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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific characters or symbols

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.91
    /**
    -0.88
     &___
    -0.84
    contentLoaded
    -0.83
     MonoBehaviour
    -0.83
    abestanden
    -0.81
    AsUp
    -0.79
    "]);
    -0.79
     Audiodateien
    -0.78
    Ārējās
    -0.78
    POSITIVE LOGITS
     [
    0.59
     ...
    0.54
    ...
    0.54
    box
    0.51
    section
    0.50
    yttö
    0.49
     (
    0.48
    tuig
    0.47
     
    0.47
    subsubsection
    0.45
    Act Density 0.009%

    No Known Activations