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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authority or control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stamps
    -0.15
    memberof
    -0.14
     Operational
    -0.14
    oyo
    -0.14
    rez
    -0.14
    окÑģ
    -0.14
    ativ
    -0.14
    é¾Ħ
    -0.14
     dial
    -0.13
    íĺ¼
    -0.13
    POSITIVE LOGITS
    zbek
    0.15
    зна
    0.15
    irut
    0.15
    767
    0.14
    "crypto
    0.14
    467
    0.14
    .rdf
    0.14
    SHOT
    0.13
    alette
    0.13
    /effects
    0.13
    Act Density 0.022%

    No Known Activations