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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving addition and variables

    oai_token-act-pair · gpt-3.5-turbo

    mathematical symbols and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achus
    -0.73
    advertising
    -0.72
    heit
    -0.67
    ppelin
    -0.66
    ktop
    -0.66
    ainment
    -0.63
    DonaldTrump
    -0.63
    76561
    -0.63
    sburg
    -0.62
    mia
    -0.60
    POSITIVE LOGITS
    {\
    0.77
     {\
    0.72
     //[
    0.71
     ACTIONS
    0.70
     {{
    0.69
     </
    0.69
     Result
    0.69
    initialized
    0.69
    ((
    0.68
    result
    0.67
    Act Density 0.086%

    No Known Activations