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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to subversion and undermining authority or norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ions
    -0.18
    leon
    -0.17
    วà¸Ļ
    -0.15
    enberg
    -0.15
     dr
    -0.15
    ario
    -0.15
     Kot
    -0.14
     eagle
    -0.14
    .extensions
    -0.14
    lick
    -0.14
    POSITIVE LOGITS
    ersive
    0.21
     sub
    0.21
    =sub
    0.20
    [sub
    0.20
    verted
    0.19
    jug
    0.19
    standard
    0.19
     rosa
    0.19
    terr
    0.19
    (sub
    0.18
    Act Density 0.018%

    No Known Activations