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

    Neuronpedia

    INDEX
    Explanations

    phrases describing an action that is intended or expected to happen in the future

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "set to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Perspective
    -0.72
    quickShipAvailable
    -0.70
    76561
    -0.66
    checking
    -0.65
    Apps
    -0.65
     embodiments
    -0.62
     Explan
    -0.60
     unworthy
    -0.59
     universes
    -0.58
    xus
    -0.58
    POSITIVE LOGITS
     expire
    1.20
     arrive
    1.14
     unveil
    1.08
     announce
    1.07
     undergo
    1.02
     commence
    1.02
     coincide
    1.01
     begin
    1.01
     unleash
    0.99
     be
    0.97
    Act Density 0.093%

    No Known Activations