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

    Neuronpedia

    INDEX
    Explanations

    character sequences related to code and technical commands

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    wered
    -0.66
     VIDEOS
    -0.66
    ony
    -0.64
    uberty
    -0.62
     Aid
    -0.61
     Giul
    -0.60
    alky
    -0.60
    ahime
    -0.59
     Simone
    -0.58
     Democr
    -0.56
    POSITIVE LOGITS
    wcsstore
    1.10
    roots
    0.71
    nl
    0.65
    inet
    0.64
    nos
    0.63
    ÙĨ
    0.63
    \":
    0.63
    files
    0.62
    arty
    0.62
    intosh
    0.61
    Act Density 2.559%

    No Known Activations