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

    Neuronpedia

    INDEX
    Explanations

    references to blocks and their attributes in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     payé
    -0.81
    stdarg
    -0.80
    ükemmel
    -0.76
    ươi
    -0.75
    %)$
    -0.73
     للاسماء
    -0.73
    HttpFoundation
    -0.73
     Ory
    -0.73
     sexuales
    -0.73
     révélé
    -0.73
    POSITIVE LOGITS
     BLOCK
    2.14
     Block
    2.09
     block
    2.06
     blocks
    2.04
    block
    2.03
    BLOCK
    1.98
    Block
    1.92
     Blocks
    1.91
    blocks
    1.87
    Blocks
    1.75
    Act Density 0.046%

    No Known Activations