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

    Neuronpedia

    INDEX
    Explanations

    names of famous or notable people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artifacts
    -0.84
    cia
    -0.81
    atu
    -0.80
    omi
    -0.80
    Disclaimer
    -0.80
    lia
    -0.78
    onyms
    -0.74
    ictions
    -0.74
    cot
    -0.74
    Accessory
    -0.73
    POSITIVE LOGITS
     Rowling
    1.22
     Abrams
    1.07
     Marriott
    1.02
     Reynolds
    1.01
     Blaz
    0.99
     Bach
    0.95
     Tolkien
    0.94
     Simmons
    0.93
     Ballard
    0.92
     Hig
    0.89
    Act Density 0.069%

    No Known Activations