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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of specific names or initials within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #__
    -0.17
    uzey
    -0.16
    ãģ£ãģ¡
    -0.16
    ROUND
    -0.15
    itel
    -0.14
     NotImplemented
    -0.14
    èŃľ
    -0.14
     câ
    -0.14
     ç¨
    -0.14
    erable
    -0.14
    POSITIVE LOGITS
    ork
    0.24
    ORK
    0.20
    anka
    0.17
    oro
    0.17
    anca
    0.15
    uids
    0.15
    oval
    0.15
    oll
    0.15
    ento
    0.15
    AUSE
    0.14
    Act Density 0.010%

    No Known Activations