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

    Neuronpedia

    INDEX
    Explanations

    absolute terms of certainty and knowledge

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     indestru
    -0.78
     accla
    -0.75
     reluct
    -0.75
     indescri
    -0.74
     intrigu
    -0.71
     nobly
    -0.69
     inconce
    -0.67
     gaily
    -0.66
     strto
    -0.66
     unspeak
    -0.66
    POSITIVE LOGITS
    <bos>
    0.93
     fidanz
    0.89
     siquiera
    0.84
    even
    0.71
     even
    0.69
     EVEN
    0.69
    Même
    0.67
    EVEN
    0.61
     cammin
    0.59
     parteci
    0.59
    Act Density 0.118%

    No Known Activations