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

    Neuronpedia

    INDEX
    Explanations

    words associated with quantitative measurements or indicators of performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AMS
    -0.16
    άλι
    -0.15
    λÏĮ
    -0.15
    nee
    -0.14
    ITEM
    -0.14
     Meaning
    -0.14
    icken
    -0.14
     precedent
    -0.14
     Robotics
    -0.13
     Campos
    -0.13
    POSITIVE LOGITS
    orra
    0.16
    ting
    0.15
    uters
    0.15
    utorial
    0.15
     اÙĦأسر
    0.13
    sum
    0.13
    infinity
    0.13
    rolled
    0.13
    avar
    0.13
     PT
    0.13
    Act Density 0.026%

    No Known Activations