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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to embedding or integration within content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÌĨ
    -0.16
    eland
    -0.15
    еÑģÑĤв
    -0.14
    andro
    -0.14
    asmus
    -0.14
    ahoma
    -0.14
    ismatic
    -0.14
    anger
    -0.14
    ormsg
    -0.14
    inea
    -0.14
    POSITIVE LOGITS
    /embed
    0.28
    ding
    0.23
    ment
    0.22
    .embed
    0.21
    ded
    0.20
    dings
    0.19
    (embed
    0.18
    Into
    0.18
    esson
    0.17
    prise
    0.17
    Act Density 0.015%

    No Known Activations