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

    Neuronpedia

    INDEX
    Explanations

    references to masks and their political implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deniz
    -0.18
    ensen
    -0.17
    ipel
    -0.15
    CEED
    -0.15
    alse
    -0.15
    redentials
    -0.15
    atch
    -0.15
    istrovstvÃŃ
    -0.14
    aliz
    -0.14
    mant
    -0.14
    POSITIVE LOGITS
    rips
    0.15
    oux
    0.14
    iji
    0.14
    ous
    0.14
    815
    0.14
    quis
    0.13
    _dispatcher
    0.13
    685
    0.13
    akan
    0.13
    nez
    0.13
    Act Density 0.118%

    No Known Activations