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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     basket
    -0.69
     phyl
    -0.68
     multiplying
    -0.67
     suitcase
    -0.63
     expansion
    -0.62
     prolifer
    -0.62
    ļéĨĴ
    -0.61
     expansions
    -0.61
     zones
    -0.61
     behavi
    -0.59
    POSITIVE LOGITS
     29
    1.00
     04
    0.99
     07
    0.98
     27
    0.98
     06
    0.97
     03
    0.96
     28
    0.96
     08
    0.95
     09
    0.94
     26
    0.94
    Act Density 0.063%

    No Known Activations