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

    Neuronpedia

    INDEX
    Explanations

    content that emphasizes the communication and understanding of scientific knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     paste
    -0.15
    åĬ¨çĶŁæĪIJ
    -0.15
     Blades
    -0.14
    ores
    -0.14
    elman
    -0.14
     Kelly
    -0.14
     stations
    -0.14
    ads
    -0.14
    UT
    -0.14
    oyal
    -0.14
    POSITIVE LOGITS
     explanations
    0.21
     explaining
    0.19
     understandable
    0.18
     explanation
    0.18
     complexity
    0.17
    REATED
    0.17
     Complexity
    0.17
    explained
    0.17
    Explanation
    0.17
    nap
    0.17
    Act Density 0.181%

    No Known Activations