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

    Neuronpedia

    INDEX
    Explanations

    locations and countries

    oai_token-act-pair · gpt-3.5-turbo

    references to specific countries or geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.81
    bats
    -0.81
    igan
    -0.71
    bern
    -0.69
    µ
    -0.67
    BOOK
    -0.66
    Torrent
    -0.66
    gotten
    -0.65
    struct
    -0.64
    abol
    -0.63
    POSITIVE LOGITS
    ;;;;;;;;;;;;
    0.77
     Dept
    0.76
     Territory
    0.76
     Converted
    0.75
    tu
    0.72
     Headquarters
    0.69
     respectively
    0.66
     Til
    0.66
     Miko
    0.66
     Died
    0.65
    Act Density 0.074%

    No Known Activations