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

    Neuronpedia

    INDEX
    Explanations

    phrases that express exceeding expectations or limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     helst
    -0.61
    PropertyChanging
    -0.61
     mulighed
    -0.58
     referenties
    -0.56
    strategia
    -0.56
    cetin
    -0.56
    Schneider
    -0.56
     kasarigan
    -0.56
    marvin
    -0.56
    enterOuterAlt
    -0.55
    POSITIVE LOGITS
     beyond
    1.61
    YOND
    1.60
     Beyond
    1.59
     BEYOND
    1.58
    Beyond
    1.53
    beyond
    1.49
    delà
    1.16
     delà
    0.88
     betweenstory
    0.87
     transcend
    0.87
    Act Density 0.084%

    No Known Activations