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

    Neuronpedia

    INDEX
    Explanations

    sections of text labeled as "Introduction."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſte
    -0.61
    expandindo
    -0.56
    windowFixed
    -0.54
     queſta
    -0.53
    PropertyChanging
    -0.52
     diſt
    -0.52
     canst
    -0.50
    shadowRadius
    -0.49
    cloudflare
    -0.49
     Prov
    -0.49
    POSITIVE LOGITS
    Introduction
    0.55
     circonstances
    0.53
    intro
    0.52
     relieved
    0.52
     dermed
    0.52
    introduction
    0.50
     Einleitung
    0.50
     berlebihan
    0.49
    relief
    0.49
     navideños
    0.49
    Act Density 0.274%

    No Known Activations