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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases expressing excess or extreme conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pread
    -0.18
    pur
    -0.18
     Chambers
    -0.15
    ttl
    -0.15
    ë¡
    -0.14
     pur
    -0.14
    down
    -0.14
    PUR
    -0.14
    WD
    -0.14
    avis
    -0.14
    POSITIVE LOGITS
    utsch
    0.15
    ãĤ¢ãĥ³
    0.15
    ollar
    0.14
    xit
    0.14
    ipa
    0.14
    ootball
    0.13
     vic
    0.13
    lys
    0.13
    appings
    0.13
     nursery
    0.13
    Act Density 0.008%

    No Known Activations