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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating transformation or becoming something significant

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     always
    -0.17
     currently
    -0.16
     former
    -0.16
    eza
    -0.15
    ĸ
    -0.15
    chi
    -0.15
     ALWAYS
    -0.14
     older
    -0.14
    ERCHANT
    -0.14
    former
    -0.14
    POSITIVE LOGITS
     household
    0.19
    dlg
    0.19
     fixture
    0.19
     overnight
    0.18
    oren
    0.18
    fixture
    0.17
     Overnight
    0.16
    æĸ°çļĦ
    0.16
    amura
    0.16
     fixtures
    0.16
    Act Density 0.140%

    No Known Activations