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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal relationships and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uard
    -0.15
    ulen
    -0.15
    icket
    -0.14
    inou
    -0.14
    490
    -0.14
    足
    -0.14
    usual
    -0.14
    uml
    -0.13
    ãĥ¼ãĥŃ
    -0.13
    613
    -0.13
    POSITIVE LOGITS
     suddenly
    0.17
     potentially
    0.16
    ãģĵãĤĵãģª
    0.16
    mere
    0.16
     basically
    0.16
     essentially
    0.15
     someone
    0.15
    ExecutionContext
    0.15
    ç«
    0.15
     Suddenly
    0.15
    Act Density 0.837%

    No Known Activations