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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political events and societal issues, particularly focusing on expressions of disenfranchisement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    expressions of feelings associated with disenfranchisement and social discomfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.05
    3:0.06
    4:0.04
    5:0.08
    6:0.03
    7:0.06
    8:0.32
    9:0.06
    10:0.12
    11:0.06
    Negative Logits
     endorsements
    -1.16
    atern
    -1.14
     surrog
    -1.10
     litter
    -1.10
     Yel
    -1.06
     raids
    -1.05
     counties
    -1.04
     alt
    -1.03
     conglomer
    -1.03
     gangs
    -1.02
    POSITIVE LOGITS
    raq
    1.33
    uko
    1.29
    GoldMagikarp
    1.27
    QUI
    1.23
    ��
    1.23
     happiest
    1.23
    ergic
    1.17
    lime
    1.16
    nah
    1.15
    amiliar
    1.15
    Act Density 0.075%

    No Known Activations