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

    Neuronpedia

    INDEX
    Explanations

    identifiers and versioning related to software dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dera
    -0.16
    zo
    -0.16
    ww
    -0.16
    pus
    -0.16
    ersh
    -0.15
    вол
    -0.15
    arel
    -0.14
    YSTEM
    -0.14
    atures
    -0.14
     Ulus
    -0.14
    POSITIVE LOGITS
     Gott
    0.15
     Revision
    0.15
    Raised
    0.14
    arget
    0.13
    revision
    0.13
    .Formatting
    0.13
    éĹ
    0.13
     Lone
    0.13
    æł¹æľ¬
    0.13
    %%%%%%%%
    0.13
    Act Density 0.002%

    No Known Activations