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

    Neuronpedia

    INDEX
    Explanations

    percentages and numbers in the context of political polls

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     flakes
    -0.65
     overcl
    -0.61
     withdrawals
    -0.61
     cracks
    -0.60
     traveller
    -0.60
     Donation
    -0.58
     invocation
    -0.58
     tones
    -0.57
     postage
    -0.56
    pict
    -0.56
    POSITIVE LOGITS
    ggles
    1.09
     commemorate
    1.00
     satisfy
    0.97
     accommodate
    0.93
     signify
    0.93
     celebrate
    0.92
    wered
    0.91
     appease
    0.89
     compensate
    0.88
     coincide
    0.85
    Act Density 0.226%

    No Known Activations