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

    Neuronpedia

    INDEX
    Explanations

    references to healthcare and waiting areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Factory
    -0.17
    factory
    -0.16
     bed
    -0.16
    pr
    -0.15
    rous
    -0.15
    zap
    -0.14
    phet
    -0.14
    utta
    -0.14
     s
    -0.14
     factory
    -0.14
    POSITIVE LOGITS
     lobby
    0.34
     Lobby
    0.29
    lobby
    0.29
     reception
    0.25
     Reception
    0.22
     entrance
    0.18
     Entrance
    0.18
     Waiting
    0.17
     receptions
    0.17
    çİĦ
    0.16
    Act Density 0.185%

    No Known Activations