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

    Neuronpedia

    INDEX
    Explanations

    document structure elements or specific formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    الإنجليزية
    -0.65
    SEGUIR
    -0.61
     للاسماء
    -0.56
    reszcie
    -0.52
     Familienname
    -0.51
     věci
    -0.50
     נוספת
    -0.49
    こちらも
    -0.48
     aikaa
    -0.48
    again
    -0.48
    POSITIVE LOGITS
    <bos>
    0.90
    tvguidetime
    0.89
    ADVERTISEMENT
    0.80
     referenties
    0.78
     Италијани
    0.71
    ❋
    0.67
    IsInitialized
    0.63
    yntaxException
    0.59
    ########.
    0.58
    0.58
    Act Density 0.764%

    No Known Activations