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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and landmarks

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations and landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-
    -0.72
     interrog
    -0.72
     deflation
    -0.68
     infall
    -0.67
     Canaver
    -0.66
     ridic
    -0.66
     pessim
    -0.66
    erity
    -0.65
     attribution
    -0.63
     whistleblower
    -0.63
    POSITIVE LOGITS
     Islands
    1.10
     counties
    0.99
     Peninsula
    0.98
     Highlands
    0.92
    shire
    0.92
     suburbs
    0.91
    opolis
    0.90
     Junction
    0.90
     Regions
    0.90
     peninsula
    0.90
    Act Density 0.363%

    No Known Activations