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

    Neuronpedia

    INDEX
    Explanations

    phrases related to algorithms and their impact on individuals or society

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

    going beyond what is possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Concer
    -0.35
    Rüyada
    -0.34
    vec
    -0.33
    aren
    -0.32
    ARTER
    -0.32
    muer
    -0.32
    astéro
    -0.31
    buah
    -0.31
    target
    -0.31
    tum
    -0.30
    POSITIVE LOGITS
    httphttps
    0.75
     Signalez
    0.69
    IsMutable
    0.59
    
    0.57
    WriteTagHelper
    0.56
    ientras
    0.55
    0.54
     وتسجيلات
    0.54
    Caratteristiche
    0.54
     ब्रेकडाउन
    0.51
    Act Density 0.197%

    No Known Activations