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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "we're" and variations of it indicating presence or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.18
    ungan
    -0.16
     å¹
    -0.15
    224
    -0.14
     Pell
    -0.14
    ag
    -0.14
    cloak
    -0.14
    unc
    -0.14
     smoke
    -0.14
     conv
    -0.14
    POSITIVE LOGITS
    üh
    0.16
     Cain
    0.15
    èĨ
    0.15
    adlo
    0.14
    ickt
    0.14
    aday
    0.14
     Spicer
    0.14
    ))),
    0.14
    InSection
    0.14
    idden
    0.13
    Act Density 0.053%

    No Known Activations