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

    Neuronpedia

    INDEX
    Explanations

    information related to galaxies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of galaxies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ership
    -0.80
    âķIJâķIJ
    -0.77
    erred
    -0.76
    thodox
    -0.73
    tern
    -0.71
    ointed
    -0.71
    Labor
    -0.71
    fficiency
    -0.70
    udo
    -0.70
    ovic
    -0.69
    POSITIVE LOGITS
     galaxy
    1.04
     Andromeda
    0.89
     Milky
    0.83
     galaxies
    0.80
     hots
    0.79
     gazing
    0.78
     Telescope
    0.77
    arium
    0.75
     capacitor
    0.73
     blo
    0.72
    Act Density 0.008%

    No Known Activations