INDEX
    Explanations

    control over / dive into / focus on

    New Auto-Interp
    Negative Logits
    한테
    0.84
    padă
    0.79
     كلهم
    0.75
    <unused90>
    0.74
    𝓾
    0.73
    一脸
    0.73
    accay
    0.73
    льному
    0.73
     jaoks
    0.72
     novedad
    0.72
    POSITIVE LOGITS
     regarding
    1.20
     concerning
    0.97
     towards
    0.96
     toward
    0.92
    regarding
    0.85
     Regarding
    0.82
     surrounding
    0.79
     both
    0.79
    Regarding
    0.77
     not
    0.75
    Act Density 0.368%

    No Known Activations