INDEX
    Explanations

    mentions of the name "Robert."

    New Auto-Interp
    Negative Logits
     whoſe
    -0.94
     Unwin
    -0.89
     Desai
    -0.87
     Dinah
    -0.85
     Cano
    -0.81
     becauſe
    -0.80
     ſhe
    -0.80
     ſhould
    -0.77
     يتيمه
    -0.77
     houſe
    -0.76
    POSITIVE LOGITS
     Robert
    1.75
    Robert
    1.57
     ROBERT
    1.44
     robert
    1.40
     Roberts
    1.39
    ROBERT
    1.31
    robert
    1.30
    Roberts
    1.19
     Rober
    1.15
     Bob
    1.07
    Act Density 0.096%

    No Known Activations