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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    its
    -0.16
    aml
    -0.16
    ria
    -0.15
    isko
    -0.15
    agt
    -0.15
    thag
    -0.14
    ogany
    -0.14
    m
    -0.14
    atel
    -0.14
    olders
    -0.14
    POSITIVE LOGITS
    iez
    0.16
    วà¸Ļ
    0.15
    imports
    0.15
    .googleapis
    0.14
    大çļĦ
    0.14
    δÎŃ
    0.13
    evenodd
    0.13
    edla
    0.13
    UMB
    0.13
    OfString
    0.13
    Act Density 0.000%

    No Known Activations