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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "at a," particularly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Images
    -0.85
    baugh
    -0.81
    Sources
    -0.77
    Types
    -0.71
    rils
    -0.70
    facts
    -0.70
    ernels
    -0.69
     variants
    -0.69
    Methods
    -0.67
    uploads
    -0.67
    POSITIVE LOGITS
     shitty
    0.90
     stranger
    0.90
     rave
    0.89
     birthday
    0.88
     drunken
    0.87
     menstru
    0.86
     restaurant
    0.84
     picnic
    0.83
     crowded
    0.83
     wedding
    0.82
    Act Density 0.315%

    No Known Activations