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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data regarding statistical highs and lows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.73
    love
    -0.70
    hyde
    -0.69
    fab
    -0.68
    iverse
    -0.66
    prototype
    -0.66
    mar
    -0.65
    èĪ
    -0.65
    faith
    -0.65
    unity
    -0.64
    POSITIVE LOGITS
    ever
    1.02
     contrace
    0.84
     earners
    0.82
     ever
    0.81
     allowable
    0.77
     Cutter
    0.74
     contiguous
    0.72
    vati
    0.71
     EVER
    0.69
     seiz
    0.67
    Act Density 0.171%

    No Known Activations