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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     appart
    0.49
     upper
    0.49
     spying
    0.46
     ability
    0.45
    polling
    0.45
     étudier
    0.44
     polling
    0.44
     revolutionize
    0.43
     estudia
    0.43
     invite
    0.42
    POSITIVE LOGITS
    lossen
    0.50
    麂
    0.48
     πιο
    0.46
    絮
    0.46
     parcialmente
    0.46
     לאחר
    0.45
    utables
    0.45
    izoen
    0.44
    ISON
    0.43
    మిక
    0.43
    Act Density 0.000%

    No Known Activations