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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Transition
    0.62
    P
    0.60
    Dynamic
    0.57
    State
    0.55
    Single
    0.54
    G
    0.54
    Action
    0.52
    Third
    0.52
     \
    0.52
    Optional
    0.51
    POSITIVE LOGITS
     embold
    0.52
     memperbaiki
    0.49
     विषया
    0.49
     accedi
    0.49
     corpses
    0.48
     accredited
    0.48
     verified
    0.48
    ವೆ
    0.47
     সম্পর্
    0.47
    谄
    0.47
    Act Density 0.005%

    No Known Activations