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

    Neuronpedia

    INDEX
    Explanations

    instances of plurality and variations in number and configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     directly
    -0.17
    cken
    -0.17
     fa
    -0.15
     få
    -0.14
     that
    -0.14
    ibli
    -0.14
     some
    -0.14
    ãĤ¡
    -0.14
    edImage
    -0.13
    cin
    -0.13
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.20
     simultaneous
    0.20
    åIJĮæĻĤ
    0.20
     birden
    0.20
     equally
    0.20
     VERSION
    0.19
    çīĪæľ¬
    0.17
     separate
    0.17
     simultaneously
    0.17
     versions
    0.17
    Act Density 0.188%

    No Known Activations