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

    Neuronpedia

    INDEX
    Explanations

    complex combinations of special characters and alphanumeric symbols

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols from non-Latin scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cly
    -0.78
    abase
    -0.72
     Probe
    -0.70
    ulators
    -0.69
     wallets
    -0.68
     Sega
    -0.67
    iko
    -0.67
    atcher
    -0.66
    ernels
    -0.65
     payday
    -0.65
    POSITIVE LOGITS
    ا
    2.03
    Ù
    1.97
    Ùĩ
    1.96
    د
    1.93
    ÙĪ
    1.92
    ÙĨ
    1.91
    Ø
    1.90
    اØ
    1.90
    ر
    1.87
    ت
    1.85
    Act Density 0.009%

    No Known Activations