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

    Neuronpedia

    INDEX
    Explanations

    cities or countries

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations, particularly cities and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Surviv
    -0.73
    Leod
    -0.72
    Trend
    -0.71
     Raider
    -0.70
     Trooper
    -0.67
    Norm
    -0.65
    vich
    -0.65
     Scotch
    -0.65
    LLOW
    -0.65
    estern
    -0.64
    POSITIVE LOGITS
    ascus
    1.04
     Lumpur
    1.01
     rall
    0.91
     Pact
    0.83
    ijing
    0.80
     Aires
    0.78
     suburbs
    0.78
     metropolitan
    0.76
     suburb
    0.75
     Zoo
    0.74
    Act Density 0.055%

    No Known Activations