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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical rates and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ness
    -0.18
    odd
    -0.18
    ry
    -0.16
    rn
    -0.15
    thon
    -0.15
    º
    -0.15
    oding
    -0.15
    mer
    -0.15
    ning
    -0.15
    naire
    -0.14
    POSITIVE LOGITS
    istrovstvÃŃ
    0.20
    payer
    0.19
    (rate
    0.17
    .rate
    0.17
    illo
    0.17
    ascal
    0.16
    dna
    0.16
    ÏħÏĦÏĮ
    0.15
    illy
    0.15
    icals
    0.15
    Act Density 0.029%

    No Known Activations