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

    Neuronpedia

    INDEX
    Explanations

    the use of pronouns and references to people and their actions

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

    they/their followed by a noun/verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Picchu
    -0.50
    Datuak
    -0.48
    RegressionTest
    -0.46
    ➯
    -0.46
    menes
    -0.46
    ellido
    -0.45
     سكانية
    -0.44
    ower
    -0.44
    spending
    -0.44
    getKeyCode
    -0.44
    POSITIVE LOGITS
     pihaknya
    0.43
     livraison
    0.40
     totalSupply
    0.39
    RegistryLite
    0.39
     nargin
    0.38
    Dış
    0.37
     fallu
    0.36
     culoare
    0.36
    通販
    0.36
    __':
    0.35
    Act Density 0.023%

    No Known Activations