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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns ('I', 'we', 'she') followed by specific related actions or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "I" and expressions of personal sentiment or agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undy
    -0.69
    oras
    -0.66
    è¦ļéĨĴ
    -0.64
    ixt
    -0.64
    ormal
    -0.63
    代
    -0.62
     BaseType
    -0.61
    Journal
    -0.59
    ãĥ¼ãĥĨ
    -0.59
    ĺħ
    -0.59
    POSITIVE LOGITS
     nonetheless
    1.45
     nevertheless
    1.43
     also
    1.07
     still
    1.06
     didn
    1.05
     couldn
    1.04
     alas
    1.03
     ain
    1.01
     never
    1.00
    'll
    0.97
    Act Density 0.194%

    No Known Activations