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

    Neuronpedia

    INDEX
    Explanations

    names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.77
     Solitaire
    -0.71
    bart
    -0.70
    ãĥ¼ãĥ«
    -0.70
     Ceres
    -0.70
    culosis
    -0.67
     Yankee
    -0.66
     Fargo
    -0.64
     fabrication
    -0.63
     Buffy
    -0.63
    POSITIVE LOGITS
    Į
    1.27
    ´
    1.21
    £
    1.13
    ·
    1.08
    Ń
    1.07
    ¸
    1.06
    º
    1.03
    ¦
    1.01
    ¢
    1.01
    ¥
    1.00
    Act Density 0.018%

    No Known Activations