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

    Neuronpedia

    INDEX
    Explanations

    references to celestial bodies and astronomical phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruba
    -0.18
    Æ°
    -0.17
    ppe
    -0.16
    vant
    -0.15
    ahead
    -0.15
    iflower
    -0.15
    ampo
    -0.15
    decay
    -0.15
    AdapterFactory
    -0.14
    IMENT
    -0.14
    POSITIVE LOGITS
     planet
    0.21
    planet
    0.21
     planets
    0.19
    Extras
    0.18
     transit
    0.17
    extras
    0.17
     extras
    0.17
     Extras
    0.16
     HR
    0.16
     habit
    0.16
    Act Density 0.053%

    No Known Activations