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

    Neuronpedia

    INDEX
    Explanations

    people expressing their desires or intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal goals and aspirations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.76
     respectively
    -0.53
     propelled
    -0.53
     inexpl
    -0.51
    })
    -0.46
    ello
    -0.46
    ibaba
    -0.45
     mysteriously
    -0.45
    @#&
    -0.44
     counting
    -0.44
    POSITIVE LOGITS
     someday
    0.72
     ASAP
    0.64
     tomorrow
    0.60
     responsibly
    0.60
     oneself
    0.58
     yourselves
    0.57
     ourselves
    0.53
     anytime
    0.53
     humility
    0.51
     yourself
    0.50
    Act Density 1.567%

    No Known Activations