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

    Neuronpedia

    INDEX
    Explanations

    terms related to identity and social roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gangs
    -0.17
    .libs
    -0.16
    oven
    -0.16
    ä¹ĭä¸Ģ
    -0.15
    ç´
    -0.15
     Spells
    -0.15
     staffer
    -0.15
     guy
    -0.15
     teammate
    -0.15
     itself
    -0.15
    POSITIVE LOGITS
     themselves
    0.40
     yourselves
    0.19
     mess
    0.18
     ones
    0.18
     holders
    0.17
     mere
    0.17
     condu
    0.17
     replacements
    0.16
     members
    0.16
     Mess
    0.16
    Act Density 0.658%

    No Known Activations