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

    Neuronpedia

    INDEX
    Explanations

    phrases related to regulatory actions and penalties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iais
    -0.15
    olean
    -0.15
    ellas
    -0.15
    ewater
    -0.15
    azer
    -0.14
    uggage
    -0.14
    HUD
    -0.14
     Infant
    -0.14
    cka
    -0.14
     iq
    -0.14
    POSITIVE LOGITS
     Workers
    0.48
     workers
    0.48
     worker
    0.40
    Workers
    0.40
     Worker
    0.39
    workers
    0.37
    -workers
    0.33
    Worker
    0.32
     injured
    0.31
    -worker
    0.30
    Act Density 0.034%

    No Known Activations