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

    Neuronpedia

    INDEX
    Explanations

    prepositions "in."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emis
    -0.66
    tal
    -0.62
    awei
    -0.57
    chel
    -0.57
    yss
    -0.57
    IRO
    -0.56
     Loans
    -0.54
    ¿½
    -0.54
    bryce
    -0.54
    rose
    -0.54
    POSITIVE LOGITS
     spite
    1.16
     vain
    1.14
    clusively
    1.14
     lieu
    1.09
     earnest
    1.09
     accordance
    1.09
     order
    1.08
    humane
    1.05
     person
    1.03
     advance
    0.99
    Act Density 0.217%

    No Known Activations