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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Universidad
    0.94
    ال
    0.93
    Other
    0.90
    other
    0.88
    Fract
    0.87
    Tert
    0.87
    Agregar
    0.87
    ०
    0.86
    Miscellaneous
    0.86
    Observations
    0.86
    POSITIVE LOGITS
     begins
    0.90
     deflection
    0.90
     exemplifies
    0.89
     surpassing
    0.88
     specifically
    0.86
     explains
    0.86
     begin
    0.84
     cradle
    0.84
     reject
    0.84
     🥰
    0.84
    Act Density 0.785%

    No Known Activations