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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     disruptive
    -0.55
    ulhu
    -0.53
     reliability
    -0.52
     accuracy
    -0.51
     Dickinson
    -0.51
     fingerprint
    -0.51
     antiv
    -0.50
     adherent
    -0.49
     dece
    -0.49
     revealing
    -0.49
    POSITIVE LOGITS
    tra
    0.70
    Tra
    0.66
    know
    0.62
    Town
    0.62
    series
    0.61
    shaped
    0.61
    adic
    0.59
    Phones
    0.59
    san
    0.59
    Capital
    0.58
    Act Density 15.446%

    No Known Activations