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

    Neuronpedia

    INDEX
    Explanations

    instances of alternating roles or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     дело
    -0.17
    agg
    -0.16
    ownik
    -0.15
     desn
    -0.15
    ìĿ´ìĸ´
    -0.15
    UCCESS
    -0.14
    ạc
    -0.14
     sá»ijng
    -0.14
    á»Ļ
    -0.14
    εÏħ
    -0.14
    POSITIVE LOGITS
     between
    0.20
    ouro
    0.15
    istr
    0.14
     twin
    0.14
    odash
    0.14
    .parallel
    0.14
     partner
    0.14
    -between
    0.14
    rek
    0.14
    mitter
    0.13
    Act Density 0.162%

    No Known Activations