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

    Neuronpedia

    INDEX
    Explanations

    words related to precision or correctness

    oai_token-act-pair · gpt-3.5-turbo

    references to accuracy and its evaluation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sg
    -0.84
     Pharma
    -0.76
    si
    -0.75
    ÃŁ
    -0.74
    hibit
    -0.74
     Towns
    -0.73
    Ing
    -0.72
    Bi
    -0.71
    joining
    -0.70
    Vert
    -0.70
    POSITIVE LOGITS
    uracy
    1.59
     accuracy
    1.39
     inacc
    1.36
     accur
    1.12
     mathemat
    1.09
     confir
    1.06
     inaccur
    1.03
     inaccurate
    1.00
     guiActiveUn
    0.98
     Accuracy
    0.98
    Act Density 0.010%

    No Known Activations