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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cyclone
    1.11
    abandon
    1.06
     jealousy
    1.03
     けど
    1.03
    ayeva
    1.02
     manslaughter
    1.00
     malicious
    0.98
    riya
    0.98
     trauma
    0.98
     harassment
    0.97
    POSITIVE LOGITS
    ált
    1.02
    芃
    0.86
    ബ്രുവരി
    0.86
    ፴
    0.86
     Substituting
    0.85
    ടു
    0.84
    }[!
    0.84
     таки
    0.83
     Employ
    0.82
     Recent
    0.81
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.