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

    Neuronpedia

    INDEX
    Explanations

    terms related to experimental research and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.82
    +#+#
    -0.80
    NameInMap
    -0.73
    ing
    -0.68
    createCell
    -0.68
     postId
    -0.68
     leksikon
    -0.67
     bookId
    -0.66
    Amaz
    -0.66
    uegos
    -0.65
    POSITIVE LOGITS
     Experimental
    2.01
     experimental
    1.96
    Experimental
    1.92
    experimental
    1.80
     EXPERIMENTAL
    1.75
    EXPERIMENTAL
    1.53
     experimentally
    1.41
     expéri
    1.34
     experimente
    0.93
     эксперимента
    0.90
    Act Density 0.104%

    No Known Activations