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

    Neuronpedia

    INDEX
    Explanations

    references to geographic locations and their capitals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UNITIES
    -0.48
    IMENTS
    -0.45
    communities
    -0.43
     района
    -0.42
    社区
    -0.42
     obce
    -0.41
     communities
    -0.41
     روستا
    -0.41
    riturismo
    -0.40
    Communities
    -0.39
    POSITIVE LOGITS
     capital
    2.25
    capital
    1.85
     capitale
    1.74
     Capital
    1.72
     CAPITAL
    1.72
    Capital
    1.70
     capitol
    1.61
     capitals
    1.60
    CAPITAL
    1.44
     capitales
    1.37
    Act Density 0.130%

    No Known Activations