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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographical locations, especially bodies of water

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    picture
    -0.78
    jad
    -0.73
    ered
    -0.61
    UTE
    -0.61
     amount
    -0.60
     diagrams
    -0.59
    psc
    -0.59
    skirts
    -0.58
    tein
    -0.58
    elsius
    -0.57
    POSITIVE LOGITS
     Mexico
    0.95
     Ton
    0.95
     Aden
    0.86
     Guinea
    0.85
     Galile
    0.80
     Corinth
    0.77
     Plenty
    0.75
     Oman
    0.73
     Hispan
    0.71
     Naples
    0.69
    Act Density 0.033%

    No Known Activations