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

    Neuronpedia

    INDEX
    Explanations

    references to collective human experiences and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quizás
    -0.56
    ItemBackground
    -0.56
     совсем
    -0.55
    exitRule
    -0.54
    setObjectName
    -0.51
     talvez
    -0.50
     Ganze
    -0.50
     AssemblyTitle
    -0.50
     hiç
    -0.49
    省市镇
    -0.49
    POSITIVE LOGITS
     except
    1.02
    except
    0.89
     kecuali
    0.88
    Except
    0.87
     alike
    0.84
     Except
    0.81
     sauf
    0.78
     excepto
    0.78
     individually
    0.77
     EXCEPT
    0.77
    Act Density 0.626%

    No Known Activations