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

    Neuronpedia

    INDEX
    Explanations

    phrases or references to laws and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eling
    -0.17
    ovy
    -0.15
    ovice
    -0.14
    vr
    -0.14
    ller
    -0.14
    ares
    -0.13
    prim
    -0.13
    aire
    -0.13
    gar
    -0.13
    ella
    -0.13
    POSITIVE LOGITS
     mere
    0.16
    afort
    0.16
    imson
    0.14
    ichern
    0.14
    acie
    0.14
    entai
    0.14
    contres
    0.14
    cheiden
    0.14
    ÂŃi
    0.14
     there
    0.13
    Act Density 0.184%

    No Known Activations