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

    Neuronpedia

    INDEX
    Explanations

    specific symbols or characters indicative of categorization or emphasis in written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kuala
    -0.19
     Melbourne
    -0.18
     Malaysian
    -0.16
     Bahrain
    -0.16
     Monaco
    -0.15
     Montreal
    -0.15
    PMC
    -0.15
    ustralian
    -0.15
     proton
    -0.15
     Dubai
    -0.15
    POSITIVE LOGITS
     Iowa
    0.57
     Sioux
    0.36
     rural
    0.31
     Moines
    0.29
     Rural
    0.28
     Des
    0.27
     Haw
    0.27
     Cedar
    0.26
     Ames
    0.26
     Midwest
    0.25
    Act Density 0.003%

    No Known Activations