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

    Neuronpedia

    INDEX
    Explanations

    references to tribal identities or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tra
    -0.19
    ipers
    -0.17
    _EOF
    -0.15
    fsp
    -0.15
    erate
    -0.15
    ween
    -0.15
    лаб
    -0.15
    iers
    -0.14
    peria
    -0.14
    ÏģÏĮÏĤ
    -0.14
    POSITIVE LOGITS
    æ³Ĭ
    0.19
    bed
    0.17
    olini
    0.16
    bing
    0.16
    atical
    0.16
    kov
    0.15
    bles
    0.15
    ust
    0.15
    ble
    0.14
    utors
    0.14
    Act Density 0.010%

    No Known Activations