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

    Neuronpedia

    INDEX
    Explanations

    the word "Whole"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific brands, organizations, or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oused
    -0.83
    icable
    -0.78
    aciously
    -0.78
     externalToEVAOnly
    -0.75
     convincing
    -0.73
    iosyncr
    -0.72
     includ
    -0.70
     tremend
    -0.70
    oled
    -0.67
    antically
    -0.67
    POSITIVE LOGITS
     Responsibility
    0.90
     Limits
    0.90
     Foods
    0.89
     Investigations
    0.89
     Ones
    0.89
     Definition
    0.86
     Forces
    0.85
     Mind
    0.84
     Works
    0.84
     Room
    0.84
    Act Density 0.202%

    No Known Activations