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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "centric"/"centering"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "cent" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ©
    -0.82
    è¦ļéĨĴ
    -0.81
    ãģį
    -0.80
    ettings
    -0.76
    bably
    -0.75
    isSpecialOrderable
    -0.73
    çīĪ
    -0.71
     ABE
    -0.70
    IGHTS
    -0.70
    GBT
    -0.69
    POSITIVE LOGITS
    imet
    1.29
    ennial
    1.24
    enary
    1.18
    rals
    1.14
    imeters
    1.09
    imeter
    1.09
    uries
    1.04
    rum
    1.02
    roman
    0.97
    roid
    0.96
    Act Density 0.022%

    No Known Activations