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

    Neuronpedia

    INDEX
    Explanations

    unicode characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    the special character representations or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     princ
    -0.68
     tourist
    -0.64
     comprom
    -0.64
     interf
    -0.64
     Ukrain
    -0.63
     managerial
    -0.61
     Borough
    -0.61
     Mous
    -0.61
     divers
    -0.58
     Prospect
    -0.57
    POSITIVE LOGITS
    ¡
    1.19
    Ĵ
    1.09
    Ļ
    1.08
    ¬
    1.07
    ı
    1.05
    ¤
    1.04
    ª
    1.01
    ij
    1.00
    ľ
    0.95
    Ķ
    0.93
    Act Density 0.392%

    No Known Activations