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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations and related events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cay
    -0.48
     chiaramente
    -0.46
     sembrano
    -0.46
     Oth
    -0.46
    silen
    -0.44
     incarcer
    -0.44
     Oru
    -0.44
    Braz
    -0.43
     Qar
    -0.43
    makeText
    -0.43
    POSITIVE LOGITS
     Afghanistan
    1.20
    Afghanistan
    1.12
     Afghan
    1.08
    ABUL
    1.02
    Afghan
    0.98
     Afghans
    0.85
     Darío
    0.83
     afghan
    0.83
     Afgan
    0.80
     Kabul
    0.76
    Act Density 0.094%

    No Known Activations