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

    Neuronpedia

    INDEX
    Explanations

    mentions of numerical measurements, particularly in centimeters or percentages

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģį
    -0.81
     ABE
    -0.79
    IGHTS
    -0.79
    IDES
    -0.77
    HCR
    -0.72
    Else
    -0.71
    Thumbnail
    -0.70
    é¾įå
    -0.70
    Techn
    -0.67
    Ö¼
    -0.66
    POSITIVE LOGITS
    imet
    1.24
     cent
    1.15
    urion
    0.89
    imeter
    0.86
     foss
    0.85
    enaries
    0.84
    enary
    0.83
    roid
    0.79
    igr
    0.79
    roman
    0.78
    Act Density 0.009%

    No Known Activations