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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey a sense of identity and self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilians
    -0.18
    ICO
    -0.17
    :name
    -0.15
    ãģ«è¦ĭ
    -0.15
    OMET
    -0.14
    chaft
    -0.14
    elenium
    -0.14
    umont
    -0.14
    awe
    -0.14
    indr
    -0.14
    POSITIVE LOGITS
     someone
    0.17
     Someone
    0.16
     undergone
    0.15
     somebody
    0.15
    someone
    0.15
    oad
    0.14
    cul
    0.14
    ict
    0.14
     Uhr
    0.14
    Someone
    0.14
    Act Density 0.145%

    No Known Activations