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

    Neuronpedia

    INDEX
    Explanations

    concepts and terms related to flexibility in contexts such as planning, processes, and adaptability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ädchen
    -0.15
    erset
    -0.15
    arde
    -0.15
    ollen
    -0.15
    acades
    -0.15
    ihn
    -0.15
    hung
    -0.15
    ÅĻeh
    -0.14
    <pcl
    -0.14
    collision
    -0.14
    POSITIVE LOGITS
    -flex
    0.20
     flex
    0.18
    ibility
    0.17
    ality
    0.17
    flex
    0.16
     flexible
    0.16
    /stretch
    0.16
    infeld
    0.16
    -minded
    0.16
     Flex
    0.16
    Act Density 0.039%

    No Known Activations