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

    Neuronpedia

    INDEX
    Explanations

    references to solar systems and celestial objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ane
    -0.16
    ANE
    -0.14
     Geh
    -0.14
    ãĥĭãĥ¥
    -0.14
    ierte
    -0.14
     Bans
    -0.14
    recht
    -0.14
    çŃĭ
    -0.14
    .Tests
    -0.13
     tornado
    -0.13
    POSITIVE LOGITS
     Moon
    0.37
     moon
    0.37
    moon
    0.32
     Sun
    0.31
    Moon
    0.29
     sun
    0.29
     atmosphere
    0.26
     Solar
    0.25
     solar
    0.23
     heavens
    0.23
    Act Density 0.162%

    No Known Activations