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

    Neuronpedia

    INDEX
    Explanations

    topics related to human society and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    repeated mentions of the word "human" in various contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    **)
    -0.48
     aneurysm
    -0.45
    **
    -0.45
     élector
    -0.45
     oscu
    -0.44
     mukaan
    -0.44
     rurale
    -0.43
     Teach
    -0.43
     ventre
    -0.43
     oscura
    -0.42
    POSITIVE LOGITS
     human
    1.71
     humans
    1.49
    human
    1.46
     HUMAN
    1.43
     Human
    1.39
     humano
    1.39
    Human
    1.39
     humaine
    1.34
     humain
    1.33
     Humans
    1.29
    Act Density 0.227%

    No Known Activations