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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences and their formatting

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     (
    -0.72
     "
    -0.69
     .
    -0.66
      
    -0.64
     T
    -0.63
     $
    -0.63
     D
    -0.63
     <
    -0.63
     S
    -0.62
     The
    -0.60
    POSITIVE LOGITS
     Efq
    1.63
     Majefty
    1.41
     Theſe
    1.37
     myſelf
    1.32
     Anſ
    1.31
     Monfieur
    1.31
     itſelf
    1.29
     Jefus
    1.28
     fevere
    1.26
     Eſ
    1.23
    Act Density 0.059%

    No Known Activations