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

    Neuronpedia

    INDEX
    Explanations

    references to established norms and conditions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seamnă
    -0.70
    InjectAttribute
    -0.61
    ientôt
    -0.60
    assertRaises
    -0.58
     '/':
    -0.55
    :✨
    -0.54
    MLLoader
    -0.53
     sappi
    -0.52
    PYX
    -0.52
    èvent
    -0.51
    POSITIVE LOGITS
     maupun
    0.62
     lẫn
    0.62
     GetEnumerator
    0.58
     OMITBAD
    0.58
    Aholisi
    0.58
     يتيمه
    0.56
    slidesToShow
    0.55
     or
    0.54
    だけでなく
    0.52
    ibilité
    0.52
    Act Density 0.662%

    No Known Activations