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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers within a specific format or context

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values, particularly related to dates and statistical rankings in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifice
    -0.65
    Ĥİ
    -0.65
    lich
    -0.65
     hegemony
    -0.64
    herty
    -0.64
    urus
    -0.62
    ½
    -0.61
    chwitz
    -0.60
    ĺħ
    -0.59
     Proposition
    -0.59
    POSITIVE LOGITS
    th
    1.00
    86
    0.94
    87
    0.94
    89
    0.93
    ½
    0.93
    76
    0.91
    96
    0.90
    92
    0.89
    68
    0.89
    78
    0.89
    Act Density 0.215%

    No Known Activations