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

    Neuronpedia

    INDEX
    Explanations

    celestial bodies such as stars

    oai_token-act-pair · gpt-3.5-turbo

    mentions of stars, particularly in the context of entertainment or celestial references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -0.87
    »Ĵ
    -0.84
    apons
    -0.81
    odcast
    -0.80
    nsic
    -0.78
    ibaba
    -0.75
    icultural
    -0.75
    perties
    -0.71
    utral
    -0.70
    utics
    -0.70
    POSITIVE LOGITS
     stars
    1.34
    hips
    1.06
    stars
    1.04
     star
    1.00
    cream
    1.00
    light
    0.84
    Stars
    0.82
    bucks
    0.81
     Stars
    0.81
    nova
    0.79
    Act Density 0.007%

    No Known Activations