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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people's names with "oe" in them

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    rons
    -0.77
    ifiable
    -0.77
    ifiers
    -0.76
    iques
    -0.71
    iments
    -0.70
    naires
    -0.69
    arians
    -0.67
    ifications
    -0.67
    ifier
    -0.65
    ificate
    -0.64
    POSITIVE LOGITS
    ppel
    1.36
    hler
    1.21
    lect
    1.19
    hner
    1.18
    ffer
    1.11
    zie
    1.11
    cker
    1.04
    hl
    1.02
    zzi
    1.01
    utenant
    1.01
    Act Density 0.037%

    No Known Activations