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

    Neuronpedia

    INDEX
    Explanations

    frequency of personal pronouns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IndentedString
    -0.91
     мәкал
    -0.91
    RegressionTest
    -0.90
     autorytatywna
    -0.88
    featureID
    -0.82
     Roskov
    -0.82
     Савезне
    -0.81
     '\\;'
    -0.78
     ExecuteAsync
    -0.78
    Geplaatst
    -0.76
    POSITIVE LOGITS
     can
    0.84
     is
    0.84
     They
    0.84
     never
    0.83
     have
    0.81
     He
    0.81
     also
    0.80
     always
    0.80
     has
    0.78
     will
    0.78
    Act Density 0.973%

    No Known Activations