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

    Neuronpedia

    INDEX
    Explanations

    references to scientific councils and committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akan
    -0.17
    rug
    -0.16
    icks
    -0.16
    gow
    -0.15
    oš
    -0.15
    overy
    -0.15
    ungan
    -0.14
    温
    -0.14
    Smarty
    -0.14
     hart
    -0.14
    POSITIVE LOGITS
     committee
    0.21
     Committee
    0.20
     National
    0.18
     NAS
    0.18
    BOSE
    0.17
     workshop
    0.17
    NAS
    0.16
    committee
    0.16
    National
    0.16
     Workshop
    0.16
    Act Density 0.012%

    No Known Activations