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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    joy
    -0.16
    tainment
    -0.15
    رسÛĮ
    -0.15
    aign
    -0.15
    eval
    -0.15
    yyy
    -0.15
    esco
    -0.14
    MMdd
    -0.14
    tml
    -0.14
    EMENT
    -0.13
    POSITIVE LOGITS
     mesmo
    0.16
    oll
    0.15
    rike
    0.14
    ย
    0.14
    ITO
    0.14
    οÏħλ
    0.14
    loff
    0.14
    лÑıÑħ
    0.14
    uÃŃ
    0.14
    ØŃØ«
    0.14
    Act Density 0.463%

    No Known Activations