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

    Neuronpedia

    INDEX
    Explanations

    references to historical and mythological narratives involving the Pandavas from the Mahabharata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ores
    -0.17
    halten
    -0.15
    762
    -0.15
    crest
    -0.15
    ÑĢо
    -0.14
    _slope
    -0.14
    ivent
    -0.14
    ÙĪÙĥ
    -0.14
    893
    -0.14
     ple
    -0.14
    POSITIVE LOGITS
    jie
    0.15
    inar
    0.15
    adu
    0.15
    inars
    0.14
    ISED
    0.14
    amage
    0.14
    engan
    0.14
    ptal
    0.14
    raid
    0.13
     Leakage
    0.13
    Act Density 0.053%

    No Known Activations