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

    Neuronpedia

    INDEX
    Explanations

    foreign language characters and symbols from various languages

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.80
     guiActiveUnfocused
    -0.75
    terday
    -0.70
    ORED
    -0.67
    bucks
    -0.65
     TPP
    -0.64
    ierre
    -0.63
    flash
    -0.62
     Athletics
    -0.60
     discounted
    -0.59
    POSITIVE LOGITS
    ģ
    1.22
    ¬
    1.08
    ¼
    1.08
    ĭ
    1.05
    ®
    1.02
    ½
    1.02
    Ł
    1.00
    ³
    1.00
     Ã
    0.99
    Ģ
    0.99
    Act Density 0.006%

    No Known Activations