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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical pain, physical sensations, and physical actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    tesy
    -0.85
    ady
    -0.78
     volunte
    -0.72
    itional
    -0.72
    conservancy
    -0.71
    itionally
    -0.71
    icip
    -0.70
     advoc
    -0.70
    oubted
    -0.68
    odox
    -0.68
    POSITIVE LOGITS
     Whatever
    1.14
     Anything
    1.14
     Something
    1.10
     And
    1.07
     Everywhere
    1.06
     Anyway
    1.04
     Everything
    1.03
     Everybody
    1.01
     Nothing
    1.00
     Nobody
    1.00
    Act Density 7.806%

    No Known Activations