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

    Neuronpedia

    INDEX
    Explanations

    references to official departments or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sut
    -0.18
    ÌĨ
    -0.17
    abis
    -0.15
    eree
    -0.14
    ups
    -0.14
    fall
    -0.14
    ëĮĢíķľ
    -0.14
    RLF
    -0.14
    cess
    -0.14
    trap
    -0.14
    POSITIVE LOGITS
    al
    0.32
    alist
    0.23
    artment
    0.23
    als
    0.21
    ally
    0.21
    ial
    0.20
    份
    0.19
    ular
    0.18
    alis
    0.18
    wide
    0.17
    Act Density 0.030%

    No Known Activations