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

    Neuronpedia

    INDEX
    Explanations

    phrases related to duties and obligations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _crc
    -0.16
    .FILL
    -0.16
    ÙģاÙĦ
    -0.15
    eland
    -0.15
    arResult
    -0.15
    unma
    -0.14
    arend
    -0.14
     jlong
    -0.14
    γά
    -0.14
    SAFE
    -0.14
    POSITIVE LOGITS
    cht
    0.15
     Savage
    0.15
    leton
    0.15
    chl
    0.15
     Ob
    0.15
    UMAN
    0.14
     objective
    0.14
    ucc
    0.14
    abra
    0.14
     superv
    0.14
    Act Density 0.002%

    No Known Activations