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

    Neuronpedia

    INDEX
    Explanations

    complex mathematical expressions and symbols

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    valently
    -0.84
    cheiben
    -0.79
     /\.(
    -0.78
     Kers
    -0.74
     azy
    -0.74
     Magellan
    -0.73
     ➢
    -0.73
     MonoBehaviour
    -0.71
    WithIOException
    -0.71
    ing
    -0.71
    POSITIVE LOGITS
    }_{
    0.86
    alba
    0.75
     cun
    0.73
    ########.
    0.71
    ➷
    0.71
    fjspx
    0.70
    gridx
    0.66
    ↵↵↵
    0.66
     STEIN
    0.66
    Caprio
    0.65
    Act Density 0.094%

    No Known Activations