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

    Neuronpedia

    INDEX
    Explanations

    phrases related to identity and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¹ĭä¸Ģ
    -0.17
     guy
    -0.17
     staffer
    -0.17
    .libs
    -0.17
     gangs
    -0.16
    ista
    -0.15
     Spells
    -0.15
    çļĦä¸Ģ个
    -0.15
     newcomer
    -0.15
    341
    -0.15
    POSITIVE LOGITS
     themselves
    0.40
     condu
    0.19
     ones
    0.18
     stew
    0.18
     yourselves
    0.18
     masters
    0.18
     initi
    0.18
    asters
    0.17
     holders
    0.17
     catalyst
    0.17
    Act Density 0.621%

    No Known Activations