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

    Neuronpedia

    INDEX
    Explanations

    Twitter usernames

    oai_token-act-pair · gpt-3.5-turbo

    underscore-prefixed usernames or handles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eteria
    -0.76
     Leilan
    -0.73
    quished
    -0.71
    atform
    -0.69
     Yose
    -0.66
     Manson
    -0.65
     blender
    -0.63
     reception
    -0.62
     screenings
    -0.62
     Galile
    -0.62
    POSITIVE LOGITS
    ebook
    1.04
    blank
    1.03
    dict
    0.99
    tro
    0.97
    country
    0.96
    chance
    0.94
    dust
    0.93
    gradient
    0.93
    pill
    0.93
    page
    0.92
    Act Density 0.019%

    No Known Activations