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

    Neuronpedia

    INDEX
    Explanations

    terms related to architecture and architectural styles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceptive
    -0.16
    icity
    -0.15
    ÑĥÑĪки
    -0.14
    yun
    -0.14
    eration
    -0.14
    oo
    -0.14
    arious
    -0.14
    arga
    -0.13
    tings
    -0.13
    rog
    -0.13
    POSITIVE LOGITS
    urally
    0.36
    ural
    0.36
    URAL
    0.27
    /engine
    0.25
    ures
    0.21
    itect
    0.20
    onical
    0.20
    å¸Ī
    0.20
    tura
    0.20
    tober
    0.20
    Act Density 0.015%

    No Known Activations