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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names, specifically last names but may include any kind of names

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    coni
    -0.70
    rower
    -0.68
     ejac
    -0.67
     ende
    -0.67
    kefeller
    -0.66
    berman
    -0.65
    opausal
    -0.65
     disproportionate
    -0.65
    iltration
    -0.64
    stros
    -0.63
    POSITIVE LOGITS
    atchewan
    1.43
    ansas
    1.06
    atoon
    1.05
     Rapids
    1.05
    edIn
    1.01
    aign
    0.97
    oln
    0.97
    ings
    0.89
    erness
    0.89
    erville
    0.89
    Act Density 0.927%

    No Known Activations