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

    Neuronpedia

    INDEX
    Explanations

    locations and events mentioned in a historical or news context

    oai_token-act-pair · gpt-3.5-turbo

    references to significant historical events or periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mariners
    -0.78
     Uzbek
    -0.77
    opal
    -0.73
    antha
    -0.73
    Arizona
    -0.72
     Koreans
    -0.71
     AAP
    -0.69
     Hyundai
    -0.69
    480
    -0.68
     Kodi
    -0.67
    POSITIVE LOGITS
     Franç
    1.48
     Ãī
    1.47
     Ré
    1.44
     Qué
    1.42
     Ãł
    1.42
    ère
    1.39
     Rouge
    1.37
     François
    1.36
     du
    1.35
     Jacques
    1.29
    Act Density 0.378%

    No Known Activations