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

    Neuronpedia

    INDEX
    Explanations

    words related to specific events, locations, and names, potentially related to a legal or criminal context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    awaran
    -0.47
     Puritans
    -0.47
     Greensboro
    -0.46
    yelidikan
    -0.45
     siyang
    -0.45
    Cormack
    -0.44
    visející
    -0.44
    empatan
    -0.43
    コマ
    -0.43
    millan
    -0.43
    POSITIVE LOGITS
     Cal
    1.42
     cal
    1.36
    Cal
    1.35
     CAL
    1.33
    cal
    1.24
    CAL
    1.15
     Kalifor
    1.03
    Kal
    1.00
     Cali
    0.99
     cale
    0.98
    Act Density 0.090%

    No Known Activations