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

    Neuronpedia

    INDEX
    Explanations

    complicated mathematical expressions and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -1.01
    rungsseite
    -1.00
    MessageTagHelper
    -0.92
    adaptiveStyles
    -0.89
     BoxFit
    -0.87
     resourceCulture
    -0.85
    ロウィン
    -0.81
     fubject
    -0.81
    InstrumentedTest
    -0.81
     يتيمه
    -0.80
    POSITIVE LOGITS
     
    0.51
    1
    0.39
    3
    0.37
    2
    0.36
    us
    0.36
     =
    0.36
    -
    0.35
    4
    0.35
    .
    0.34
    ada
    0.34
    Act Density 1.240%

    No Known Activations