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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ation
    1.13
    یت
    1.11
    curl
    1.11
    er
    1.10
    estimator
    1.04
    H
    1.03
    V
    1.02
    earch
    1.01
    istance
    1.00
    bé
    0.98
    POSITIVE LOGITS
     snare
    1.50
     grotes
    1.39
     sinusitis
    1.38
    1.36
     ganó
    1.28
    1.25
     catwalk
    1.25
     Arvind
    1.25
     estaba
    1.25
    ために
    1.25
    Act Density 0.000%

    No Known Activations