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

    Neuronpedia

    INDEX
    Explanations

    terms related to community development and project proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idious
    -0.19
    theid
    -0.16
    лоÑĩ
    -0.16
    elastic
    -0.14
    à¸ķร
    -0.14
    ãģĿãģĨãģª
    -0.14
    acious
    -0.14
    iteration
    -0.14
    .invalidate
    -0.13
    .cloudflare
    -0.13
    POSITIVE LOGITS
    -wise
    0.43
    wise
    0.37
    ewise
    0.34
     wise
    0.34
    lessly
    0.33
    ologically
    0.32
    aneously
    0.31
    wards
    0.28
    ensively
    0.28
    istically
    0.27
    Act Density 0.594%

    No Known Activations