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

    Neuronpedia

    INDEX
    Explanations

    phrases related to galaxies

    oai_token-act-pair · gpt-3.5-turbo

    references to "galactic" themes and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOOK
    -0.73
    orters
    -0.63
    uncture
    -0.63
     fateful
    -0.63
     established
    -0.62
     compr
    -0.62
    erous
    -0.62
     RIP
    -0.61
     archived
    -0.60
    akening
    -0.60
    POSITIVE LOGITS
    axy
    1.15
    gal
    1.10
    axies
    1.06
     ILCS
    0.93
    pha
    0.84
    actic
    0.83
    odon
    0.83
    actus
    0.83
    iev
    0.81
    itary
    0.79
    Act Density 0.010%

    No Known Activations