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

    Neuronpedia

    INDEX
    Explanations

    French language text and words.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @danielepoterti

    words related to war, literature, and industry

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to societal critique or observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Arizona
    -0.90
    baugh
    -0.87
     Mariners
    -0.79
     Hispanic
    -0.77
    Seattle
    -0.77
    arijuana
    -0.75
     Uzbek
    -0.75
    Redd
    -0.75
    amsung
    -0.75
    antha
    -0.74
    POSITIVE LOGITS
     Ré
    1.47
     Ãī
    1.40
     Ãł
    1.39
     Franç
    1.38
     France
    1.37
     François
    1.35
     Qué
    1.33
     Rouge
    1.32
     Hollande
    1.31
     Paris
    1.31
    Act Density 0.502%

    No Known Activations