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

    Neuronpedia

    INDEX
    Explanations

    people's names with the substring "ins"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ploma
    -0.62
     Achieve
    -0.60
     Governments
    -0.59
    ¥µ
    -0.59
     Prime
    -0.58
     Proposition
    -0.58
    sterdam
    -0.57
     DISTR
    -0.57
     shake
    -0.56
     compr
    -0.56
    POSITIVE LOGITS
    pection
    1.24
    urance
    1.20
    kaya
    1.04
    anity
    0.99
    poon
    0.99
    ufficient
    0.98
    piration
    0.98
    ensitive
    0.97
    pect
    0.97
    piring
    0.97
    Act Density 0.024%

    No Known Activations