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

    Neuronpedia

    INDEX
    Explanations

    references to public life

    oai_token-act-pair · gpt-3.5-turbo

    references to life in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -0.95
    oug
    -0.79
    mented
    -0.78
    ractive
    -0.77
    atchewan
    -0.73
    uned
    -0.72
    agger
    -0.71
    essee
    -0.70
    ressed
    -0.70
    rosc
    -0.70
    POSITIVE LOGITS
    guards
    0.97
     expectancy
    0.97
    guard
    0.91
    blood
    0.91
    forms
    0.90
    boat
    0.84
    boats
    0.81
    lihood
    0.81
    bringer
    0.72
    mares
    0.71
    Act Density 0.035%

    No Known Activations