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

    Neuronpedia

    INDEX
    Explanations

    references to historical and iconic symbols

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    _.
    -0.86
    *.
    -0.80
     ;)
    -0.79
     behav
    -0.75
    sic
    -0.73
    .*
    -0.73
    +.
    -0.69
    ļéĨĴ
    -0.69
    >.
    -0.69
    tml
    -0.67
    POSITIVE LOGITS
     Hearthstone
    0.65
     NASCAR
    0.62
     Canaver
    0.62
     Hillary
    0.60
     Pokémon
    0.60
     Donald
    0.57
     Wenger
    0.57
     astronomers
    0.56
     Guardiola
    0.55
     Orioles
    0.55
    Act Density 2.177%

    No Known Activations