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

    Neuronpedia

    INDEX
    Explanations

    mentions of criminal records and legal situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    atible
    -0.68
    paralle
    -0.62
     menstrual
    -0.61
     similarities
    -0.59
    estial
    -0.59
    iencies
    -0.59
     totality
    -0.57
    bol
    -0.57
    some
    -0.56
    otal
    -0.56
    POSITIVE LOGITS
     sarcast
    0.90
     diplom
    0.87
     rhet
    0.86
     said
    0.83
     bluntly
    0.82
    said
    0.80
    .
    0.79
     quoted
    0.79
     paraph
    0.76
     adding
    0.75
    Act Density 2.911%

    No Known Activations