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

    Neuronpedia

    INDEX
    Explanations

    references to consumers and consumer-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uber
    -0.20
    ew
    -0.19
    ses
    -0.17
    dır
    -0.16
    ern
    -0.15
    ement
    -0.15
    rew
    -0.15
    finger
    -0.15
    ependency
    -0.14
    acey
    -0.14
    POSITIVE LOGITS
    нии
    0.16
    ManagerInterface
    0.16
    ilere
    0.15
    sein
    0.14
    ption
    0.14
    ized
    0.14
    oha
    0.14
    izer
    0.14
    izing
    0.14
    izable
    0.13
    Act Density 0.027%

    No Known Activations