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

    Neuronpedia

    INDEX
    Explanations

    references to sections, subsections, or numbered lists within technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥãĥĹ
    -0.16
    _fwd
    -0.15
    rypt
    -0.15
    agma
    -0.15
    -marker
    -0.14
     Scalars
    -0.14
    iad
    -0.14
    ekler
    -0.14
     Prim
    -0.14
    urve
    -0.14
    POSITIVE LOGITS
    ilig
    0.16
    -on
    0.15
    izon
    0.15
    dsa
    0.15
    zan
    0.15
    SENT
    0.14
    -IS
    0.14
    isky
    0.14
    oli
    0.14
     Paramount
    0.14
    Act Density 0.032%

    No Known Activations