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

    Neuronpedia

    INDEX
    Explanations

    elements related to object-oriented programming and data structure definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.96
    ########.
    -0.91
     nahilalakip
    -0.90
    MessageTagHelper
    -0.89
     виправивши
    -0.88
     kasarigan
    -0.88
     betweenstory
    -0.85
    __':
    -0.85
    adaptiveStyles
    -0.83
    rungsseite
    -0.82
    POSITIVE LOGITS
     black
    0.29
     latein
    0.28
     emperador
    0.28
     Kirchen
    0.28
     estrada
    0.28
    miş
    0.26
     extrême
    0.26
    ↵↵
    0.26
     dramatique
    0.26
     Espíritu
    0.25
    Act Density 0.944%

    No Known Activations