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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ".
    0.86
    :.
    0.76
    **.
    0.74
     diversos
    0.73
     berbagai
    0.72
     various
    0.70
     maraming
    0.69
    +.
    0.69
    .
    0.67
     yakni
    0.67
    POSITIVE LOGITS
    ؟
    2.62
    ?
    2.59
    ？
    2.37
    ?)
    2.35
    ?”
    2.27
    ?"
    2.25
    ?;
    2.21
    ?]
    2.21
    ?")
    2.15
    ]?
    2.15
    Act Density 1.989%

    No Known Activations