INDEX
    Explanations

    terms after specific words

    New Auto-Interp
    Negative Logits
     wier
    0.93
     schoon
    0.84
    清潔
    0.83
    t
    0.82
    들의
    0.81
    0.79
     bora
    0.79
     haline
    0.77
    此类
    0.75
    にい
    0.75
    POSITIVE LOGITS
     molecules
    0.95
     synthesizer
    0.93
     synthase
    0.89
     Molecules
    0.86
     stripes
    0.85
     dioxide
    0.83
     impairment
    0.82
     reagents
    0.82
    ativity
    0.82
     impairments
    0.81
    Act Density 0.877%

    No Known Activations