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

    Neuronpedia

    INDEX
    Explanations

    recurring phrases and expressions conveying similarity or equivalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    üs
    -0.16
    Ñīин
    -0.14
    oup
    -0.14
    ÑĢел
    -0.14
    uting
    -0.14
    à¤Ŀ
    -0.14
     lawy
    -0.13
    sth
    -0.13
    ker
    -0.13
    rence
    -0.13
    POSITIVE LOGITS
     with
    0.23
     true
    0.22
    对äºİ
    0.22
     regarding
    0.20
     applies
    0.20
     when
    0.19
     respecto
    0.19
     chez
    0.18
     reverse
    0.18
    true
    0.17
    Act Density 0.209%

    No Known Activations