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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proportions or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anova
    -0.17
    eri
    -0.16
    éri
    -0.15
    ermo
    -0.15
    hled
    -0.14
    itan
    -0.14
    EMALE
    -0.14
    ä¸ĺ
    -0.14
    erver
    -0.14
    agn
    -0.14
    POSITIVE LOGITS
    alcon
    0.17
    OfClass
    0.15
    ¡
    0.15
    tron
    0.14
    239
    0.14
    ÑĤÑĥ
    0.14
     UCHAR
    0.14
    resco
    0.14
    лаг
    0.14
    %%%%%%%%
    0.13
    Act Density 0.032%

    No Known Activations