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

    Neuronpedia

    INDEX
    Explanations

    concepts related to freedom of expression and the importance of diverse voices in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.84
    Билгалдахарш
    -0.83
     kasarigan
    -0.82
     disambiguazione
    -0.73
    RegistryLite
    -0.71
    ">//
    -0.68
    */),
    -0.67
    grà
    -0.67
    ]})
    -0.66
    hoodie
    -0.66
    POSITIVE LOGITS
     things
    0.56
     everything
    0.55
     either
    0.54
     anything
    0.50
     şeyler
    0.49
     qualcosa
    0.48
    kloped
    0.48
    zinho
    0.46
     stuff
    0.46
    addPreferredGap
    0.46
    Act Density 0.292%

    No Known Activations