INDEX
    Explanations

    technical descriptions

    The neuron fires on descriptive technical terms that specify physical or material properties (e.g. bulkiness, energy input, airflow, high, large, thin).

    New Auto-Interp
    Negative Logits
    quotelev
    -0.07
    Ell
    -0.07
    elivery
    -0.06
    wright
    -0.06
    Bound
    -0.06
     cvs
    -0.06
    	io
    -0.06
     INSTALL
    -0.06
     lyrics
    -0.06
    obook
    -0.06
    POSITIVE LOGITS
     dys
    0.07
    άλ
    0.07
    ีส
    0.07
     accompany
    0.07
     моря
    0.06
    ắm
    0.06
    inars
    0.06
    ัดการ
    0.06
     Span
    0.06
    ASSES
    0.06
    Act Density 0.110%

    No Known Activations