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

    Neuronpedia

    INDEX
    Explanations

    email promotions and newsletters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    naire
    -0.59
    ilion
    -0.58
    bara
    -0.58
    _>
    -0.56
    llan
    -0.56
     largeDownload
    -0.54
    Rule
    -0.54
    auga
    -0.54
     disappearance
    -0.54
     brut
    -0.54
    POSITIVE LOGITS
     POLITICO
    0.79
    bleacher
    0.74
    ivably
    0.68
    independent
    0.67
     subscribing
    0.61
    ivered
    0.60
    taboola
    0.60
     Hels
    0.60
    rex
    0.59
    Dispatch
    0.59
    Act Density 0.019%

    No Known Activations