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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "Me" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alez
    -0.17
     Reign
    -0.16
    pus
    -0.16
    rush
    -0.16
    olut
    -0.16
    wer
    -0.15
    stadt
    -0.15
    격
    -0.15
    rey
    -0.15
    mas
    -0.15
    POSITIVE LOGITS
    adows
    0.24
    adow
    0.24
    asured
    0.23
    zzo
    0.22
    iosis
    0.21
    asuring
    0.21
    zz
    0.21
    cca
    0.21
    asures
    0.21
    ander
    0.21
    Act Density 0.027%

    No Known Activations