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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences containing comparative quantities such as "more than" or "about."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantities or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ococ
    -0.71
    Definition
    -0.67
    ãĤ¿
    -0.64
     Clicker
    -0.63
    Universal
    -0.61
    Zip
    -0.60
     Savings
    -0.60
    respective
    -0.60
    NEY
    -0.59
    Introduced
    -0.59
    POSITIVE LOGITS
     dozen
    1.28
    dozen
    1.17
     200
    1.14
     300
    1.10
     250
    1.09
     400
    1.09
     150
    1.08
     500
    1.08
     120
    1.03
     100
    1.01
    Act Density 0.119%

    No Known Activations