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

    Neuronpedia

    INDEX
    Explanations

    passive voice constructions and forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vá
    -0.15
    ighth
    -0.15
    agan
    -0.15
    orton
    -0.15
     Gia
    -0.14
    nea
    -0.14
    unate
    -0.14
    swire
    -0.14
    thon
    -0.14
    erton
    -0.14
    POSITIVE LOGITS
    ould
    0.13
     Ying
    0.13
    /dist
    0.13
     settles
    0.13
    shade
    0.13
     Gast
    0.13
    arda
    0.13
    ÑĨ
    0.13
    utos
    0.13
    angled
    0.12
    Act Density 0.177%

    No Known Activations