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

    Neuronpedia

    INDEX
    Explanations

    specific dates, events, or actions mentioned in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilet
    -0.64
     physiology
    -0.61
     physic
    -0.60
     Divinity
    -0.60
     Eye
    -0.60
     Hyd
    -0.59
     guessing
    -0.58
     Vend
    -0.57
     Everywhere
    -0.56
    ysis
    -0.56
    POSITIVE LOGITS
     resulted
    1.05
     culminated
    1.02
     preceded
    0.96
     fateful
    0.92
     sparked
    0.89
     includes
    0.87
     lasted
    0.87
    amar
    0.87
     accompanies
    0.86
     prompted
    0.85
    Act Density 0.235%

    No Known Activations