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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations, particularly related to specific bodies of water or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to geopolitical entities and locations, particularly related to the South China Sea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     canv
    -0.73
    erity
    -0.72
     Bolton
    -0.71
    oln
    -0.66
    acc
    -0.65
    conserv
    -0.65
    RM
    -0.65
    MJ
    -0.62
    ateurs
    -0.62
    roph
    -0.60
    POSITIVE LOGITS
     Sea
    1.28
     Seas
    1.19
     seas
    1.03
    Sea
    0.97
    sea
    0.92
     enclave
    0.80
     sea
    0.79
     Morning
    0.79
     Reef
    0.77
     Pacific
    0.76
    Act Density 0.049%

    No Known Activations