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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to the term "Stars"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Stars," likely in relation to a sports team or awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vice
    -0.78
    ufact
    -0.74
    tons
    -0.70
    aterial
    -0.68
    duction
    -0.68
     Canaver
    -0.67
     millenn
    -0.66
    armac
    -0.66
    ĵĺ
    -0.66
    ibaba
    -0.65
    POSITIVE LOGITS
    cream
    1.47
    hips
    1.38
    bucks
    0.97
    ystem
    0.87
     Stars
    0.84
    mith
    0.82
    ilver
    0.81
    burst
    0.80
    manship
    0.79
    stars
    0.78
    Act Density 0.016%

    No Known Activations