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

    Neuronpedia

    INDEX
    Explanations

    words indicating simplicity or lack of complexity

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    saraba
    -0.78
    uxxxx
    -0.77
     يتيمه
    -0.76
     nakalista
    -0.75
    aktery
    -0.74
     ویکی‌پدیا
    -0.70
    omiast
    -0.68
     InputDecoration
    -0.67
    ⓧ
    -0.66
    úrese
    -0.66
    POSITIVE LOGITS
    baomidou
    0.60
    utton
    0.58
    väg
    0.57
     comprim
    0.57
     []).
    0.57
    StrictEqual
    0.56
    zehn
    0.55
    苷
    0.53
    CommandHandler
    0.52
     Paulo
    0.52
    Act Density 0.080%

    No Known Activations