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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "So" as a transition or emphasis in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    introduces questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.46
    SuccessListener
    -0.43
     AssemblyVersion
    -0.43
    MergeFrom
    -0.41
     Lijst
    -0.40
    setViewName
    -0.39
     """",
    -0.39
    Pozdrawiam
    -0.37
    saurus
    -0.36
    Fernsehserie
    -0.36
    POSITIVE LOGITS
     why
    0.77
     mengapa
    0.60
     how
    0.60
    why
    0.57
     WHY
    0.56
     hvorfor
    0.56
     dlaczego
    0.56
     क्यों
    0.55
     waarom
    0.55
     pourquoi
    0.52
    Act Density 0.034%

    No Known Activations