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

    Neuronpedia

    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bottleneck
    -0.77
    ģĸ
    -0.67
    ĸļ
    -0.66
    £ı
    -0.66
     Thumbnails
    -0.65
     Gemini
    -0.63
     limiting
    -0.63
     *.
    -0.62
     renamed
    -0.62
     sidebar
    -0.62
    POSITIVE LOGITS
    isha
    1.01
    add
    0.99
    ona
    0.98
    osh
    0.97
    ok
    0.96
    annie
    0.96
    anta
    0.96
    FA
    0.96
    azz
    0.95
    aj
    0.93
    Act Density 0.219%

    No Known Activations