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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and their components related to equations and formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zwiebel
    -0.71
     fubject
    -0.71
    ugier
    -0.65
     Streit
    -0.65
    存于互联网档案馆
    -0.60
    Canyon
    -0.60
     Stoff
    -0.60
     Kommune
    -0.59
     Nusantara
    -0.59
    səhifə
    -0.58
    POSITIVE LOGITS
    {\
    0.86
     {\
    0.83
    (\
    0.81
    _{\
    0.79
    )_{\
    0.75
     (\
    0.72
     [\
    0.71
     $(\
    0.71
    [\
    0.69
     {{\
    0.69
    Act Density 0.620%

    No Known Activations