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

    Neuronpedia

    INDEX
    Explanations

    terms related to societal constructs and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ileged
    -0.20
    Ø©
    -0.20
    lopedia
    -0.19
    thing
    -0.18
    ãģĤãģ£ãģŁ
    -0.17
    ippet
    -0.17
    thon
    -0.17
    sburg
    -0.17
    tures
    -0.17
    ãĥ³
    -0.17
    POSITIVE LOGITS
    quarters
    0.29
    bsites
    0.28
    adays
    0.28
    etheless
    0.27
    nger
    0.26
    tlement
    0.25
    atre
    0.24
    west
    0.23
    ropolitan
    0.22
    erior
    0.21
    Act Density 0.380%

    No Known Activations