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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "in"

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" used to introduce contexts or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nailed
    -0.62
     lodged
    -0.60
    hur
    -0.60
     endors
    -0.58
    76561
    -0.57
    channelAvailability
    -0.56
     spoil
    -0.56
     indisc
    -0.55
    resh
    -0.55
     looms
    -0.55
    POSITIVE LOGITS
     spite
    1.36
     lieu
    1.30
     addition
    1.29
     accordance
    1.19
     order
    1.09
    clus
    1.08
    flation
    1.08
     contrast
    1.07
     essence
    1.07
     conjunction
    1.07
    Act Density 0.171%

    No Known Activations