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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate identification and various forms of classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    keit
    -0.19
    bers
    -0.18
    ën
    -0.16
    lett
    -0.16
    AllWindows
    -0.16
    pline
    -0.15
    еÑģÑĤи
    -0.15
    itar
    -0.15
    RS
    -0.15
    uten
    -0.15
    POSITIVE LOGITS
    emente
    0.25
    ertainment
    0.23
    iation
    0.22
    ennial
    0.21
    ials
    0.21
    itious
    0.21
    ia
    0.20
    ech
    0.20
    ijn
    0.20
    iated
    0.19
    Act Density 0.103%

    No Known Activations