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

    Neuronpedia

    INDEX
    Explanations

    words related to proper nouns and titles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    autical
    -0.70
     departures
    -0.68
    olves
    -0.67
    alities
    -0.65
    products
    -0.64
    iculture
    -0.64
    ews
    -0.63
    acion
    -0.61
    interstitial
    -0.61
    ancial
    -0.61
    POSITIVE LOGITS
     meanwhile
    1.14
     alas
    1.09
     incidentally
    1.05
     however
    0.98
     huh
    0.94
     moreover
    0.93
     bless
    0.90
     unsurprisingly
    0.88
     aka
    0.85
     beware
    0.84
    Act Density 0.289%

    No Known Activations