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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaboration and the formation of distinct identities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IFO
    -0.16
    RootElement
    -0.16
    ł
    -0.15
    UpInside
    -0.15
     addCriterion
    -0.15
    _Variable
    -0.15
    <textarea
    -0.15
    ulumi
    -0.14
    InstanceState
    -0.14
    apel
    -0.14
    POSITIVE LOGITS
    rossover
    0.15
    커
    0.15
     inse
    0.15
    omed
    0.15
    ocl
    0.15
    fern
    0.14
    conde
    0.14
    ic
    0.14
     package
    0.14
    emma
    0.14
    Act Density 0.002%

    No Known Activations