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

    Neuronpedia

    INDEX
    Explanations

    personal actions or decisions taken by the individual

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "I" and its associated actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irlf
    -0.65
     Gale
    -0.64
    tnc
    -0.64
     Allied
    -0.64
     Rolls
    -0.64
     Yon
    -0.62
     Amid
    -0.61
     Georgian
    -0.60
    groupon
    -0.60
     rebellion
    -0.58
    POSITIVE LOGITS
    'm
    1.32
    've
    1.13
     recommend
    1.06
    'll
    1.03
     prefer
    1.00
    EEE
    0.99
     personally
    0.99
     suppose
    0.99
     guess
    0.98
     assume
    0.97
    Act Density 0.233%

    No Known Activations