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

    Neuronpedia

    INDEX
    Explanations

    references or statements prefaced by "according to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bucks
    -0.15
    anki
    -0.15
    мен
    -0.15
    ilha
    -0.15
    ERSHEY
    -0.14
    agers
    -0.14
    oksen
    -0.14
    633
    -0.14
    stroy
    -0.14
    éĤ¦
    -0.14
    POSITIVE LOGITS
    edir
    0.16
    ly
    0.15
    eriod
    0.15
    etto
    0.15
    hy
    0.15
     Nolan
    0.14
    iec
    0.14
    vailable
    0.14
    ToProps
    0.13
     to
    0.13
    Act Density 0.023%

    No Known Activations