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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "do"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "do" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     critical
    -0.63
     centres
    -0.62
     respectively
    -0.62
     passing
    -0.61
     upfront
    -0.61
     centers
    -0.60
     cent
    -0.60
     screened
    -0.59
     acquired
    -0.58
     bags
    -0.58
    POSITIVE LOGITS
    do
    4.18
    dos
    2.34
    DO
    1.83
    did
    1.71
    doing
    1.63
    Do
    1.51
    does
    1.49
    don
    1.49
    di
    1.38
    da
    1.34
    Act Density 0.008%

    No Known Activations