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

    Neuronpedia

    INDEX
    Explanations

    scientific measurements and units of measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Resili
    -0.52
    razio
    -0.51
     FormsModule
    -0.47
     Cruelty
    -0.47
     Exploitation
    -0.47
    illett
    -0.47
    ={<
    -0.46
     дописавши
    -0.46
     Subsid
    -0.45
    geln
    -0.45
    POSITIVE LOGITS
    0.75
    awtextra
    0.65
     <=",
    0.64
     otomatig
    0.62
     ***!
    0.60
    kháu
    0.58
     kasarigan
    0.56
    shire
    0.56
     ModelRenderer
    0.56
     "..\..\..\
    0.55
    Act Density 0.416%

    No Known Activations