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

    Neuronpedia

    INDEX
    Explanations

    references to legal obligations and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oon
    -0.16
    /mod
    -0.15
    APE
    -0.15
    merce
    -0.14
    cale
    -0.14
     ØŃØ°
    -0.14
     Kah
    -0.14
    iat
    -0.14
    ãĢħ
    -0.14
    etti
    -0.13
    POSITIVE LOGITS
     duty
    0.21
    -duty
    0.19
     Duty
    0.19
     duties
    0.18
     obligation
    0.17
    iful
    0.16
     obligations
    0.16
     Obl
    0.15
    ulfilled
    0.15
    vic
    0.15
    Act Density 0.041%

    No Known Activations