INDEX
    Explanations

    mentions of heat and heating-related concepts

    New Auto-Interp
    Negative Logits
    ites
    -0.17
    ing
    -0.17
    hood
    -0.16
    edes
    -0.15
    asca
    -0.15
    oz
    -0.15
     kin
    -0.15
    jour
    -0.15
    afia
    -0.15
    hed
    -0.14
    POSITIVE LOGITS
    stroke
    0.28
    lh
    0.25
    wave
    0.25
    waves
    0.19
    -transfer
    0.19
     transfer
    0.19
    illac
    0.17
    izontal
    0.17
    nad
    0.16
    transfer
    0.16
    Act Density 0.018%

    No Known Activations