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

    Neuronpedia

    INDEX
    Explanations

    references to scientific articles and their citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asd
    -0.16
     zev
    -0.15
    peak
    -0.14
     kara
    -0.14
    sel
    -0.14
    ÙĤÙģ
    -0.14
     Smarty
    -0.14
    Tube
    -0.13
    inst
    -0.13
    mat
    -0.13
    POSITIVE LOGITS
     pp
    0.50
     p
    0.31
     pag
    0.27
    (pp
    0.27
    .pp
    0.27
    pp
    0.26
     pages
    0.26
     pg
    0.25
    	pp
    0.25
    /pp
    0.24
    Act Density 0.014%

    No Known Activations