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

    Neuronpedia

    INDEX
    Explanations

    terms related to circular or cyclical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettings
    -0.15
    gend
    -0.15
    oug
    -0.15
    ivery
    -0.15
    edly
    -0.14
    ëĵĿ
    -0.14
    dür
    -0.14
    esiz
    -0.14
    æĭĶ
    -0.14
    IVERY
    -0.14
    POSITIVE LOGITS
    adian
    0.32
    uits
    0.31
     Circ
    0.30
     circ
    0.30
    circ
    0.29
    ums
    0.26
    uito
    0.24
    uite
    0.24
    ulating
    0.22
    ulation
    0.21
    Act Density 0.008%

    No Known Activations