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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical movement or progress

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "run" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Virtue
    -0.68
     Hots
    -0.66
     Voice
    -0.64
     Canad
    -0.61
    oshop
    -0.60
    ĵĺ
    -0.59
     suscept
    -0.59
    Birth
    -0.58
    cientious
    -0.58
     Ink
    -0.58
    POSITIVE LOGITS
    aways
    1.21
    gs
    1.15
    ners
    1.13
    nings
    1.12
    escape
    1.10
    swick
    1.10
    ways
    1.02
    away
    1.00
    times
    0.96
    dy
    0.96
    Act Density 0.038%

    No Known Activations