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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "Prototype" or variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of prototypes and protections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.99
    è£ħ
    -0.77
    INESS
    -0.74
     Tonight
    -0.67
     mund
    -0.66
     Sins
    -0.65
     Confederacy
    -0.62
     visitor
    -0.62
    cloth
    -0.60
    edin
    -0.60
    POSITIVE LOGITS
    otyp
    1.38
    ected
    1.36
    agonist
    1.36
    otypes
    1.33
    ests
    1.23
    racted
    1.19
    ocol
    1.18
    agonists
    1.17
    otype
    1.08
    ractor
    1.07
    Act Density 0.045%

    No Known Activations