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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to legal or procedural matters

    oai_token-act-pair · gpt-3.5-turbo

    legal and bureaucratic terminology related to rulings and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ibid
    -0.60
    ossier
    -0.57
    æĸ¹
    -0.54
    Russ
    -0.53
    cyclopedia
    -0.52
     Erd
    -0.52
     Mouth
    -0.51
    tsky
    -0.51
     Masters
    -0.50
    asu
    -0.50
    POSITIVE LOGITS
    ibly
    0.86
    ially
    0.66
    ably
    0.64
    iably
    0.63
    icip
    0.63
     loopholes
    0.62
    nance
    0.62
     tariffs
    0.57
    erred
    0.57
    arbon
    0.56
    Act Density 1.292%

    No Known Activations