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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate factual claims or assertions

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

    fact that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.65
    parsedMessage
    -0.57
    ImageContext
    -0.53
    ConstraintMaker
    -0.53
    uxxxx
    -0.52
     ویکی‌پدی
    -0.51
    PerformLayout
    -0.51
    writeFieldEnd
    -0.50
    RegistryLite
    -0.48
    enumii
    -0.47
    POSITIVE LOGITS
    Dass
    0.54
     Daß
    0.53
     Tatsache
    0.51
     feit
    0.48
    まさか
    0.47
     faptul
    0.42
     fact
    0.41
     fakta
    0.40
     Dass
    0.37
    AlterField
    0.36
    Act Density 0.123%

    No Known Activations