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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns referring to a male person

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or character in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    services
    -0.63
    odge
    -0.62
     Pastebin
    -0.61
    mble
    -0.61
    profits
    -0.60
    itures
    -0.60
     Result
    -0.60
     Worlds
    -0.59
     Railroad
    -0.58
    ĨĴ
    -0.58
    POSITIVE LOGITS
     personally
    1.00
    panic
    0.98
    ading
    0.93
     Majesty
    0.88
     orally
    0.82
     himself
    0.82
    atically
    0.81
    atic
    0.78
    zbollah
    0.76
    soever
    0.70
    Act Density 0.097%

    No Known Activations