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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns referring to a male individual

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pastebin
    -0.67
    profits
    -0.61
     Railroad
    -0.59
     ITS
    -0.58
     Idle
    -0.57
     communities
    -0.57
     Gems
    -0.56
     AM
    -0.56
     appl
    -0.55
    uve
    -0.54
    POSITIVE LOGITS
     personally
    1.12
    panic
    0.99
    ading
    0.92
     Majesty
    0.90
    zbollah
    0.87
    atically
    0.86
    enegger
    0.85
     himself
    0.84
    eded
    0.81
    sing
    0.81
    Act Density 0.105%

    No Known Activations