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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals, associated with significant events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tered
    -0.83
    izont
    -0.81
    rine
    -0.80
    ration
    -0.80
    ional
    -0.80
    urity
    -0.77
    ihad
    -0.76
    pees
    -0.75
    raq
    -0.74
    oded
    -0.73
    POSITIVE LOGITS
    giving
    0.82
    mares
    0.78
    bye
    0.72
     Newman
    0.68
    ening
    0.68
    ships
    0.66
     fixme
    0.65
    bourg
    0.65
    stadt
    0.64
    Safety
    0.64
    Act Density 0.052%

    No Known Activations