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

    Neuronpedia

    INDEX
    Explanations

    references to safety or protective items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĪı
    -0.13
    ãĥĮ
    -0.13
    #ad
    -0.13
    ï½¢
    -0.12
    iesz
    -0.12
     Butt
    -0.12
    Ø¢Ùħ
    -0.12
    Č
    -0.12
    ville
    -0.12
    .MixedReality
    -0.12
    POSITIVE LOGITS
    ##
    0.16
     welcome
    0.15
    #
    0.14
    ÂŃi
    0.14
    651
    0.14
    ...↵↵
    0.14
    alink
    0.13
    ErrorException
    0.13
     reliably
    0.13
    hey
    0.12
    Act Density 0.771%

    No Known Activations