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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions of confusion about understanding or reasoning

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

    asking why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.75
    Personensuche
    -0.66
     propOrder
    -0.63
     AssemblyTitle
    -0.58
    KURZBESCHREIBUNG
    -0.57
    endphp
    -0.56
     intptr
    -0.56
    parsedMessage
    -0.56
    cipe
    -0.52
    ariConfig
    -0.52
    POSITIVE LOGITS
     why
    0.49
    Why
    0.48
    竟
    0.47
    竟然
    0.47
     kenapa
    0.46
    为什么
    0.45
    为何
    0.45
     Why
    0.44
    why
    0.44
     warum
    0.43
    Act Density 0.069%

    No Known Activations