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

    Neuronpedia

    INDEX
    Explanations

    terms related to workers and their compensation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obbies
    -0.17
    rous
    -0.15
     lance
    -0.15
     æij
    -0.15
    .Layout
    -0.15
    esses
    -0.14
     Gale
    -0.14
    088
    -0.14
    etroit
    -0.14
    лиÑĨ
    -0.14
    POSITIVE LOGITS
     compensation
    0.41
     Compensation
    0.36
     compens
    0.28
     compensate
    0.25
     comp
    0.24
    Comp
    0.22
     Comp
    0.21
    comp
    0.21
     compensated
    0.20
    -comp
    0.18
    Act Density 0.013%

    No Known Activations