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

    Neuronpedia

    INDEX
    Explanations

    terms related to various types and properties of spectra

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assis
    -0.17
    antan
    -0.16
    ábado
    -0.15
    nown
    -0.15
    angan
    -0.15
    ungan
    -0.14
    ams
    -0.14
    ÄĻd
    -0.14
    isi
    -0.14
    ivar
    -0.13
    POSITIVE LOGITS
    ardy
    0.15
    NAL
    0.15
    mek
    0.15
    typings
    0.15
    werk
    0.15
    shint
    0.15
    avers
    0.14
    YLES
    0.14
    Ú¯ÛĮر
    0.14
    phony
    0.14
    Act Density 0.011%

    No Known Activations