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

    Neuronpedia

    INDEX
    Explanations

    descriptions of actions or events in a narrative context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     inev
    -1.41
     maneu
    -1.38
     disagre
    -1.37
     reluct
    -1.36
     depic
    -1.34
     kasa
    -1.34
     abstrait
    -1.34
     suscep
    -1.33
     encomp
    -1.32
     indestru
    -1.32
    POSITIVE LOGITS
     albeit
    0.68
     yet
    0.63
     vibrant
    0.62
     reliable
    0.62
     efficient
    0.60
    Reparto
    0.59
    لكن
    0.59
    Même
    0.58
    Edición
    0.58
     pero
    0.58
    Act Density 0.147%

    No Known Activations