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

    Neuronpedia

    INDEX
    Explanations

    references to ownership or possessive expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    locke
    -0.54
    -0.52
     réussir
    -0.51
     noexcept
    -0.51
     Persön
    -0.50
    ViewFeatures
    -0.50
    mergeFrom
    -0.49
    RegressionTest
    -0.49
    Observ
    -0.48
     emigrants
    -0.48
    POSITIVE LOGITS
     ujednoznacz
    1.16
     own
    0.86
     vendors
    0.78
     próprios
    0.77
     وتسجيلات
    0.76
     vendor
    0.74
     Vendors
    0.72
     própria
    0.71
     Vendor
    0.69
     próprio
    0.67
    Act Density 0.079%

    No Known Activations