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

    Neuronpedia

    INDEX
    Explanations

    references to "pieces" and their ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    795
    -0.18
     sigh
    -0.15
    asp
    -0.14
     datap
    -0.14
    882
    -0.14
    ittal
    -0.13
    olas
    -0.13
    voir
    -0.13
    aux
    -0.13
    622
    -0.13
    POSITIVE LOGITS
     machinery
    0.23
     legislation
    0.22
     advice
    0.21
     furniture
    0.21
     scenery
    0.21
     luggage
    0.20
     footage
    0.20
     wreckage
    0.20
     territory
    0.19
     evidence
    0.19
    Act Density 0.141%

    No Known Activations