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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     folded
    -0.17
     fold
    -0.15
    ÛĮزÛĮ
    -0.15
    ismatic
    -0.15
    chyb
    -0.15
    odelist
    -0.14
    ohon
    -0.14
     åĸ
    -0.14
    uebas
    -0.14
    íĻĢ
    -0.14
    POSITIVE LOGITS
     democr
    0.16
    ëĬIJ
    0.14
    enta
    0.14
     اÙĦجÙħ
    0.14
     suiv
    0.14
    åĮ
    0.14
    _TMP
    0.13
     Libert
    0.13
    unta
    0.13
    star
    0.13
    Act Density 0.189%

    No Known Activations