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

    Neuronpedia

    INDEX
    Explanations

    references to related topics or categories within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -0.15
    _relations
    -0.15
    ruz
    -0.15
    atti
    -0.15
    ¶Į
    -0.15
    rik
    -0.14
    azy
    -0.14
    asers
    -0.14
    anko
    -0.14
    adors
    -0.14
    POSITIVE LOGITS
    ly
    0.23
    ness
    0.22
     topics
    0.19
     Topics
    0.18
    èģĶ
    0.18
    Topics
    0.16
     issues
    0.15
    osh
    0.15
    oram
    0.15
    396
    0.15
    Act Density 0.026%

    No Known Activations