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

    Neuronpedia

    INDEX
    Explanations

    mention uses of the word "will" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "will" indicating intention or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amps
    -0.65
    amped
    -0.65
    BuyableInstoreAndOnline
    -0.65
    quickShipAvailable
    -0.64
    REE
    -0.64
    Creat
    -0.63
    bies
    -0.63
    angled
    -0.63
    uria
    -0.62
    taboola
    -0.62
    POSITIVE LOGITS
     gladly
    1.32
     admit
    0.98
     assume
    0.98
     presume
    0.93
     happily
    0.93
     continue
    0.92
     summarize
    0.91
     endeavour
    0.91
     reiterate
    0.89
     discuss
    0.87
    Act Density 0.095%

    No Known Activations