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

    Neuronpedia

    INDEX
    Explanations

    information related to financial contracts or performance metrics

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

    penalty, reduction, loss, or cost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tavo
    -0.34
     Schwe
    -0.32
    ỏ
    -0.30
     Former
    -0.30
     former
    -0.29
    clearInterval
    -0.28
    र्व
    -0.27
     Toward
    -0.27
     Mont
    -0.27
     Montes
    -0.27
    POSITIVE LOGITS
     penalty
    1.05
    penalty
    0.89
     penalties
    0.89
    Penalty
    0.87
     Penalty
    0.87
     reduction
    0.78
     penal
    0.76
     downgrade
    0.75
     '\\;'
    0.72
     deduction
    0.71
    Act Density 0.146%

    No Known Activations