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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    sequences of Arabic script that form coherent words or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tether
    -0.80
     Sega
    -0.76
     puppy
    -0.75
     reinvest
    -0.74
     Wilmington
    -0.74
     demos
    -0.74
    axter
    -0.73
     welf
    -0.72
     homebrew
    -0.72
     puppies
    -0.72
    POSITIVE LOGITS
    Ú
    2.52
    Û
    2.48
    د
    2.46
    ر
    2.45
    ا
    2.41
    ÙĪ
    2.41
    ت
    2.39
    Ùħ
    2.38
    اØ
    2.37
    Ùĩ
    2.34
    Act Density 0.019%

    No Known Activations