INDEX
    Explanations

    phrases and descriptions that evoke strong sensory experiences and emotions

    New Auto-Interp
    Negative Logits
    iek
    -0.16
    rouch
    -0.15
    ett
    -0.15
    elman
    -0.14
     eff
    -0.14
    ÑĥÑĢа
    -0.14
    èĸ
    -0.14
     damp
    -0.14
    cess
    -0.13
    ÎŃÏģ
    -0.13
    POSITIVE LOGITS
    amat
    0.16
    oldt
    0.16
     EXPER
    0.15
    ξι
    0.14
    بات
    0.14
    ppv
    0.14
    esium
    0.14
     feeling
    0.14
    eel
    0.13
    Ïģιο
    0.13
    Act Density 0.204%

    No Known Activations