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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    speak
    -1.02
    ^(@)
    -0.95
    SourceChecksum
    -0.93
    Према
    -0.91
     speak
    -0.91
    discuss
    -0.91
     talk
    -0.90
     odkazy
    -0.89
     Monfieur
    -0.88
     purpoſe
    -0.88
    POSITIVE LOGITS
     []:
    0.33
     sü
    0.32
     mathvariant
    0.31
    TH
    0.30
     Bourgoin
    0.29
    #!/
    0.29
    ải
    0.28
    kheim
    0.28
                              
    0.28
    dec
    0.28
    Act Density 0.000%

    No Known Activations