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

    Neuronpedia

    INDEX
    Explanations

    people who are involved in legal or political situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ."<
    -0.70
    ."\
    -0.68
    ,'\
    -0.62
    )+"
    -0.60
    ."/
    -0.60
    +".
    -0.59
    .'</
    -0.58
    +"_
    -0.57
     tiks
    -0.57
    Cursors
    -0.56
    POSITIVE LOGITS
     encomp
    1.30
     intersper
    1.23
     emphat
    1.22
     depic
    1.18
     disagre
    1.13
     unspeak
    1.12
     inev
    1.09
     affor
    1.09
     increa
    1.07
     reluct
    1.06
    Act Density 0.167%

    No Known Activations