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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contradiction or opposing viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    introducing contrasting ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.75
    enderror
    -0.55
    MemoryWarning
    -0.54
     Theſe
    -0.52
    Personensuche
    -0.52
    iffance
    -0.52
    httphttps
    -0.51
    ⟬
    -0.50
    তথ্যসূত্র
    -0.50
    RenderAtEndOf
    -0.50
    POSITIVE LOGITS
     наоборот
    1.00
     justru
    0.79
     contraire
    0.79
     juist
    0.75
    相反
    0.75
     opposite
    0.73
    逆に
    0.72
     sebaliknya
    0.70
    むしろ
    0.70
     conversely
    0.68
    Act Density 0.037%

    No Known Activations