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

    Neuronpedia

    INDEX
    Explanations

    descriptions of legal or official documents

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal and bureaucratic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estival
    -0.67
     reckoned
    -0.63
    eers
    -0.55
    hedon
    -0.55
     worshipped
    -0.54
    ovies
    -0.54
    ahime
    -0.51
    iverpool
    -0.51
    %]
    -0.51
    essel
    -0.50
    POSITIVE LOGITS
    ibly
    0.59
     Plaint
    0.58
     Permanent
    0.57
     indemn
    0.57
    tails
    0.57
    lihood
    0.56
     Applicant
    0.55
     discretion
    0.53
     monetary
    0.53
    illy
    0.53
    Act Density 1.674%

    No Known Activations