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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal accomplishment or recognition

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to making a name for oneself

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bowser
    -0.70
     NCT
    -0.57
     Edwards
    -0.56
     DOE
    -0.55
     Anon
    -0.54
     rapper
    -0.53
     Engineers
    -0.53
     Kw
    -0.53
    """
    -0.52
     Tiff
    -0.52
    POSITIVE LOGITS
    ãĥ¼ãĥĨãĤ£
    0.86
    ufact
    0.85
    ewitness
    0.84
    izontal
    0.81
    vironment
    0.80
    aughtered
    0.80
    ibly
    0.79
    ibles
    0.79
    urally
    0.78
    oaded
    0.78
    Act Density 1.237%

    No Known Activations