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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criticizing or discussing issues or problems

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughtered
    -0.96
    ickets
    -0.89
    rollers
    -0.89
    apps
    -0.89
    ricanes
    -0.86
    phies
    -0.85
    ²¾
    -0.85
    к
    -0.84
    operated
    -0.83
    agues
    -0.83
    POSITIVE LOGITS
     notion
    1.33
     assertion
    1.33
     analogy
    1.32
     characterization
    1.29
     assumption
    1.27
     argument
    1.25
     premise
    1.25
     presumption
    1.23
     worldview
    1.23
     conclusion
    1.22
    Act Density 0.188%

    No Known Activations