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

    Neuronpedia

    INDEX
    Explanations

    references to political parties and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     desierto
    -0.51
    GEBURTSDATUM
    -0.50
     esclavos
    -0.50
     miniaturka
    -0.50
    دانشنامهٔ
    -0.49
    preuve
    -0.49
    RegressionTest
    -0.48
     continúas
    -0.48
     damska
    -0.47
     pegat
    -0.47
    POSITIVE LOGITS
     Dec
    0.34
     Submit
    0.33
     Rer
    0.31
     NS
    0.30
    <bos>
    0.30
     ModelExpression
    0.30
     Drs
    0.30
    ﾟ)
    0.29
     Building
    0.29
     Nov
    0.29
    Act Density 0.051%

    No Known Activations