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

    Neuronpedia

    INDEX
    Explanations

    metrics and statistics related to performance outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atica
    -0.19
    oney
    -0.15
     Ke
    -0.15
    .vo
    -0.15
    ÑĨÑİ
    -0.15
    تÛĮب
    -0.14
    isas
    -0.14
    ellipsis
    -0.14
    imir
    -0.13
    urus
    -0.13
    POSITIVE LOGITS
     hardly
    0.15
    oppers
    0.15
    steder
    0.14
    ãĥ«ãĥī
    0.14
    fp
    0.14
     apart
    0.14
     Burgess
    0.14
    à¥įवत
    0.14
    posta
    0.13
     only
    0.13
    Act Density 0.267%

    No Known Activations