INDEX
    Explanations

    words related to wood or wooden materials

    New Auto-Interp
    Negative Logits
    uberty
    -0.74
    VICE
    -0.67
     aver
    -0.67
    orsche
    -0.66
    ochet
    -0.66
    ansky
    -0.66
     Fren
    -0.65
    oresc
    -0.65
     Sunshine
    -0.64
     Merkel
    -0.63
    POSITIVE LOGITS
    working
    1.05
     pulp
    1.04
    \\\\\\\\
    1.02
    ruff
    0.96
    wood
    0.96
    blocks
    0.95
    worker
    0.95
    work
    0.93
     wood
    0.91
    wind
    0.90
    Act Density 0.019%

    No Known Activations