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

    Neuronpedia

    INDEX
    Explanations

    words related to developing, building, and creating

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nery
    -0.86
    ably
    -0.81
    itism
    -0.77
    iness
    -0.77
    ternity
    -0.75
    ses
    -0.74
    agne
    -0.74
    icals
    -0.73
    Downloadha
    -0.72
    asers
    -0.71
    POSITIVE LOGITS
    tons
    1.22
     Sands
    1.02
     Rooms
    0.87
    ton
    0.86
     Factors
    0.86
     Grounds
    0.86
     Disorders
    0.85
     Disorder
    0.84
     Behavior
    0.84
     Agents
    0.81
    Act Density 0.130%

    No Known Activations