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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names associated with politicians or political entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.06
    3:0.06
    4:0.06
    5:0.03
    6:0.43
    7:0.04
    8:0.04
    9:0.06
    10:0.07
    11:0.05
    Negative Logits
    MSN
    -1.52
    ERY
    -1.34
    icides
    -1.34
    anwhile
    -1.27
    tumblr
    -1.25
    abouts
    -1.25
    nels
    -1.24
    conn
    -1.22
    BUG
    -1.21
    MX
    -1.18
    POSITIVE LOGITS
    lique
    1.50
    ��
    1.30
    ciating
    1.27
    ample
    1.19
    VIDIA
    1.17
    bery
    1.16
     agre
    1.16
    bender
    1.16
    pson
    1.11
     rall
    1.11
    Act Density 0.001%

    No Known Activations