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

    Neuronpedia

    INDEX
    Explanations

    website domain names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of website domain extensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Revel
    -0.73
     numbering
    -0.66
    JUST
    -0.57
    rons
    -0.56
    DERR
    -0.56
     Shades
    -0.55
     evapor
    -0.55
     Hungry
    -0.55
     corrections
    -0.55
     Kut
    -0.55
    POSITIVE LOGITS
    ffee
    1.33
    perty
    1.11
    verage
    1.02
    opers
    1.01
    ffic
    0.97
    lymp
    0.90
    ingen
    0.89
    oper
    0.88
    zon
    0.88
    ilers
    0.88
    Act Density 0.015%

    No Known Activations