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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing collective experiences and shared identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.69
    ărilor
    -0.65
    LETTER
    -0.63
    "/",
    -0.59
    ITTEN
    -0.59
    messer
    -0.59
    cba
    -0.58
    éron
    -0.58
    ormány
    -0.57
     للاسماء
    -0.57
    POSITIVE LOGITS
     everyone
    1.04
    Everyone
    0.99
     everybody
    0.97
    everyone
    0.96
     Everyone
    0.96
    Everybody
    0.92
     Everybody
    0.91
    everybody
    0.88
     EVERYONE
    0.86
    Tutti
    0.66
    Act Density 0.149%

    No Known Activations