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

    Neuronpedia

    INDEX
    Explanations

    references to welfare and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewe
    -0.15
    u
    -0.15
    essim
    -0.14
    تÙĬÙĨ
    -0.14
    .EventArgs
    -0.14
    -With
    -0.14
     Ment
    -0.14
    wallet
    -0.14
     Mint
    -0.14
    -assets
    -0.14
    POSITIVE LOGITS
    isper
    0.16
    boys
    0.15
    룬
    0.15
    legg
    0.15
    tere
    0.15
    krom
    0.15
    MI
    0.15
    Ĵ
    0.14
    apist
    0.14
    erce
    0.14
    Act Density 0.006%

    No Known Activations