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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic characters and English loanwords written with Cyrillic character representations

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols of non-standard ASCII encoding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Riley
    -0.65
    ebted
    -0.65
     Daly
    -0.64
     Firm
    -0.58
     GAME
    -0.58
    oppable
    -0.58
     sting
    -0.58
     Lisp
    -0.58
     Fisher
    -0.57
    omial
    -0.57
    POSITIVE LOGITS
    ¹
    2.08
    ·
    1.98
    ³
    1.98
    ±
    1.97
    1.92
    ¿
    1.91
    ¯
    1.57
    ¡
    1.53
    ©
    1.45
    Ń
    1.45
    Act Density 0.012%

    No Known Activations