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

    Neuronpedia

    INDEX
    Explanations

    sentences that end in a period

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.83
     averages
    -0.78
     extinct
    -0.73
    thal
    -0.72
    soDeliveryDate
    -0.70
     dips
    -0.69
     selfie
    -0.68
    eatures
    -0.68
     shark
    -0.67
     bearer
    -0.67
    POSITIVE LOGITS
     Eventually
    1.48
     Suddenly
    1.47
     Soon
    1.37
     Then
    1.30
     Unable
    1.25
     Slowly
    1.25
     Instead
    1.25
     Fortunately
    1.23
     Within
    1.21
     Ultimately
    1.21
    Act Density 0.397%

    No Known Activations