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

    Neuronpedia

    INDEX
    Explanations

    terms related to welfare analysis

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.93
     Denis
    -0.79
     Turn
    -0.77
     nocturne
    -0.75
     turn
    -0.74
     Driscoll
    -0.74
    spac
    -0.71
    kehr
    -0.70
     Bist
    -0.69
    voet
    -0.69
    POSITIVE LOGITS
    Welfare
    1.02
     Welfare
    0.90
     resourceCulture
    0.90
     "..\..\
    0.89
    Newport
    0.88
     welfare
    0.88
     Marek
    0.87
     SV
    0.86
    WEL
    0.86
     welder
    0.83
    Act Density 0.029%

    No Known Activations