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

    Neuronpedia

    INDEX
    Explanations

    references to social norms and societal behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.62
    ScopeManager
    -0.58
    erover
    -0.53
    TypedDataSet
    -0.51
     virginity
    -0.48
    Activité
    -0.48
    DeleteBehavior
    -0.47
    MemoryWarning
    -0.46
     nahilalakip
    -0.44
    RetentionPolicy
    -0.44
    POSITIVE LOGITS
     unknownFields
    0.63
     HasFactory
    0.63
    RenderAtEndOf
    0.59
     '\\;'
    0.57
    出版年
    0.55
    ContentView
    0.55
     tape
    0.52
    +#+
    0.52
    ByExample
    0.51
     समीक्षक
    0.51
    Act Density 0.266%

    No Known Activations