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

    Neuronpedia

    INDEX
    Explanations

    specific terms and phrases related to dynamic and engaging interactions or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enstein
    -0.16
    Impl
    -0.15
     liver
    -0.14
    bjerg
    -0.14
    ray
    -0.14
    amas
    -0.13
    amedi
    -0.13
    spi
    -0.13
    990
    -0.13
    ters
    -0.13
    POSITIVE LOGITS
    erse
    0.15
    /goto
    0.15
     aks
    0.15
    iland
    0.15
    378
    0.14
     Designed
    0.14
     scales
    0.14
    ichel
    0.14
     agre
    0.13
    urg
    0.13
    Act Density 0.529%

    No Known Activations