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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of years or time frames

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating performance, outcomes, or comparisons related to activities or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )))
    -0.79
    ))))
    -0.73
    xit
    -0.72
    exit
    -0.67
    Fuck
    -0.66
    ***
    -0.65
    "))
    -0.64
     ***
    -0.62
     )))
    -0.61
    fuck
    -0.61
    POSITIVE LOGITS
    entimes
    1.14
    often
    0.96
     often
    0.92
    sometimes
    0.90
     typically
    0.89
     usually
    0.86
     frequently
    0.85
     sometimes
    0.81
    typically
    0.80
     oft
    0.79
    Act Density 1.161%

    No Known Activations