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

    Neuronpedia

    INDEX
    Explanations

    programming-related elements and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.79
     ujednoznacz
    -0.71
     للاسماء
    -0.68
     ſich
    -0.68
     Weiſe
    -0.65
     jspb
    -0.63
     beſte
    -0.62
     ſei
    -0.62
     препратки
    -0.61
     ब्रेकडाउन
    -0.61
    POSITIVE LOGITS
    ↵
    0.63
    </code>
    0.58
    ↵↵↵
    0.50
    
    0.48
    ↵↵
    0.47
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.46
    </blockquote>
    0.46
    
    0.45
    ↵↵↵↵↵↵↵↵↵
    0.43
    ↵↵↵↵
    0.43
    Act Density 0.865%

    No Known Activations