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

    Neuronpedia

    INDEX
    Explanations

    words and phrases in italics

    oai_token-act-pair · gpt-3.5-turbo

    references to italicized text formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĵĺ
    -0.87
    bell
    -0.85
    ModLoader
    -0.77
    é¾
    -0.74
    uyomi
    -0.71
    liga
    -0.68
    alore
    -0.68
    redits
    -0.68
    awaru
    -0.67
    redit
    -0.67
    POSITIVE LOGITS
    icity
    0.93
    isf
    0.83
    itaire
    0.74
    isphere
    0.73
    itarian
    0.72
    ics
    0.72
    icals
    0.72
    ician
    0.70
    ienne
    0.70
    isk
    0.70
    Act Density 0.046%

    No Known Activations