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

    Neuronpedia

    INDEX
    Explanations

    mentions of different versions or instances of a specific protocol or term

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific type of protocol, often abbreviated as "Prot."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.93
    è£ħ
    -0.78
    INESS
    -0.75
     Sins
    -0.69
     Tonight
    -0.69
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
     Learns
    -0.64
     visitor
    -0.63
     Crusher
    -0.63
    uliffe
    -0.63
    POSITIVE LOGITS
    agonist
    1.32
    ests
    1.29
    ected
    1.27
    otyp
    1.24
    otypes
    1.22
    racted
    1.19
    ocol
    1.17
    agonists
    1.15
    otype
    1.07
    ective
    1.06
    Act Density 0.032%

    No Known Activations