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

    Neuronpedia

    INDEX
    Explanations

    phrases related to concerns and reasoning within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }{*}{
    -0.51
    setViewportView
    -0.51
     non
    -0.50
    latform
    -0.49
    CppMethod
    -0.49
    OCCURRED
    -0.49
    beiten
    -0.48
     ikke
    -0.48
    ----</
    -0.48
    UrlResolution
    -0.48
    POSITIVE LOGITS
    而是
    1.24
     بلکه
    1.17
     sondern
    1.06
     melainkan
    0.80
     אלא
    0.79
     vaan
    0.75
     يتيمه
    0.63
    BeginInit
    0.63
     للاسماء
    0.63
     vielmehr
    0.62
    Act Density 0.238%

    No Known Activations