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

    Neuronpedia

    INDEX
    Explanations

    personal statements and affirmations

    oai_token-act-pair · gpt-3.5-turbo

    first-person singular pronouns and expressions of self-identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     antitrust
    -0.63
    ses
    -0.63
    icist
    -0.62
     Millennium
    -0.62
     Gad
    -0.59
     Annotations
    -0.56
    TPS
    -0.56
     apiece
    -0.56
     Straw
    -0.56
    earch
    -0.56
    POSITIVE LOGITS
    'm
    1.43
    've
    1.22
    'll
    1.13
     am
    1.04
     owe
    1.02
    'd
    1.00
    ronic
    0.92
     deserve
    0.90
     adore
    0.90
     hereby
    0.90
    Act Density 0.297%

    No Known Activations