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

    Neuronpedia

    INDEX
    Explanations

    people or things shaking or trembling

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     envy
    -0.26
    EMP
    -0.26
    erva
    -0.26
     contrace
    -0.25
    ======
    -0.25
    umen
    -0.25
     Bravo
    -0.24
    HCR
    -0.23
    coni
    -0.23
     Skydragon
    -0.23
    POSITIVE LOGITS
    ed
    0.29
    orf
    0.25
    inx
    0.25
    eded
    0.24
    ijk
    0.23
    icz
    0.23
    edly
    0.23
    rown
    0.23
    ird
    0.22
    eding
    0.22
    Act Density 0.034%

    No Known Activations