INDEX
    Explanations

    references to animals in a predatory context

    references to "prey" and its various contexts in relation to feeding behavior

    New Auto-Interp
    Negative Logits
    aan
    -0.75
    andro
    -0.65
     MX
    -0.65
     provisional
    -0.64
     Kubrick
    -0.62
     PRESIDENT
    -0.61
    ados
    -0.61
     McKenna
    -0.61
    essa
    -0.60
    ocal
    -0.59
    POSITIVE LOGITS
     prey
    1.02
     vanquished
    0.79
    fish
    0.78
     predators
    0.76
    ele
    0.75
     predator
    0.72
     Horses
    0.71
    ãĤ¼ãĤ¦ãĤ¹
    0.70
    emouth
    0.70
    brates
    0.69
    Act Density 0.011%

    No Known Activations