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

    Neuronpedia

    INDEX
    Explanations

    the term "follow-up" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "follow" along with variations indicating continuation or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scotia
    -0.85
    ãĥĨãĤ£
    -0.70
     Riot
    -0.65
    uana
    -0.64
     ILCS
    -0.64
    inese
    -0.62
     Tire
    -0.61
     Tripoli
    -0.60
     sidx
    -0.60
     Mali
    -0.60
    POSITIVE LOGITS
    ings
    1.01
    ership
    0.99
    ers
    0.91
    ingly
    0.85
    overs
    0.85
    downs
    0.84
    ences
    0.83
    ictions
    0.81
    ups
    0.81
    follow
    0.79
    Act Density 0.019%

    No Known Activations