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

    Neuronpedia

    INDEX
    Explanations

    numerical values and indicators of measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruz
    -0.16
    //{{
    -0.16
     (£
    -0.14
    ÏģοÏħ
    -0.14
    ãĥ³ãĥĪ
    -0.14
    vd
    -0.14
    \common
    -0.14
    atha
    -0.14
    ừa
    -0.14
    pch
    -0.14
    POSITIVE LOGITS
     tens
    0.17
     sim
    0.16
    ery
    0.16
    Ìĥ
    0.15
     hun
    0.15
    urt
    0.15
    ems
    0.14
    order
    0.14
    icans
    0.14
    ids
    0.14
    Act Density 0.083%

    No Known Activations