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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names, specifically with the substring "ans" frequently appearing in the activations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Fr" or variations thereof related to locations, specifically San Francisco

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jinn
    -0.80
    izu
    -0.68
     Izan
    -0.66
     Contrast
    -0.64
     Siren
    -0.64
     Archdemon
    -0.63
    Redd
    -0.63
    atsu
    -0.62
     Lith
    -0.61
     Khe
    -0.61
    POSITIVE LOGITS
    isco
    0.98
    ruary
    0.79
    ulent
    0.78
    atism
    0.76
    rance
    0.74
    nce
    0.70
    furt
    0.69
    fur
    0.67
    acies
    0.67
    ateurs
    0.65
    Act Density 0.083%

    No Known Activations