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

    Neuronpedia

    INDEX
    Explanations

    references to relationships and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Win
    -0.17
    est
    -0.15
    iable
    -0.14
    resh
    -0.14
    ess
    -0.14
    ãĥIJãĥ¼
    -0.14
    imit
    -0.14
    ammed
    -0.14
    ote
    -0.13
     Requires
    -0.13
    POSITIVE LOGITS
    anine
    0.18
     DISCLAIM
    0.16
     tane
    0.16
    $MESS
    0.15
    AREST
    0.15
    icaid
    0.15
    دÛĮگر
    0.14
    byt
    0.14
    bens
    0.14
    зÑĮ
    0.14
    Act Density 0.144%

    No Known Activations