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

    Neuronpedia

    INDEX
    Explanations

    references to political events and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     uu
    -0.15
    sak
    -0.14
    unda
    -0.14
    038
    -0.14
     Atomic
    -0.14
     Athe
    -0.13
     تÙĦ
    -0.13
    bidden
    -0.13
    éº
    -0.13
     equals
    -0.13
    POSITIVE LOGITS
     Hait
    0.45
     Haiti
    0.43
    hait
    0.29
     Dominican
    0.25
     Caribbean
    0.24
     Santo
    0.23
     Jamaica
    0.22
    isque
    0.22
     Bahamas
    0.21
     gang
    0.21
    Act Density 0.027%

    No Known Activations