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

    Neuronpedia

    INDEX
    Explanations

    mentions or descriptions of 'black holes'

    oai_token-act-pair · gpt-3.5-turbo

    references to black holes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.80
    IGH
    -0.77
    nesota
    -0.72
     livest
    -0.72
    igel
    -0.70
    iage
    -0.68
    annis
    -0.66
    ivery
    -0.64
    NetMessage
    -0.63
    skill
    -0.63
    POSITIVE LOGITS
    izons
    0.86
     hole
    0.84
    hole
    0.81
    worm
    0.78
    arium
    0.76
    worms
    0.75
     Hole
    0.74
     rays
    0.73
     emitting
    0.72
    eers
    0.71
    Act Density 0.005%

    No Known Activations