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

    Neuronpedia

    INDEX
    Explanations

    parts of sentences that start with the word "In"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "In" followed by a numeric value or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resh
    -0.71
    FTWARE
    -0.67
    MpServer
    -0.63
    76561
    -0.62
     enthusi
    -0.60
     soar
    -0.59
     lodged
    -0.58
    ILY
    -0.57
    yles
    -0.57
    Magn
    -0.55
    POSITIVE LOGITS
     fact
    1.44
     hindsight
    1.37
     retrospect
    1.29
    sofar
    1.25
     essence
    1.24
     spite
    1.19
     fairness
    1.15
    herent
    1.14
     reality
    1.13
    advert
    1.11
    Act Density 0.134%

    No Known Activations