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, specifically names of people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dire
    -0.71
     helic
    -0.71
     USPS
    -0.69
     Hurricanes
    -0.69
     CLS
    -0.69
     supers
    -0.68
     AAC
    -0.67
     Helic
    -0.67
     Coastal
    -0.67
     Hyundai
    -0.65
    POSITIVE LOGITS
    rower
    1.02
    beck
    1.00
    riott
    0.95
    amiya
    0.93
    kowski
    0.91
    keley
    0.90
    rage
    0.90
    zinski
    0.90
    mberg
    0.89
    leck
    0.87
    Act Density 0.090%

    No Known Activations