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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ripcion
    0.38
     शख्स
    0.37
     indictment
    0.37
    庤
    0.37
     Typ
    0.36
     PPC
    0.36
     thematic
    0.36
    押
    0.35
    utlich
    0.35
     sta
    0.35
    POSITIVE LOGITS
    usakan
    0.50
     appealed
    0.45
     hadden
    0.43
    mlp
    0.43
     removes
    0.40
    went
    0.40
     resuelve
    0.40
    რავ
    0.40
    Had
    0.40
     manhã
    0.39
    Act Density 0.003%

    No Known Activations