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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the first-person pronoun "Me"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reign
    -0.17
    격
    -0.16
    rush
    -0.16
    wer
    -0.15
    alez
    -0.15
    mas
    -0.15
     reign
    -0.15
    stadt
    -0.15
    rey
    -0.15
    pus
    -0.15
    POSITIVE LOGITS
    adows
    0.25
    adow
    0.24
    zzo
    0.24
    asured
    0.23
    andering
    0.22
    asuring
    0.22
    gal
    0.21
    zz
    0.21
    iosis
    0.21
    ander
    0.21
    Act Density 0.029%

    No Known Activations