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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases containing the word 'in'

    oai_token-act-pair · gpt-3.5-turbo

    the word "in" indicating various contexts within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.76
    âĿ
    -0.67
     robbers
    -0.63
    resh
    -0.62
     nailed
    -0.61
     deported
    -0.60
    awei
    -0.58
     combatants
    -0.58
     assailants
    -0.57
    ģĸ
    -0.57
    POSITIVE LOGITS
     spite
    1.29
     addition
    1.25
     lieu
    1.25
     accordance
    1.19
    cluding
    1.15
     conjunction
    1.08
    flation
    1.05
    versely
    1.04
    advert
    1.03
    cluded
    1.02
    Act Density 0.106%

    No Known Activations