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

    Neuronpedia

    INDEX
    Explanations

    sections of text with high frequency of blank spaces or indentation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.81
    Datuak
    -0.76
    principalColumn
    -0.74
     فريبيس
    -0.73
     चीज़ों
    -0.72
     EconPapers
    -0.69
     Infórmanos
    -0.69
     AssemblyTitle
    -0.68
     cherchés
    -0.68
     Baillargeon
    -0.67
    POSITIVE LOGITS
    साय
    0.50
    ampunk
    0.49
    Brend
    0.49
    passphrase
    0.48
     nek
    0.48
     WS
    0.47
     terp
    0.46
     planètes
    0.46
    UrlResolution
    0.45
    educ
    0.45
    Act Density 0.001%

    No Known Activations