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

    Neuronpedia

    INDEX
    Explanations

    references to mastery or excellence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ema
    -0.17
     aras
    -0.16
    ons
    -0.15
    emas
    -0.15
    èĤĥ
    -0.15
    noc
    -0.15
    yaw
    -0.15
    AndPassword
    -0.15
    tract
    -0.14
    ares
    -0.14
    POSITIVE LOGITS
    mind
    0.34
    pieces
    0.28
    /master
    0.26
    stroke
    0.24
    (master
    0.23
    fully
    0.22
    .Master
    0.21
    ful
    0.20
    class
    0.19
    /sl
    0.19
    Act Density 0.021%

    No Known Activations