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

    Neuronpedia

    INDEX
    Explanations

    examples or instances

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Example" and variations of it, indicating examples or references within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aciously
    -0.80
    rica
    -0.71
     sweats
    -0.70
    iosity
    -0.69
    roid
    -0.69
    oop
    -0.69
     tooth
    -0.67
    ismo
    -0.67
     silence
    -0.67
    fur
    -0.66
    POSITIVE LOGITS
     Examples
    1.07
     Example
    1.06
     Helpful
    0.93
     Sample
    0.92
    Example
    0.90
     Prompt
    0.89
     Explan
    0.88
     Casting
    0.88
     Suggest
    0.87
     Typical
    0.86
    Act Density 0.034%

    No Known Activations