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

    Neuronpedia

    INDEX
    Explanations

    terms related to science and scientific inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /down
    -0.17
    rescia
    -0.16
    lander
    -0.16
    ted
    -0.16
    iser
    -0.16
    itre
    -0.16
    loe
    -0.15
    las
    -0.15
    lands
    -0.15
    tra
    -0.15
    POSITIVE LOGITS
    /engine
    0.28
    /math
    0.25
    -fiction
    0.23
    ENCES
    0.19
    /Math
    0.19
    /art
    0.18
     fiction
    0.15
    ieten
    0.15
    /sc
    0.15
    /stat
    0.15
    Act Density 0.047%

    No Known Activations