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

    Neuronpedia

    INDEX
    Explanations

    references to authors and literary works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bordel
    -0.15
    alach
    -0.15
    oler
    -0.15
    ä¸Ī
    -0.15
     whore
    -0.15
    izoph
    -0.14
    urat
    -0.14
    "struct
    -0.14
    á»iji
    -0.14
    uffman
    -0.14
    POSITIVE LOGITS
     dual
    0.17
     motor
    0.16
     Sunny
    0.16
     Dual
    0.15
    ISODE
    0.15
     CHAPTER
    0.15
     Woo
    0.15
     Bols
    0.15
     Omn
    0.15
     Sphinx
    0.15
    Act Density 0.081%

    No Known Activations