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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stm
    -0.16
    street
    -0.15
    th
    -0.14
    elik
    -0.14
    sson
    -0.14
    ahi
    -0.14
    inski
    -0.14
    em
    -0.13
    insky
    -0.13
    ives
    -0.13
    POSITIVE LOGITS
    ofilm
    0.15
    otify
    0.15
    sian
    0.14
    γκα
    0.14
    ±Ð¾ÑĤ
    0.14
    pitch
    0.14
    vatel
    0.14
     ((__
    0.14
    ATS
    0.13
    OwnProperty
    0.13
    Act Density 0.147%

    No Known Activations