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

    Neuronpedia

    INDEX
    Explanations

    proper nouns in phrases

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artifacts
    -0.79
    wcs
    -0.78
    mining
    -0.77
    uggest
    -0.72
    minist
    -0.72
    system
    -0.70
    climate
    -0.69
    vernment
    -0.69
    imum
    -0.69
    pmwiki
    -0.68
    POSITIVE LOGITS
     Sons
    0.92
     Morty
    0.91
     Ellie
    0.89
     Mary
    0.86
     Buster
    0.85
     Clyde
    0.84
     Paige
    0.84
     Donna
    0.84
     Kyl
    0.84
     Jerry
    0.84
    Act Density 0.119%

    No Known Activations