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

    Neuronpedia

    INDEX
    Explanations

    concepts related to processes and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ismet
    -0.14
    Matchers
    -0.14
    orest
    -0.14
    eyen
    -0.14
    shal
    -0.14
    /current
    -0.14
    íĭ±
    -0.14
    acht
    -0.13
    endar
    -0.13
    allel
    -0.13
    POSITIVE LOGITS
    agra
    0.17
    cation
    0.16
    anon
    0.14
     Roths
    0.14
    redients
    0.14
    andre
    0.14
    ابÙĦ
    0.14
    èµ·æĿ¥
    0.14
    beck
    0.14
    /install
    0.14
    Act Density 0.819%

    No Known Activations