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

    Neuronpedia

    INDEX
    Explanations

    phrases that express disagreement or challenge established opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes after a citation (e.g. Id. at)

    np_acts-logits-general · gemini-2.0-flash

    told or retweeted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ungszeit
    -0.50
    BufferException
    -0.42
    migrationBuilder
    -0.39
     proyección
    -0.37
     noticia
    -0.37
     lunak
    -0.36
     Hallen
    -0.36
    AlterField
    -0.36
     brinquedo
    -0.35
     penyakit
    -0.35
    POSITIVE LOGITS
    kapet
    0.46
    ViewFeatures
    0.45
    __":
    0.42
    MigrationBuilder
    0.42
    Хро
    0.41
    gdala
    0.41
     Fram
    0.41
     Kategorie
    0.40
    ENDIAN
    0.40
    ſelf
    0.39
    Act Density 0.682%

    No Known Activations