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

    Neuronpedia

    INDEX
    Explanations

    combinations of numbers and letters, potentially related to codes or identification numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usra
    -0.77
     Lindsay
    -0.69
    bryce
    -0.68
    aining
    -0.67
     Buk
    -0.65
    grain
    -0.64
     mull
    -0.64
    McC
    -0.64
     mal
    -0.63
     Bruins
    -0.62
    POSITIVE LOGITS
     E
    2.09
    E
    1.95
     e
    1.59
     EB
    1.51
    EE
    1.48
     EE
    1.45
    Es
    1.44
     EF
    1.43
    EH
    1.42
     Ek
    1.38
    Act Density 0.628%

    No Known Activations