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

    Neuronpedia

    INDEX
    Explanations

    dates formatted as "Month Date"

    oai_token-act-pair · gpt-3.5-turbo

    dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lder
    -0.71
    itaire
    -0.70
     cumbers
    -0.68
    kB
    -0.66
     tray
    -0.65
    gone
    -0.63
     unnecess
    -0.63
     tox
    -0.63
     cleansing
    -0.63
     suspic
    -0.62
    POSITIVE LOGITS
     Madness
    1.22
    riage
    0.91
    ing
    0.90
    yard
    0.89
    rd
    0.87
    steen
    0.81
     2019
    0.79
    nard
    0.78
    flower
    0.77
     Arbor
    0.75
    Act Density 0.023%

    No Known Activations