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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "st"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peel
    -0.70
     deaf
    -0.68
     Tate
    -0.66
     thumbs
    -0.64
     prepar
    -0.60
    perty
    -0.59
     amy
    -0.59
     competent
    -0.58
     entitle
    -0.57
     disabling
    -0.57
    POSITIVE LOGITS
    retch
    1.26
    oppers
    1.21
    oppable
    1.10
    itute
    1.05
    alker
    1.04
    hetics
    1.04
    rict
    1.03
    ools
    1.01
    itution
    1.01
    amped
    1.01
    Act Density 0.043%

    No Known Activations