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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate continuity or persistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abin
    -0.15
    osu
    -0.14
    ac
    -0.14
    /from
    -0.14
    abyrin
    -0.14
    sein
    -0.14
    acia
    -0.13
    ula
    -0.13
     Settlement
    -0.13
    phe
    -0.13
    POSITIVE LOGITS
    ders
    0.22
    íģ¼
    0.16
    LEGAL
    0.16
    ickers
    0.15
    ainen
    0.15
    812
    0.15
    opal
    0.15
    CHANT
    0.14
    nings
    0.14
    nech
    0.14
    Act Density 0.027%

    No Known Activations