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

    Neuronpedia

    INDEX
    Explanations

    references to bugs and errors in a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.56
    versch
    -0.53
     wyś
    -0.52
    istung
    -0.50
     oč
    -0.49
     éc
    -0.48
    はじめに
    -0.48
     kuş
    -0.48
     muhte
    -0.47
    }{*}{
    -0.46
    POSITIVE LOGITS
     unknownFields
    0.82
    Datuak
    0.79
    PerformLayout
    0.78
    Билгалдахарш
    0.78
    TestingModule
    0.76
    DeleteBehavior
    0.76
     lenker
    0.76
    MLLoader
    0.74
    IntoConstraints
    0.73
    Personensuche
    0.72
    Act Density 0.404%

    No Known Activations