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

    Neuronpedia

    INDEX
    Explanations

    references to reputation and its implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    combe
    -0.20
    aths
    -0.18
    omb
    -0.16
    icular
    -0.16
    IDDEN
    -0.14
    åĻ¨
    -0.14
    ignon
    -0.14
    кÑĥлÑĮ
    -0.14
    ford
    -0.14
    inality
    -0.14
    POSITIVE LOGITS
    ries
    0.16
    ateg
    0.16
    ãĤĴãģ¤
    0.15
    ably
    0.15
    laps
    0.14
    resi
    0.14
    oje
    0.14
    atively
    0.14
     IE
    0.14
    ech
    0.13
    Act Density 0.028%

    No Known Activations