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

    Neuronpedia

    INDEX
    Explanations

    terms related to data storage size, particularly in megabytes (MB)

    oai_token-act-pair · gpt-3.5-turbo

    references to memory size measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Akron
    -0.72
    ×Ļ×
    -0.71
    cha
    -0.63
     pol
    -0.62
     Apollo
    -0.61
     Patron
    -0.61
     por
    -0.61
     Az
    -0.60
     Halloween
    -0.60
     Dayton
    -0.59
    POSITIVE LOGITS
    MB
    0.94
    ishop
    0.87
    ertodd
    0.86
    ilib
    0.82
    TeX
    0.82
    ilit
    0.82
    uilt
    0.79
     vulner
    0.78
    apixel
    0.78
    isoft
    0.77
    Act Density 0.003%

    No Known Activations