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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ‏:‏
    0.51
    centric
    0.50
    faceted
    0.49
    ː
    0.48
    phosphat
    0.48
     अभिव्य
    0.47
    zeption
    0.47
    burgh
    0.47
    0.47
     있어서
    0.46
    POSITIVE LOGITS
    if
    0.60
     If
    0.60
     if
    0.59
     questo
    0.56
     jika
    0.54
     nếu
    0.54
     This
    0.53
                        
    0.52
     если
    0.52
                
    0.51
    Act Density 0.000%

    No Known Activations