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

    Neuronpedia

    INDEX
    Explanations

    terms related to evaluating network performance in simulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¬
    -0.15
    ç¯Ħ
    -0.15
     inoc
    -0.15
    anio
    -0.14
     Spin
    -0.13
    ACHI
    -0.13
     hazır
    -0.13
    otope
    -0.13
     hemisphere
    -0.13
    subtotal
    -0.13
    POSITIVE LOGITS
     que
    0.30
     queue
    0.29
     fairness
    0.28
     Queue
    0.27
     fair
    0.27
     Que
    0.25
    Queue
    0.25
    queue
    0.24
     admission
    0.24
    Que
    0.24
    Act Density 0.064%

    No Known Activations