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

    Neuronpedia

    INDEX
    Explanations

    elements related to astronomy and the cosmos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.16
    1:0.02
    2:0.08
    3:0.13
    4:0.03
    5:0.13
    6:0.05
    7:0.10
    8:0.15
    9:0.02
    10:0.05
    11:0.03
    Negative Logits
     recruitment
    -2.37
     Wolver
    -2.28
     Bundesliga
    -2.21
     Yorkshire
    -2.21
     SQL
    -2.21
     coached
    -2.15
     recru
    -2.15
     informants
    -2.13
     Adidas
    -2.13
     interviewing
    -2.12
    POSITIVE LOGITS
     Cosmic
    3.70
     cosmos
    3.37
     cosmic
    3.37
    Cos
    3.31
     Sagan
    3.02
    Ast
    2.98
    nova
    2.95
     Cosmos
    2.91
     Hubble
    2.82
     astronomer
    2.79
    Act Density 0.001%

    No Known Activations