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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing doubt or uncertainty

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.80
    options
    -0.74
    Rated
    -0.74
    apest
    -0.72
    gard
    -0.70
    oulder
    -0.70
    ruciating
    -0.69
    Zone
    -0.68
    ideshow
    -0.68
    phabet
    -0.66
    POSITIVE LOGITS
     origin
    0.88
     faked
    0.87
     coincidence
    0.87
     possibly
    0.86
     culprit
    0.86
     intentional
    0.84
     motives
    0.83
     subconscious
    0.83
     mistaken
    0.83
     deliberate
    0.82
    Act Density 0.919%

    No Known Activations