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

    Neuronpedia

    INDEX
    Explanations

    the word "Paris" with various linguistic variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "ais" related to places or people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Skull
    -0.74
     Stur
    -0.72
    è¦ļéĨĴ
    -0.68
     gestation
    -0.64
     thumbnail
    -0.61
     Happiness
    -0.61
     Operation
    -0.61
    finger
    -0.60
     interval
    -0.59
     Suff
    -0.58
    POSITIVE LOGITS
    ais
    1.43
    xual
    1.08
    chwitz
    1.05
    cean
    1.00
    auga
    0.92
    eme
    0.89
    ylum
    0.89
    ateur
    0.88
    terness
    0.87
    ai
    0.86
    Act Density 0.003%

    No Known Activations