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

    Neuronpedia

    INDEX
    Explanations

    countries as locations

    oai_token-act-pair · gpt-3.5-turbo

    geographical references to specific countries and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etsk
    -0.98
    status
    -0.72
    gotten
    -0.70
    ensions
    -0.70
    Privacy
    -0.69
    allow
    -0.68
    balance
    -0.67
    framework
    -0.67
    information
    -0.67
     bailed
    -0.65
    POSITIVE LOGITS
     Nights
    0.84
     Prix
    0.76
     Rite
    0.73
     Horror
    0.72
     Trilogy
    0.71
     accents
    0.70
     accent
    0.70
     Fried
    0.70
     Novel
    0.69
     Ninja
    0.67
    Act Density 0.329%

    No Known Activations