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

    Neuronpedia

    INDEX
    Explanations

    keywords related to various types of protests and demonstrations

    oai_token-act-pair · gpt-3.5-turbo

    different protocols and variations of the term "Prot"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.91
    è£ħ
    -0.78
    INESS
    -0.78
    uliffe
    -0.76
    hyde
    -0.71
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
     Tonight
    -0.67
     Sins
    -0.65
     Learns
    -0.64
    BuyableInstoreAndOnline
    -0.63
    POSITIVE LOGITS
    agonist
    1.32
    otyp
    1.25
    otypes
    1.24
    ected
    1.24
    ests
    1.19
    racted
    1.11
    ocol
    1.10
    agonists
    1.08
    ractor
    1.05
    uber
    1.02
    Act Density 0.024%

    No Known Activations