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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time, scheduling, and planning

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and phrases related to quantity or prevalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CTV
    -0.67
    ukemia
    -0.65
    atz
    -0.64
    liest
    -0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
    interstitial
    -0.62
    erest
    -0.61
    TextColor
    -0.61
    onymous
    -0.60
     Canaver
    -0.60
    POSITIVE LOGITS
     equation
    1.17
     room
    1.12
     universe
    1.11
     scene
    1.05
     world
    1.01
     vicinity
    1.00
     whole
    0.96
     conversation
    0.96
     entire
    0.96
     situation
    0.94
    Act Density 0.485%

    No Known Activations