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

    Neuronpedia

    INDEX
    Explanations

    terms related to compensation and related processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    compensation for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rus
    -0.46
     uș
    -0.42
    Strict
    -0.42
     étr
    -0.42
     Gorb
    -0.41
     Hierro
    -0.41
    nrows
    -0.41
     Siete
    -0.41
    www
    -0.40
    Street
    -0.40
    POSITIVE LOGITS
     compensation
    1.30
     Compensation
    1.17
    compensation
    1.16
    Compensation
    1.08
     compens
    1.05
     Compens
    1.04
     compensate
    1.02
     compensated
    0.99
    compens
    0.97
     compensating
    0.96
    Act Density 0.006%

    No Known Activations