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

    Neuronpedia

    INDEX
    Explanations

    instances of mathematical expressions or symbols, particularly those involving exponents or powers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     invokingState
    -0.84
     MenuView
    -0.79
     kaarangay
    -0.79
    SBATCH
    -0.75
     StringTokenizer
    -0.70
     MainAxisSize
    -0.69
    WebVitals
    -0.68
    SerializeField
    -0.67
    ніципа
    -0.67
    TestTools
    -0.66
    POSITIVE LOGITS
     sub
    0.50
    rovnik
    0.48
     Markle
    0.47
     Це
    0.47
    vis
    0.46
    dr
    0.46
     "
    0.44
     astore
    0.43
     bearbeitet
    0.43
    b
    0.43
    Act Density 0.006%

    No Known Activations