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

    Neuronpedia

    INDEX
    Explanations

    structural terminology related to research reviews or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    رشف
    -1.03
     AssemblyCulture
    -0.97
     InputDecoration
    -0.92
     Normdatei
    -0.89
    awtextra
    -0.88
     שוליים
    -0.82
     '\\;'
    -0.82
    Hentet
    -0.82
     ModelExpression
    -0.80
    InputBorder
    -0.78
    POSITIVE LOGITS
    RegressionTest
    0.62
    KommentareTeilen
    0.61
     NBS
    0.47
     DFB
    0.46
    ↵↵
    0.43
     barges
    0.41
     irony
    0.41
    br
    0.41
    чник
    0.41
     postulates
    0.40
    Act Density 0.294%

    No Known Activations