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

    Neuronpedia

    INDEX
    Explanations

    terms related to embedding or incorporation within a larger context or system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÌĨ
    -0.16
    inea
    -0.15
    ventions
    -0.15
    atham
    -0.15
    еÑģÑĤв
    -0.15
    andro
    -0.15
    eland
    -0.15
    -ÑĤо
    -0.14
    nou
    -0.14
    dump
    -0.14
    POSITIVE LOGITS
    /embed
    0.30
    ding
    0.25
    ded
    0.24
    ment
    0.23
    .embed
    0.23
    å¼ı
    0.21
    dings
    0.20
    (embed
    0.20
    horn
    0.20
    iment
    0.19
    Act Density 0.018%

    No Known Activations