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

    Neuronpedia

    INDEX
    Explanations

    words related to obligations or duties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onte
    -0.17
    илÑı
    -0.15
    ForObject
    -0.15
    ptime
    -0.15
    ABCDE
    -0.14
    elpers
    -0.14
    .apple
    -0.14
    reater
    -0.14
    cctor
    -0.14
    ropy
    -0.13
    POSITIVE LOGITS
    uary
    0.29
     ob
    0.28
     Ob
    0.24
    -ob
    0.22
    (ob
    0.22
     Obl
    0.21
    fuscated
    0.20
    Ob
    0.19
    Âłob
    0.19
    fusc
    0.19
    Act Density 0.025%

    No Known Activations