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

    Neuronpedia

    INDEX
    Explanations

    unsaturated fatty acids

    oai_token-act-pair · gpt-3.5-turbo

    variations of the prefix "un-" and "uns," indicating negation or a lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    brush
    -0.75
    stal
    -0.74
    stals
    -0.73
    rar
    -0.72
    istics
    -0.71
    ulations
    -0.70
    lov
    -0.70
    mers
    -0.69
    cing
    -0.68
    types
    -0.67
    POSITIVE LOGITS
    afe
    0.88
    Unt
    0.78
     safety
    0.75
    ierrez
    0.72
    ECTION
    0.71
     adolesc
    0.70
    ACTED
    0.68
    icit
    0.67
    ategor
    0.66
    unction
    0.66
    Act Density 0.032%

    No Known Activations