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

    Neuronpedia

    INDEX
    Explanations

    references to scientific theories and concepts related to astrophysics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Techniques
    -0.17
     Guar
    -0.16
     Technique
    -0.15
     techniques
    -0.15
    onu
    -0.14
    ãĥªãĤ¢
    -0.14
     âĵĺ
    -0.14
     teknik
    -0.14
     technique
    -0.13
    asco
    -0.13
    POSITIVE LOGITS
     explanations
    0.39
     explanation
    0.39
     explaining
    0.30
     Explanation
    0.29
     explain
    0.28
     mechanism
    0.28
     scenarios
    0.27
     scenario
    0.27
     explan
    0.27
     predictions
    0.26
    Act Density 0.111%

    No Known Activations