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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and indigenous peoples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sloven
    -0.18
    ãĤ¤ãĥĦ
    -0.18
     Eston
    -0.16
     belg
    -0.15
    ozÃŃ
    -0.15
    istrovstvÃŃ
    -0.15
     Belg
    -0.15
    plen
    -0.15
     Slovak
    -0.15
     Austrian
    -0.14
    POSITIVE LOGITS
     Africa
    0.23
     remote
    0.22
     remot
    0.20
     Java
    0.20
     Siber
    0.17
     Flores
    0.17
     distant
    0.17
     Asia
    0.17
     parts
    0.16
     Amazon
    0.16
    Act Density 0.251%

    No Known Activations