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

    Neuronpedia

    INDEX
    Explanations

    background settings or contexts described in written text

    oai_token-act-pair · gpt-3.5-turbo

    references to visual backdrops or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ishable
    -0.88
    alties
    -0.81
    ldon
    -0.80
    secut
    -0.78
    nery
    -0.74
    ike
    -0.73
    cers
    -0.73
    ealing
    -0.72
    cer
    -0.71
    atri
    -0.70
    POSITIVE LOGITS
     backdrop
    1.39
    GROUND
    0.83
    enance
    0.75
    drops
    0.73
    ĸļ
    0.71
     EDITION
    0.68
     setting
    0.68
     Setting
    0.68
    )=(
    0.68
    FORE
    0.64
    Act Density 0.008%

    No Known Activations