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

    Neuronpedia

    INDEX
    Explanations

    references to measurement and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ough
    -0.19
    ually
    -0.17
    erson
    -0.16
    iface
    -0.16
    ogle
    -0.15
    ished
    -0.15
    agi
    -0.15
    建设
    -0.14
    882
    -0.14
    uce
    -0.14
    POSITIVE LOGITS
    ments
    0.21
    .Measure
    0.19
    UREMENT
    0.18
    ables
    0.18
    abant
    0.17
    nts
    0.17
    ably
    0.16
    ÑīинÑĭ
    0.15
    idian
    0.15
    nt
    0.15
    Act Density 0.036%

    No Known Activations