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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or official processes

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grunt
    -0.69
     ogre
    -0.68
     closet
    -0.68
     silent
    -0.68
    ding
    -0.67
     jugg
    -0.66
     slightest
    -0.66
    ishable
    -0.65
     sideways
    -0.65
     utter
    -0.65
    POSITIVE LOGITS
     Specifically
    1.27
     However
    1.20
     Asked
    1.14
     Furthermore
    1.09
     He
    1.09
     Especially
    1.08
     Instead
    1.07
     Particularly
    1.07
     Therefore
    1.06
     According
    1.06
    Act Density 0.402%

    No Known Activations