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

    Neuronpedia

    INDEX
    Explanations

    phrases related to serious investigations or legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant moral or ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?).
    -0.79
     nonetheless
    -0.75
    !).
    -0.70
    ).[
    -0.69
    .).
    -0.66
     accordingly
    -0.63
    ).
    -0.63
    ))))
    -0.62
    ."[
    -0.61
    )."
    -0.58
    POSITIVE LOGITS
     unlaw
    0.56
     commissions
    0.55
     Franch
    0.54
     Ferdinand
    0.54
     Scarlet
    0.53
    amen
    0.53
     Byr
    0.52
     Briggs
    0.51
     Seym
    0.50
     Gard
    0.50
    Act Density 1.653%

    No Known Activations