INDEX
    Explanations

    mentions of the name "Bob" and variations of it in different contexts

    bob and related phrases

    New Auto-Interp
    Negative Logits
    Dani
    -0.52
     Dani
    -0.49
     Kien
    -0.45
     TN
    -0.45
    Martina
    -0.44
     Envi
    -0.44
     TDA
    -0.44
    Vii
    -0.43
     TCA
    -0.43
    PHA
    -0.42
    POSITIVE LOGITS
     Bob
    2.14
    Bob
    2.11
     bob
    2.03
    bob
    1.91
     BOB
    1.70
    BOB
    1.68
     bobs
    1.55
     Bobo
    1.09
     bobina
    0.98
     Boba
    0.94
    Act Density 0.002%

    No Known Activations