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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and prepositions that emphasize connections or relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¹ãģį
    -0.15
    urr
    -0.15
     ayrıca
    -0.14
     Ñıким
    -0.13
     primero
    -0.13
    resp
    -0.13
     OTHERWISE
    -0.13
     коÑĤоÑĢÑĭм
    -0.13
    ï¼ĮåĪĻ
    -0.13
     notamment
    -0.13
    POSITIVE LOGITS
     after
    0.33
     although
    0.33
     when
    0.33
     upon
    0.31
     it
    0.29
     within
    0.29
     despite
    0.28
     during
    0.26
     while
    0.26
     though
    0.25
    Act Density 0.330%

    No Known Activations