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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political or social commentary

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    łaści
    -0.65
    <bos>
    -0.63
    OrEmpty
    -0.57
    wikk
    -0.56
    marginVertical
    -0.55
     exemplaires
    -0.55
    :^{
    -0.54
    !("{
    -0.53
    <?
    -0.53
     gehouden
    -0.52
    POSITIVE LOGITS
     ohr
    1.07
     kram
    1.05
     gend
    1.02
     bahia
    1.01
     plak
    0.99
     marmor
    0.98
     alpes
    0.97
     lele
    0.97
     maer
    0.96
     uhr
    0.94
    Act Density 0.336%

    No Known Activations