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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proper conditions or instructions for effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     takk
    -0.35
    NewReader
    -0.34
    Reentrant
    -0.33
     ov
    -0.32
    ございます
    -0.32
     AssemblyCompany
    -0.32
     HIGH
    -0.31
     trail
    -0.31
     name
    -0.31
     tổng
    -0.31
    POSITIVE LOGITS
    ChildScrollView
    0.60
     uſed
    0.59
     Chriftian
    0.57
     <<<<<<<<<<<<<<
    0.56
     Económica
    0.54
    rungsseite
    0.54
     autorytatywna
    0.51
    :✨
    0.50
    RegressionTest
    0.49
     againſt
    0.48
    Act Density 0.851%

    No Known Activations