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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or leaving a location

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating movement or exit from locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     globally
    -0.75
    Ħ¢
    -0.75
    azeera
    -0.65
     regimes
    -0.65
    immune
    -0.63
    ï¸ı
    -0.63
     Australians
    -0.63
     insurg
    -0.62
     yearly
    -0.62
     viruses
    -0.61
    POSITIVE LOGITS
     downstairs
    1.07
     upstairs
    1.06
     hallway
    1.04
     Room
    1.04
    rium
    1.02
     aisle
    0.95
     town
    0.92
     backstage
    0.91
     room
    0.90
     adjoining
    0.88
    Act Density 0.240%

    No Known Activations