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

    Neuronpedia

    INDEX
    Explanations

    information related to events and announcements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vou
    -0.75
     discriminated
    -0.63
     employing
    -0.60
     dehuman
    -0.60
     coercive
    -0.60
    redited
    -0.59
     implanted
    -0.58
     discrim
    -0.58
    anchester
    -0.58
     biologically
    -0.58
    POSITIVE LOGITS
     countdown
    0.93
     festive
    0.80
     fireworks
    0.77
     festivities
    0.76
     kickoff
    0.76
     Recap
    0.75
    reetings
    0.75
     anticipation
    0.73
     celebration
    0.72
     PAX
    0.71
    Act Density 1.509%

    No Known Activations