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

    Neuronpedia

    INDEX
    Explanations

    references to software actions or interactions, such as reading or downloading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĥĨãĤ£
    -0.16
    arme
    -0.15
    veh
    -0.15
    bred
    -0.14
    meta
    -0.14
    verbosity
    -0.14
    prog
    -0.14
    bis
    -0.14
    phas
    -0.13
     Stall
    -0.13
    POSITIVE LOGITS
     impro
    0.16
    anuts
    0.14
    ób
    0.14
     Trio
    0.14
    SCI
    0.14
    ollar
    0.14
    aoke
    0.14
    dorf
    0.14
    uko
    0.14
    otten
    0.13
    Act Density 0.107%

    No Known Activations