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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly focusing on last names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of players and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    metic
    -0.76
    vana
    -0.76
    Reviewer
    -0.75
    DragonMagazine
    -0.74
    arten
    -0.72
    POL
    -0.71
    dies
    -0.69
    kat
    -0.68
    enegger
    -0.68
    20439
    -0.67
    POSITIVE LOGITS
     Dixon
    0.84
     Robinson
    0.82
     Wiggins
    0.82
     Hayes
    0.81
     Frazier
    0.81
     Pruitt
    0.80
     Thompson
    0.80
     Everett
    0.79
     Booker
    0.79
     Ingram
    0.79
    Act Density 0.113%

    No Known Activations