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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities or measurements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     impra
    -2.05
     shenan
    -1.88
     increa
    -1.86
     unspeak
    -1.85
     indescri
    -1.81
     disreg
    -1.80
     affor
    -1.79
     indestru
    -1.78
     reluct
    -1.77
     gaily
    -1.75
    POSITIVE LOGITS
    <bos>
    0.88
     years
    0.86
     decade
    0.82
     months
    0.80
     decades
    0.78
     weeks
    0.77
     Baillargeon
    0.74
     Jahren
    0.73
    years
    0.72
    decade
    0.71
    Act Density 0.093%

    No Known Activations