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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and stories, including reflections, anecdotes, and personal opinions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Became
    -0.74
    iencies
    -0.71
    orks
    -0.70
     Ago
    -0.69
    hips
    -0.67
    renches
    -0.66
    storms
    -0.65
    reys
    -0.64
    css
    -0.64
    doms
    -0.64
    POSITIVE LOGITS
     favourite
    1.29
     favorite
    1.28
     own
    1.21
     biggest
    1.09
     favorites
    1.08
     consolation
    1.08
     strongest
    1.06
     preferred
    1.03
     rightful
    1.03
     choice
    1.02
    Act Density 9.456%

    No Known Activations