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

    Neuronpedia

    INDEX
    Explanations

    number ranges

    oai_token-act-pair · gpt-3.5-turbo

    numerical ranges or age groups specified in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     redes
    -0.70
    yet
    -0.61
     Polic
    -0.60
    NRS
    -0.58
    erman
    -0.58
     Adds
    -0.57
    ŃĶ
    -0.57
    AFTA
    -0.56
    ãĥķãĤ©
    -0.56
     Judge
    -0.52
    POSITIVE LOGITS
     ])
    0.66
    vag
    0.61
    flush
    0.60
     sexes
    0.59
    BuyableInstoreAndOnline
    0.58
    ust
    0.58
    wealth
    0.57
    Í
    0.56
    akespeare
    0.56
    ties
    0.56
    Act Density 0.075%

    No Known Activations