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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     drink
    0.49
     draining
    0.49
     so
    0.47
    ၤ
    0.47
     unpacking
    0.46
     fetched
    0.46
     liqueur
    0.46
     sipping
    0.46
     moyenne
    0.46
     lovely
    0.44
    POSITIVE LOGITS
    Objects
    0.50
     వ్యక్
    0.48
    verhalten
    0.45
    এর
    0.45
    todos
    0.45
    është
    0.45
     Опреде
    0.44
     Objects
    0.44
    т
    0.44
    ]^{
    0.43
    Act Density 0.001%

    No Known Activations