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

    Neuronpedia

    INDEX
    Explanations

    queries and references about identity and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Brin
    -0.56
     mors
    -0.55
    atl
    -0.54
     Magna
    -0.54
     APR
    -0.54
    mern
    -0.53
    бля
    -0.53
     abstinence
    -0.53
     Vela
    -0.52
    YOND
    -0.52
    POSITIVE LOGITS
     whom
    1.47
     who
    1.34
     hvem
    1.32
    whom
    1.30
     Who
    1.21
    who
    1.19
    Who
    1.17
     Whom
    1.17
     кто
    1.14
    Кто
    1.14
    Act Density 0.159%

    No Known Activations