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

    Neuronpedia

    INDEX
    Explanations

    information and statements related to current events, politics, and news

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     converted
    -0.68
     unsuspecting
    -0.67
     mosqu
    -0.66
     Cyp
    -0.64
     hooked
    -0.60
     misunderstood
    -0.59
     poisoned
    -0.59
    anus
    -0.58
     dated
    -0.57
    429
    -0.56
    POSITIVE LOGITS
    ³³³
    0.91
    Prev
    0.79
    Bloomberg
    0.77
    FORE
    0.76
    ³³³³³³³³
    0.75
    Earlier
    0.74
    Fans
    0.74
    Speaking
    0.72
    Reuters
    0.72
    Labour
    0.72
    Act Density 0.034%

    No Known Activations