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

    Neuronpedia

    INDEX
    Explanations

    terms related to experimental dropout and related statistical measurements

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

    Dropout and Tween

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.76
     utafitiHapana
    -0.74
    ThroughAttribute
    -0.71
    ResponseWriter
    -0.68
    httphttps
    -0.65
     enfans
    -0.63
    
    -0.60
    ſicht
    -0.60
     EconPapers
    -0.60
     createSlice
    -0.59
    POSITIVE LOGITS
    Dropout
    1.09
    dropout
    0.95
     Dropout
    0.83
     dropout
    0.58
     probab
    0.37
    朋
    0.37
     Drou
    0.36
    drop
    0.35
     during
    0.33
     Smoking
    0.33
    Act Density 0.008%

    No Known Activations