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

    Neuronpedia

    INDEX
    Explanations

    references to science and its various disciplines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lass
    -0.18
    rescia
    -0.17
    loe
    -0.17
    iser
    -0.17
    tra
    -0.16
    /down
    -0.16
    neo
    -0.16
    ting
    -0.16
    ter
    -0.15
    lander
    -0.15
    POSITIVE LOGITS
    -fiction
    0.25
    /math
    0.24
    /engine
    0.24
    ENCES
    0.18
    /Math
    0.18
     fiction
    0.18
    /art
    0.18
    fully
    0.17
    /stat
    0.16
    y
    0.16
    Act Density 0.047%

    No Known Activations