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

    Neuronpedia

    INDEX
    Explanations

    the character "Ã" followed by certain special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols commonly used in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.71
     flask
    -0.67
    bucks
    -0.66
     Donovan
    -0.63
     upd
    -0.62
     flash
    -0.60
     Bangalore
    -0.60
     karma
    -0.59
     Sakura
    -0.56
    ifications
    -0.56
    POSITIVE LOGITS
    ¢
    1.72
    ĵ
    1.64
    ĺ
    1.63
    ģ
    1.62
    į
    1.58
    ¤
    1.56
    ¼
    1.56
    ħ
    1.55
    ŀ
    1.55
    ª
    1.52
    Act Density 0.019%

    No Known Activations