Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to physical injuries and medical incidents

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ulhu
    -0.90
     Richards
    -0.83
     Lanka
    -0.70
     Ell
    -0.69
     Claus
    -0.67
    esson
    -0.67
     Kern
    -0.66
     Borders
    -0.65
     Phi
    -0.65
    ãģ®éŃĶ
    -0.65
    POSITIVE LOGITS
    based
    1.22
    sized
    1.16
    operated
    1.15
    tested
    1.13
    saving
    1.12
    driven
    1.08
    to
    1.06
    themed
    1.06
    intensive
    1.03
    produced
    1.02
    Act Density 9.255%

    No Known Activations