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

    Neuronpedia

    INDEX
    Explanations

    names of people followed by a verb in past or future tense

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.62
     Brill
    -0.62
     Relative
    -0.61
    Downloadha
    -0.59
     Artificial
    -0.59
     Household
    -0.59
     preserves
    -0.57
     Pract
    -0.57
    values
    -0.56
    ractical
    -0.56
    POSITIVE LOGITS
     gladly
    0.95
    've
    0.93
     suffice
    0.91
     be
    0.90
     doubtless
    0.90
    apest
    0.88
     later
    0.87
    othy
    0.85
     wander
    0.85
     eventually
    0.84
    Act Density 0.137%

    No Known Activations