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

    Neuronpedia

    INDEX
    Explanations

    dates, historical events, and figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     workaround
    -0.80
    anges
    -0.74
     sauces
    -0.72
    aimon
    -0.71
    usal
    -0.70
    onite
    -0.70
    arser
    -0.70
    erent
    -0.68
     prefers
    -0.68
    omorph
    -0.67
    POSITIVE LOGITS
     roared
    0.86
     celebrated
    0.84
     inaug
    0.84
     culmination
    0.83
     unforgettable
    0.82
     Congratulations
    0.81
     proclaimed
    0.81
     hailed
    0.81
     Massacre
    0.80
     PRESIDENT
    0.80
    Act Density 1.579%

    No Known Activations