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

    Neuronpedia

    INDEX
    Explanations

    strings of characters that are not typical words, potentially encoding specific information in a unique way

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.85
     guiActiveUnfocused
    -0.82
    manship
    -0.75
     Nanto
    -0.73
     Athletics
    -0.68
     VK
    -0.67
     Atom
    -0.66
     Samson
    -0.65
    iants
    -0.64
     PubMed
    -0.64
    POSITIVE LOGITS
    ¹
    1.35
    ³
    1.21
    ´
    1.17
    ¸
    1.17
    º
    1.15
    ¼
    1.14
    ¬
    1.13
    ª
    1.11
    ¿
    1.11
    ¾
    1.09
    Act Density 0.006%

    No Known Activations