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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.83
    akeru
    -0.80
    ãĥ¼ãĤ¯
    -0.79
    cedented
    -0.76
     Nadu
    -0.75
    ocre
    -0.74
    ikuman
    -0.74
    nai
    -0.73
    wcs
    -0.72
    anwhile
    -0.71
    POSITIVE LOGITS
    riott
    0.81
     Painter
    0.71
    beck
    0.71
    ordan
    0.70
    bern
    0.70
    afort
    0.69
    lander
    0.67
    Neill
    0.66
     Freed
    0.65
    anson
    0.64
    Act Density 0.179%

    No Known Activations