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

    Neuronpedia

    INDEX
    Explanations

    quantifiable limits and conditions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ury
    -0.16
    IDD
    -0.16
     Wich
    -0.15
    uder
    -0.15
    alley
    -0.14
    ugal
    -0.14
    una
    -0.14
    reau
    -0.14
    Å¡ti
    -0.13
    ados
    -0.13
    POSITIVE LOGITS
     three
    0.18
     four
    0.17
     five
    0.17
     six
    0.15
     seven
    0.14
    ingly
    0.14
    ä¸ī个
    0.14
    ould
    0.14
    0.14
     two
    0.14
    Act Density 0.080%

    No Known Activations