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

    Neuronpedia

    INDEX
    Explanations

    instances of significant locations or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    geographical locations and place names.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     street
    -0.59
     streets
    -0.54
     Streets
    -0.52
     Street
    -0.52
    city
    -0.50
     city
    -0.50
     STREET
    -0.50
    streets
    -0.50
     Chinatown
    -0.50
     downtown
    -0.50
    POSITIVE LOGITS
     farm
    1.32
     farms
    1.16
     farmhouse
    1.13
     ranch
    1.09
     Farm
    1.08
    Farm
    1.05
     granja
    1.05
    farm
    1.04
     fazenda
    1.02
     homestead
    0.97
    Act Density 0.303%

    No Known Activations