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

    Neuronpedia

    INDEX
    Explanations

    specific locations such as bodies of water and geographic regions

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and bodies of water

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    POR
    -0.78
    HK
    -0.77
    MK
    -0.77
    è»
    -0.76
    ĪĴ
    -0.75
     HK
    -0.75
    NK
    -0.74
     photoc
    -0.74
    VP
    -0.72
    OUP
    -0.70
    POSITIVE LOGITS
     Basin
    1.22
     Islands
    1.10
     basin
    1.10
     ridge
    1.03
     Peninsula
    1.01
     coastline
    1.00
     Expedition
    0.99
     Passage
    0.95
     Route
    0.94
     islands
    0.94
    Act Density 0.151%

    No Known Activations