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

    Neuronpedia

    INDEX
    Explanations

    elements related to choice and consequence in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decently
    -0.60
     basically
    -0.56
    一応
    -0.56
     fairly
    -0.54
     obviously
    -0.54
    basically
    -0.53
     непло
    -0.53
    mentioned
    -0.53
    大体
    -0.52
     Basically
    -0.50
    POSITIVE LOGITS
     thrilling
    0.71
     dazzling
    0.66
     unprecedented
    0.65
     khám
    0.64
     acclaimed
    0.62
     stunning
    0.62
     breathtaking
    0.60
     bestselling
    0.58
     captivating
    0.57
     secrets
    0.57
    Act Density 0.449%

    No Known Activations