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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numerical codes or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uss
    -0.16
    assin
    -0.15
    inqu
    -0.15
    enderit
    -0.15
    usch
    -0.15
    landscape
    -0.14
    agher
    -0.14
    okud
    -0.14
     commodities
    -0.14
    achable
    -0.14
    POSITIVE LOGITS
    s
    0.22
    burg
    0.16
     Perc
    0.15
    iday
    0.15
    evin
    0.15
    803
    0.14
     fined
    0.14
    racÃŃ
    0.14
    e
    0.14
     пÑĢи
    0.14
    Act Density 0.084%

    No Known Activations