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

    Neuronpedia

    INDEX
    Explanations

    phrases related to regulatory bodies

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "and" in a specific context, indicating a focus on cumulative elements or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Duchess
    -0.79
     Triangle
    -0.72
     Rollins
    -0.68
    pole
    -0.65
    Integ
    -0.65
     Unch
    -0.64
     Commodore
    -0.64
    iPhone
    -0.63
    RGB
    -0.63
     Rutherford
    -0.63
    POSITIVE LOGITS
     beverage
    1.27
     drink
    1.23
     beverages
    1.17
     drinks
    1.01
     clothing
    0.94
     nutrition
    0.90
     Drink
    0.90
     medicine
    0.89
     lodging
    0.88
     snack
    0.83
    Act Density 0.120%

    No Known Activations