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

    Neuronpedia

    INDEX
    Explanations

    references to scientific organizations and their missions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     as
    -0.59
    ,
    -0.51
     on
    -0.51
     (
    -0.51
      
    -0.50
     me
    -0.48
     so
    -0.46
     and
    -0.46
     of
    -0.45
     
    -0.45
    POSITIVE LOGITS
    principalColumn
    1.45
     kasarigan
    1.29
    tagHelperRunner
    1.29
    IndentedString
    1.24
     الرياضيه
    1.17
    хьтан
    1.17
     surla
    1.16
     незавершена
    1.14
     Roskov
    1.14
    MLLoader
    1.14
    Act Density 0.501%

    No Known Activations