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

    Neuronpedia

    INDEX
    Explanations

    numerical information and statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     encomp
    -1.21
     impra
    -1.19
     increa
    -1.18
     attemp
    -1.17
     erad
    -1.16
     depic
    -1.13
     affor
    -1.13
     maneu
    -1.12
     shenan
    -1.12
     inappro
    -1.10
    POSITIVE LOGITS
     luck
    0.87
    <bos>
    0.78
     happen
    0.76
     lucky
    0.71
     happened
    0.70
     circumstances
    0.70
     happens
    0.68
     happening
    0.67
     unexpected
    0.66
     fate
    0.63
    Act Density 0.625%

    No Known Activations