0.16
    lie
    0.16
    çĬ¶
    0.15
    istique
    0.15
    reuse
    0.15
    ILLISECONDS
    0.15
    aight
    0.14
    rente
    0.14
    ural
    0.14
    Act Density 0.037%

    No Known Activations