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

    Neuronpedia

    INDEX
    Explanations

    singular words related to specific topics

    oai_token-act-pair · gpt-3.5-turbo

    discussions or references to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignt
    -0.85
    inyl
    -0.69
    ATES
    -0.69
    ardo
    -0.69
    ramid
    -0.67
    olyn
    -0.65
    zman
    -0.63
    conn
    -0.63
    ypes
    -0.63
    omp
    -0.62
    POSITIVE LOGITS
    matter
    1.14
     matter
    1.07
     topic
    1.05
     topics
    1.00
     discussed
    0.90
     debated
    0.84
    topic
    0.82
     area
    0.81
     Matter
    0.81
    ivity
    0.79
    Act Density 0.038%

    No Known Activations