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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    也不能
    0.60
     nějak
    0.56
     suivants
    0.55
     valam
    0.55
    但是我
    0.53
    normally
    0.51
     někter
    0.51
    None
    0.50
    または
    0.49
    看向
    0.49
    POSITIVE LOGITS
     empowers
    1.05
     Unlike
    1.00
     think
    0.99
     Think
    0.99
     boasts
    0.98
     fosters
    0.98
     questo
    0.96
    Think
    0.95
     exemplifies
    0.94
     embodies
    0.93
    Act Density 3.099%

    No Known Activations