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

    Neuronpedia

    INDEX
    Explanations

    questions and uncertainties expressed in text

    oai_token-act-pair · gpt-3.5-turbo

    questions and concerns about individual behavior and circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     export
    -0.78
     mechan
    -0.75
     exported
    -0.72
     corrid
    -0.68
    eware
    -0.68
     artisan
    -0.68
     ancestor
    -0.66
     pioneered
    -0.65
     imported
    -0.64
     geometric
    -0.64
    POSITIVE LOGITS
    inventoryQuantity
    1.00
     apologizing
    0.85
     apologized
    0.80
     remorse
    0.77
     apology
    0.73
     demeanor
    0.73
     Rosenstein
    0.71
     flashbacks
    0.70
     Corker
    0.70
    Asked
    0.68
    Act Density 1.132%

    No Known Activations