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

    Neuronpedia

    INDEX
    Explanations

    repeated punctuation and symbolic patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     onCreateView
    -0.74
    NUMX
    -0.72
     aveug
    -0.70
    ########.
    -0.70
    REFERRED
    -0.69
    Obrázky
    -0.69
     للاسماء
    -0.68
    География
    -0.67
    ἶ
    -0.66
    cámara
    -0.66
    POSITIVE LOGITS
    PYX
    0.62
     typelib
    0.54
    Bearer
    0.54
     OSD
    0.50
    piecze
    0.49
     Beaucoup
    0.49
    いる
    0.48
     Taus
    0.48
    getMessage
    0.48
     Koran
    0.47
    Act Density 0.252%

    No Known Activations