INDEX
    Explanations

    mentions of the name "Malcolm" and its variations in different contexts

    New Auto-Interp
    Negative Logits
    à¸Ļะ
    -0.16
    illon
    -0.15
    phony
    -0.14
    çĸ¾
    -0.14
    roke
    -0.14
    roll
    -0.14
    moz
    -0.14
    eton
    -0.14
    ddy
    -0.14
    evil
    -0.14
    POSITIVE LOGITS
     mal
    0.20
    colm
    0.20
     Mal
    0.19
    ucene
    0.18
     MAL
    0.18
    Lint
    0.17
     afore
    0.17
    strom
    0.17
    Mal
    0.17
    ontent
    0.17
    Act Density 0.033%

    No Known Activations