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

    Neuronpedia

    INDEX
    Explanations

    locations or bases of businesses or military operations

    oai_token-act-pair · gpt-3.5-turbo

    references to physical locations and bases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nerv
    -0.80
    rous
    -0.70
    vernment
    -0.70
    ictionary
    -0.67
     FANTASY
    -0.64
    itive
    -0.64
     cand
    -0.64
    API
    -0.62
    gey
    -0.62
     sudden
    -0.61
    POSITIVE LOGITS
     locations
    1.01
     Locations
    0.99
     abroad
    0.99
     downtown
    0.99
     overseas
    0.89
     footprint
    0.86
     located
    0.84
     elsewhere
    0.84
     Downtown
    0.83
     Asheville
    0.83
    Act Density 0.296%

    No Known Activations