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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the significance of a concept or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    érrez
    -0.55
    遇
    -0.55
    虚
    -0.47
    zh
    -0.45
     dụ
    -0.44
    虛
    -0.44
     Big
    -0.44
     big
    -0.44
     con
    -0.43
     incremental
    -0.42
    POSITIVE LOGITS
    Extension
    0.98
    ReusableCell
    0.97
    extension
    0.94
     importance
    0.90
    ParallelGroup
    0.86
    importance
    0.86
     extension
    0.82
     Extension
    0.79
     Importance
    0.77
    กัน
    0.76
    Act Density 0.060%

    No Known Activations