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

    Neuronpedia

    INDEX
    Explanations

    characters and roles related to activism and social justice themes in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.14
    3:0.17
    4:0.11
    5:0.03
    6:0.02
    7:0.05
    8:0.04
    9:0.08
    10:0.13
    11:0.13
    Negative Logits
     confir
    -1.57
    Semitism
    -1.43
    Sov
    -1.40
    76561
    -1.35
    ��
    -1.33
    …)
    -1.32
    reports
    -1.32
    euro
    -1.30
     agre
    -1.29
     therap
    -1.26
    POSITIVE LOGITS
     respectively
    1.27
     famed
    1.19
     midway
    1.14
     Bent
    1.12
     Calvin
    1.10
     effortlessly
    1.08
     Lenn
    1.07
     villain
    1.06
     mash
    1.06
     standout
    1.05
    Act Density 0.042%

    No Known Activations