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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'in'

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behav
    -0.64
     vanquished
    -0.63
     disple
    -0.63
     remem
    -0.63
     shake
    -0.62
     lett
    -0.62
     firmly
    -0.62
    ById
    -0.61
     campuses
    -0.60
     hypoc
    -0.60
    POSITIVE LOGITS
    strument
    1.62
    visible
    1.52
    jured
    1.45
    cluded
    1.42
    juries
    1.41
    jury
    1.41
    clusive
    1.39
    herent
    1.38
    jection
    1.37
    iti
    1.37
    Act Density 0.104%

    No Known Activations