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

    Neuronpedia

    INDEX
    Explanations

    references to celestial bodies and astronomical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Moon
    -0.19
     moon
    -0.18
    Moon
    -0.17
    ãĤ¿ãĥ¼
    -0.16
     Aston
    -0.16
    ék
    -0.15
    lander
    -0.15
    ãĥ¯ãĥ¼
    -0.14
     planetary
    -0.14
    oyo
    -0.14
    POSITIVE LOGITS
     Aqu
    0.29
     Sag
    0.27
     Leo
    0.26
     Cy
    0.25
     Scor
    0.25
    Leo
    0.23
     Camel
    0.23
    Aqu
    0.23
     Cap
    0.22
     Vir
    0.22
    Act Density 0.074%

    No Known Activations