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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mastering or excelling at something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to achieving success or hitting a target

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adian
    -0.67
     Leilan
    -0.65
    çĶ°
    -0.63
    ryu
    -0.62
    ials
    -0.61
    pai
    -0.61
     reign
    -0.59
     ç¥ŀ
    -0.58
     Intake
    -0.57
    ãĥ´
    -0.57
    POSITIVE LOGITS
     surprises
    0.64
     conclusions
    0.64
     conclusion
    0.62
    ENSE
    0.61
     guesses
    0.61
     Shots
    0.60
     ballpark
    0.60
    apolis
    0.58
    oops
    0.58
    antics
    0.56
    Act Density 0.717%

    No Known Activations