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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.16
    lisi
    -0.16
    asser
    -0.14
    oplevel
    -0.14
    aits
    -0.14
    골
    -0.14
    achi
    -0.13
    äm
    -0.13
    wang
    -0.13
    esco
    -0.13
    POSITIVE LOGITS
    1
    0.14
     Affero
    0.14
    cept
    0.14
    iable
    0.14
     Schwartz
    0.13
    ÑĮко
    0.13
     McGr
    0.13
    attles
    0.13
     Swagger
    0.13
    oker
    0.13
    Act Density 0.196%

    No Known Activations