INDEX
    Explanations

    mentions of turtles or terms related to turtles

    New Auto-Interp
    Negative Logits
    Interstitial
    -0.89
    orship
    -0.76
     confir
    -0.76
    ãĥ¼ãĥĨ
    -0.74
    ãĥ¼ãĥ³
    -0.69
    trak
    -0.68
    interstitial
    -0.67
    âĸ¬
    -0.66
    Null
    -0.66
    Ľ
    -0.66
    POSITIVE LOGITS
    brates
    1.09
    brate
    1.05
     turtle
    1.03
     turtles
    1.01
    fish
    0.96
    face
    0.94
     Turtle
    0.91
     Turtles
    0.86
    ulic
    0.80
    weed
    0.79
    Act Density 0.024%

    No Known Activations