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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ily
    -0.16
    iable
    -0.14
    .mozilla
    -0.14
     bunny
    -0.14
    agle
    -0.14
     isr
    -0.14
    zyÄĩ
    -0.14
    isted
    -0.14
    ponential
    -0.14
    λά
    -0.13
    POSITIVE LOGITS
    /off
    0.19
    shore
    0.19
    ancock
    0.15
    دÛĮد
    0.14
    -demand
    0.14
     behalf
    0.14
    ritz
    0.14
    å·§
    0.14
    UPS
    0.14
    .handleChange
    0.13
    Act Density 0.043%

    No Known Activations