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

    Neuronpedia

    INDEX
    Explanations

    repeated sequences or patterns in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Gunn
    -0.82
     Haas
    -0.82
     McLaughlin
    -0.80
     HIL
    -0.77
    mathscr
    -0.76
     Hügel
    -0.75
    ist
    -0.73
    UIControlState
    -0.72
    ims
    -0.71
     Winaray
    -0.71
    POSITIVE LOGITS
    .---
    1.02
    //---
    0.90
     NDEBUG
    0.88
    — 
    0.86
    ("---
    0.85
     bookId
    0.85
    /*---
    0.85
    ---
    0.83
     doInBackground
    0.83
    etcode
    0.80
    Act Density 0.016%

    No Known Activations