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

    Neuronpedia

    INDEX
    Explanations

    forms of "to be" and "to have" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jenter
    -0.15
    zdy
    -0.14
    ertz
    -0.14
    OMB
    -0.14
    raft
    -0.13
    atti
    -0.13
    tah
    -0.13
    ENTRY
    -0.13
    rates
    -0.13
    .tm
    -0.13
    POSITIVE LOGITS
    ogo
    0.15
    å¦Ļ
    0.14
     ActionTypes
    0.14
    nu
    0.13
    _ARCHIVE
    0.13
    .BorderColor
    0.13
     Dos
    0.13
    Dos
    0.13
     từng
    0.13
    iel
    0.13
    Act Density 0.201%

    No Known Activations