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

    Neuronpedia

    INDEX
    Explanations

    words related to accidental events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accuracy and reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lyak
    -0.75
    erness
    -0.73
    geist
    -0.69
    bley
    -0.69
    wich
    -0.68
    berman
    -0.68
    glers
    -0.68
    hs
    -0.67
    bian
    -0.67
    PT
    -0.67
    POSITIVE LOGITS
    redited
    1.30
    uracy
    1.16
    urate
    1.16
    idental
    1.14
    identally
    1.14
    enture
    1.09
    used
    1.08
    ustomed
    1.04
    ompl
    1.03
    reditation
    1.02
    Act Density 0.009%

    No Known Activations