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

    Neuronpedia

    INDEX
    Explanations

    phrases that express similarity or equivalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uly
    -0.17
     Guild
    -0.15
    este
    -0.15
    ugu
    -0.15
    ested
    -0.14
     Tel
    -0.14
    -gnu
    -0.14
    .tel
    -0.14
    ubi
    -0.14
    Compat
    -0.14
    POSITIVE LOGITS
    olit
    0.15
    ãĥĦ
    0.15
    afka
    0.15
    erset
    0.15
    kas
    0.14
    nof
    0.14
     Stateless
    0.14
     Lessons
    0.14
    arkan
    0.14
    rices
    0.13
    Act Density 0.057%

    No Known Activations