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

    Neuronpedia

    INDEX
    Explanations

    terms related to identification and uniqueness in models

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.50
    mäßige
    -0.50
    Altro
    -0.49
     للمعارف
    -0.48
    endif
    -0.48
     Small
    -0.48
     Hot
    -0.48
    ọi
    -0.48
     built
    -0.47
     Find
    -0.47
    POSITIVE LOGITS
     AttributeSet
    0.74
    InitVars
    0.62
     uLocal
    0.59
     Redund
    0.54
     ruota
    0.52
     redundancy
    0.51
     createContext
    0.51
    Pratique
    0.50
     kaynağından
    0.49
     ویکی‌پدی
    0.49
    Act Density 0.089%

    No Known Activations