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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     contributes
    -0.36
     vra
    -0.35
     contribution
    -0.34
     taught
    -0.34
    Notae
    -0.34
    lauf
    -0.33
     tearing
    -0.33
     טע
    -0.33
     contributions
    -0.33
    iz
    -0.32
    POSITIVE LOGITS
     خارجية
    6.00
     esterni
    1.51
     externes
    1.16
     חיצוניים
    1.15
     الخارجية
    1.13
     esternos
    1.13
     lenker
    1.06
     External
    1.05
     externas
    1.04
    External
    1.00
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.