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

    Neuronpedia

    INDEX
    Explanations

    instances of references or identifiers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hardt
    -0.14
    cord
    -0.14
    itest
    -0.14
    许
    -0.14
    sters
    -0.14
    ĮĢ
    -0.14
    ZONE
    -0.14
    ies
    -0.14
    bern
    -0.14
    ply
    -0.14
    POSITIVE LOGITS
    Ī¬
    0.17
    OLT
    0.16
    igue
    0.15
    Bes
    0.15
    /link
    0.15
    igidBody
    0.14
    -static
    0.14
    asal
    0.14
    elman
    0.14
    avy
    0.14
    Act Density 0.016%

    No Known Activations