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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or references in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukone
    -0.75
    %)$
    -0.73
    sohn
    -0.70
    وث
    -0.69
    ))))))))
    -0.68
    Millan
    -0.68
    hubungan
    -0.68
    ποτε
    -0.68
     createState
    -0.68
     addItem
    -0.66
    POSITIVE LOGITS
     за
    2.27
    За
    1.64
     za
    1.61
     За
    1.53
     ЗА
    1.26
     Za
    1.15
    за
    1.15
    Za
    1.14
     ZA
    0.95
    ЗА
    0.90
    Act Density 0.014%

    No Known Activations