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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    the
    0.96
    You
    0.91
    on
    0.88
    I
    0.87
    you
    0.85
    in
    0.83
    ून
    0.78
    an
    0.76
    force
    0.76
    to
    0.74
    POSITIVE LOGITS
     experiências
    0.82
     experiencias
    0.81
    ுக
    0.79
     aldrig
    0.75
    น้อย
    0.74
    >+</
    0.74
    铵
    0.73
     စ
    0.73
    pciones
    0.72
     Musik
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.