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

    Neuronpedia

    INDEX
    Explanations

    historical and biographical information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.79
    @[+][
    -0.66
    ))){
    -0.65
    )))));
    -0.64
    PCell
    -0.64
    .’
    -0.62
    </h1>
    -0.62
    .”
    -0.62
    ])).
    -0.61
    .“
    -0.60
    POSITIVE LOGITS
     shenan
    1.56
     scrat
    1.53
     indestru
    1.51
     unspeak
    1.49
     inconce
    1.44
     reluct
    1.44
     cushi
    1.43
     increa
    1.42
     hairc
    1.42
     disreg
    1.40
    Act Density 0.886%

    No Known Activations