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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility, necessity, or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Newport
    -0.15
     Cove
    -0.15
    raid
    -0.15
    BSD
    -0.14
     Elo
    -0.14
     Inn
    -0.14
    AEA
    -0.14
    bart
    -0.14
    opis
    -0.13
    CEEDED
    -0.13
    POSITIVE LOGITS
    igy
    0.17
    ibt
    0.15
    arkin
    0.15
    é¨
    0.14
    atre
    0.14
    va
    0.14
    igar
    0.14
    iser
    0.14
    /extensions
    0.14
    ัà¸ģส
    0.13
    Act Density 0.057%

    No Known Activations