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

    Neuronpedia

    INDEX
    Explanations

    terms related to matter, especially in the context of physics and science

    oai_token-act-pair · gpt-3.5-turbo

    references to matter and its properties in the universe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olkien
    -0.75
    ESCO
    -0.72
    eatures
    -0.69
    udeb
    -0.67
     Jarrett
    -0.66
     [|
    -0.63
    ãĥ³ãĤ¸
    -0.63
    ARP
    -0.62
     succession
    -0.62
    è¦
    -0.61
    POSITIVE LOGITS
    matter
    0.94
    cules
    0.92
    lessly
    0.91
    flows
    0.88
    ional
    0.86
    lessness
    0.83
    horn
    0.81
    flow
    0.81
    weights
    0.80
    worms
    0.75
    Act Density 0.021%

    No Known Activations