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

    Neuronpedia

    INDEX
    Explanations

    quotes or speech marks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.73
     Mans
    -0.71
    ில்
    -0.66
    ة
    -0.66
    GENERIC
    -0.65
    льки
    -0.65
    oustics
    -0.62
     Heraus
    -0.61
    лоди
    -0.61
     S
    -0.60
    POSITIVE LOGITS
     Compagn
    0.85
     themſelves
    0.85
     referenties
    0.78
     '`
    0.75
     pleaſure
    0.73
     SWIG
    0.73
     Efq
    0.73
     habitudes
    0.72
     ویکی‌آمباردا
    0.71
     pngtree
    0.70
    Act Density 0.037%

    No Known Activations