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

    Neuronpedia

    INDEX
    Explanations

    references to labor rights and international labor standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awe
    -0.15
    Lit
    -0.15
     gezocht
    -0.14
    leo
    -0.14
    Redux
    -0.14
     neighborhood
    -0.14
     traveler
    -0.14
    .tell
    -0.14
     traveled
    -0.13
     rumored
    -0.13
    POSITIVE LOGITS
     tri
    0.24
     Tri
    0.22
     decent
    0.20
    trip
    0.19
     employers
    0.18
    Tri
    0.18
     Employ
    0.18
    lab
    0.17
     Labour
    0.17
    social
    0.17
    Act Density 0.015%

    No Known Activations