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

    Neuronpedia

    INDEX
    Explanations

    instances of structured data or code-related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cleo
    -0.73
     Chrys
    -0.67
     ['./
    -0.65
     Griffith
    -0.64
    reamble
    -0.63
    prefab
    -0.63
    
    -0.62
     فريبيس
    -0.61
    énieur
    -0.61
     Shr
    -0.59
    POSITIVE LOGITS
    ↵↵
    0.86
    ↵↵↵↵
    0.78
     Besøkt
    0.78
    <h2>
    0.74
    rus
    0.72
    ↵↵↵↵↵
    0.72
    ↵↵↵↵↵↵
    0.69
    ↵↵↵
    0.67
    setVerticalGroup
    0.65
     azzurro
    0.64
    Act Density 0.199%

    No Known Activations