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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.94
    iſen
    -0.85
     ſind
    -0.82
     purpoſe
    -0.81
     ſever
    -0.80
    SequentialGroup
    -0.78
     ſche
    -0.78
     betweenstory
    -0.77
     uſe
    -0.77
     pleaſure
    -0.77
    POSITIVE LOGITS
    s
    1.63
     own
    0.75
     s
    0.75
     his
    0.75
    S
    0.69
     His
    0.66
    His
    0.65
    ys
    0.62
     its
    0.59
     
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.