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

    Neuronpedia

    INDEX
    Explanations

    words related to chemistry and biology including chemical reactions, substances, and bodily functions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     categ
    -0.71
     Partnership
    -0.68
     Advent
    -0.68
     endorsement
    -0.66
     Creed
    -0.65
     Lithuan
    -0.65
     reservation
    -0.64
     tenure
    -0.64
     Improvement
    -0.64
     Wanted
    -0.64
    POSITIVE LOGITS
     stimulates
    1.07
     contam
    1.05
     contamin
    1.02
     then
    1.02
     causes
    1.01
     eventually
    0.97
     wre
    0.95
     deposited
    0.95
     destroys
    0.95
     emits
    0.94
    Act Density 0.539%

    No Known Activations