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

    Neuronpedia

    INDEX
    Explanations

    the start of a new section or topic in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.45
    på
    -0.39
     —
    -0.37
    borderSide
    -0.37
     various
    -0.35
     whatever
    -0.35
     pri
    -0.35
     versus
    -0.34
     obrazov
    -0.33
     O
    -0.33
    POSITIVE LOGITS
    tagHelperRunner
    1.19
    rungsseite
    1.09
    ########.
    1.02
    OGND
    1.00
    RegressionTest
    1.00
     Roskov
    1.00
     propOrder
    0.99
    <bos>
    0.99
    0.98
    :✨
    0.97
    Act Density 0.322%

    No Known Activations