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

    Neuronpedia

    INDEX
    Explanations

    references to the reader or second-person perspective pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.74
    addCriterion
    -0.68
    GEBURTSDATUM
    -0.66
     Roskov
    -0.63
     AssemblyTitle
    -0.63
    LookAnd
    -0.63
     TextAppearance
    -0.62
     GeoNames
    -0.61
    mergeFrom
    -0.61
    RegressionTest
    -0.59
    POSITIVE LOGITS
     mustn
    0.78
     should
    0.73
     shouldn
    0.73
     Deber
    0.71
     Shouldn
    0.69
     Pion
    0.65
     shou
    0.65
     SHOULD
    0.64
     ought
    0.64
     autoradio
    0.64
    Act Density 0.237%

    No Known Activations