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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditional actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -0.64
    jsxFileName
    -0.62
     يتيمه
    -0.60
    GTCX
    -0.59
    Portale
    -0.57
    BoxShadow
    -0.57
    ElementException
    -0.55
    nodoc
    -0.54
     ujednoznacz
    -0.54
    Personendaten
    -0.53
    POSITIVE LOGITS
    ])));
    0.77
    ctory
    0.68
     Вікі
    0.67
     Himo
    0.65
    🏻‍♀️
    0.63
    ]--;
    0.61
    ]<<"
    0.60
    ))));
    0.59
     requisition
    0.56
    abestanden
    0.56
    Act Density 0.132%

    No Known Activations