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

    Neuronpedia

    INDEX
    Explanations

    words related to actions and activities that involve control, allocation, or regulation

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles that imply ongoing action or process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lucy
    -0.62
    meta
    -0.62
    tall
    -0.62
    cube
    -0.61
     il
    -0.58
     Bus
    -0.57
     bisc
    -0.56
    oppy
    -0.56
    tile
    -0.56
    ps
    -0.55
    POSITIVE LOGITS
    vironment
    0.76
    theless
    0.75
    ciating
    0.73
    icating
    0.71
    icates
    0.68
    staking
    0.67
    orpor
    0.66
     INTO
    0.66
    orporated
    0.66
    ushima
    0.65
    Act Density 0.124%

    No Known Activations