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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "smart" used in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.94
     Gough
    -0.92
     betweenstory
    -0.92
    SequentialGroup
    -0.90
    hedrals
    -0.86
    LayoutPanel
    -0.85
     InputDecoration
    -0.85
     HasFactory
    -0.84
    numerusform
    -0.82
    InjectAttribute
    -0.81
    POSITIVE LOGITS
     smart
    2.51
     Smart
    2.46
    smart
    2.33
    Smart
    2.29
     SMART
    2.01
     smarter
    1.88
    SMART
    1.87
     intelligent
    1.63
     smartly
    1.62
     smartest
    1.56
    Act Density 0.039%

    No Known Activations