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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "me" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    muz
    -0.18
    wayne
    -0.17
    m
    -0.17
    pci
    -0.16
    mas
    -0.16
    wy
    -0.16
     оди
    -0.16
    pte
    -0.15
    -exclusive
    -0.15
    sum
    -0.15
    POSITIVE LOGITS
    ister
    0.24
    asured
    0.22
    ISTER
    0.20
    adow
    0.20
    iosis
    0.20
    adows
    0.20
    asurable
    0.19
    isters
    0.18
    asuring
    0.18
    ulen
    0.18
    Act Density 0.029%

    No Known Activations