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

    Neuronpedia

    INDEX
    Explanations

    laws and legal references

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     aen
    -1.25
     ibi
    -1.07
     meis
    -1.07
     fta
    -1.07
     fte
    -1.04
     magis
    -1.03
     mef
    -1.02
     fep
    -1.00
     ftu
    -1.00
     sii
    -1.00
    POSITIVE LOGITS
     Act
    1.22
    Act
    1.10
     act
    0.99
     acts
    0.88
    act
    0.87
     Acts
    0.84
    Acts
    0.79
     acted
    0.79
     ACT
    0.79
    ACT
    0.70
    Act Density 0.062%

    No Known Activations