INDEX
    Explanations

    references to high temperatures and heat-related conditions

    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.66
    ramenta
    -0.41
     ProtoMessage
    -0.35
    ExtendWith
    -0.35
    PhysRevLett
    -0.35
    träge
    -0.34
    libat
    -0.33
    tagHelperRunner
    -0.33
    ARP
    -0.32
    wände
    -0.32
    POSITIVE LOGITS
     sweating
    0.83
     heat
    0.80
     cooling
    0.74
     hotter
    0.73
     sweat
    0.73
     Cooling
    0.72
    Cooling
    0.71
     overheating
    0.71
    🥵
    0.70
    0.69
    Act Density 0.159%

    No Known Activations