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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditional statements and scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.70
     AssemblyTitle
    -0.67
    tilhe
    -0.64
    sique
    -0.61
     يتيمه
    -0.60
     Pilate
    -0.60
     insuffisamment
    -0.59
     Савезне
    -0.58
     AssemblyProduct
    -0.58
     مشين
    -0.57
    POSITIVE LOGITS
     denn
    0.49
    nessy
    0.47
    strix
    0.47
     ring
    0.46
    omitempty
    0.45
    通販
    0.44
     properly
    0.43
     well
    0.43
     fully
    0.42
    anlagen
    0.41
    Act Density 0.422%

    No Known Activations