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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "an" in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erson
    -0.16
    intelligence
    -0.15
    ushima
    -0.15
    enez
    -0.14
    ftware
    -0.14
    rike
    -0.14
    åħ±åĴĮ
    -0.14
    oog
    -0.14
    solete
    -0.14
    Ùī
    -0.14
    POSITIVE LOGITS
    ssi
    0.16
    ees
    0.15
     Kumar
    0.15
    vÄĽt
    0.14
     Rum
    0.13
    gon
    0.13
    ainen
    0.13
     Reputation
    0.13
    ez
    0.13
    een
    0.13
    Act Density 0.365%

    No Known Activations