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

    Neuronpedia

    INDEX
    Explanations

    references to dictionaries or dictionary-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    age
    -0.18
    138
    -0.17
    ages
    -0.15
    jes
    -0.15
    uck
    -0.15
    403
    -0.15
    aging
    -0.15
    745
    -0.15
    748
    -0.15
     acquainted
    -0.14
    POSITIVE LOGITS
    ../../../
    0.20
    Vectorizer
    0.18
    .reference
    0.16
    chied
    0.16
    ulaire
    0.16
    à¤Łà¤ķ
    0.16
    ç±į
    0.15
    ERGE
    0.15
    croll
    0.15
    embre
    0.15
    Act Density 0.021%

    No Known Activations