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

    Neuronpedia

    INDEX
    Explanations

    instances of emphasis or repetition in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resa
    -0.17
    loy
    -0.16
    olar
    -0.15
     تÙħاÙħ
    -0.15
    lesen
    -0.14
    arty
    -0.14
    uly
    -0.14
    ëĭ¹
    -0.13
    lemen
    -0.13
    ledo
    -0.13
    POSITIVE LOGITS
    avl
    0.18
    ucer
    0.18
    edin
    0.17
    aque
    0.17
    asn
    0.17
    ez
    0.16
    MV
    0.15
    el
    0.15
    urd
    0.14
    longleftrightarrow
    0.14
    Act Density 0.005%

    No Known Activations