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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strong opinions or stances on political or social issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    amera
    -0.76
    arations
    -0.71
    ovember
    -0.71
    umm
    -0.71
    ĸļ
    -0.70
     tallest
    -0.70
    alli
    -0.69
    pler
    -0.68
    pty
    -0.68
    otation
    -0.68
    POSITIVE LOGITS
     gamers
    0.86
     Islamists
    0.83
     adherent
    0.80
     adherents
    0.80
     enthusiasts
    0.79
     warriors
    0.77
     Gamer
    0.77
     believers
    0.76
     hardcore
    0.75
    doms
    0.75
    Act Density 0.064%

    No Known Activations