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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     oneself
    0.83
    ≻
    0.71
     sucede
    0.68
    अन्य
    0.68
    অন্য
    0.67
    Iniciar
    0.66
     mergeddata
    0.66
     jederzeit
    0.65
    อยู่ใน
    0.64
     iniciar
    0.64
    POSITIVE LOGITS
     ಮಾತ್ರ
    0.70
     agus
    0.68
     with
    0.65
    ized
    0.65
    um
    0.64
    ificantly
    0.63
    ac
    0.63
     only
    0.62
     Penalty
    0.61
    arith
    0.61
    Act Density 0.000%

    No Known Activations