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

    Neuronpedia

    INDEX
    Explanations

    words related to skills, professions, and activities

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns related to various subjects and fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ploma
    -0.65
    cise
    -0.65
    Ò
    -0.61
    ettle
    -0.60
    aughs
    -0.60
    Í
    -0.60
     Pigs
    -0.59
    iggins
    -0.57
    Ö¼
    -0.56
    Ĭ±
    -0.55
    POSITIVE LOGITS
     heirs
    0.61
     analysts
    0.60
     reverted
    0.60
     automakers
    0.56
     programmers
    0.54
     defenders
    0.54
     engineers
    0.53
     astronomers
    0.53
     âĢİ
    0.51
     craw
    0.51
    Act Density 0.725%

    No Known Activations