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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     might
    -1.05
     may
    -0.95
     acquistare
    -0.92
    だね
    -0.89
    お待ち
    -0.88
    may
    -0.88
     will
    -0.86
     forgotten
    -0.85
    ществ
    -0.85
    itemize
    -0.84
    POSITIVE LOGITS
     uwagi
    1.00
    Theres
    1.00
     prome
    0.95
    theres
    0.94
    gucci
    0.94
    îr
    0.92
    oq
    0.91
    architecte
    0.91
     potenci
    0.91
     desn
    0.91
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.