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

    Neuronpedia

    INDEX
    Explanations

    comparisons and contrasts in relationships or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acle
    -0.18
    GenerationStrategy
    -0.16
    ingo
    -0.16
    ardo
    -0.15
    ninger
    -0.15
    OffsetTable
    -0.15
    SupportedContent
    -0.15
    untime
    -0.14
    ige
    -0.14
    olkien
    -0.14
    POSITIVE LOGITS
    nor
    0.23
     nor
    0.23
     anymore
    0.17
     Strict
    0.15
     Nor
    0.15
     others
    0.15
    net
    0.15
     Cobb
    0.14
     div
    0.14
    igua
    0.14
    Act Density 0.216%

    No Known Activations