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

    Neuronpedia

    INDEX
    Explanations

    statements about human nature and societal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĸ
    -0.15
    undler
    -0.15
    æĥij
    -0.15
    ahat
    -0.15
    ารย
    -0.14
    azzo
    -0.14
    arget
    -0.14
    ubu
    -0.14
    keleton
    -0.14
    ümÃ¼ÅŁ
    -0.14
    POSITIVE LOGITS
     wired
    0.25
     creatures
    0.23
    nt
    0.21
     bomb
    0.18
     attracted
    0.17
     born
    0.17
     wiring
    0.17
     creature
    0.16
     complex
    0.16
     Creatures
    0.16
    Act Density 0.068%

    No Known Activations