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

    Neuronpedia

    INDEX
    Explanations

    mentions of pronouns indicating personal relationships or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parties
    -0.15
    sville
    -0.15
    ButtonText
    -0.15
     Roh
    -0.15
     unc
    -0.14
    ÐļТ
    -0.14
    ecycle
    -0.14
     autoload
    -0.14
    ville
    -0.14
     author
    -0.14
    POSITIVE LOGITS
    /*/
    0.16
    AppName
    0.14
    ilde
    0.14
    .Serve
    0.14
    Observable
    0.14
     crack
    0.14
    idis
    0.14
     trá»įng
    0.14
    rose
    0.14
    fault
    0.14
    Act Density 0.049%

    No Known Activations