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

    Neuronpedia

    INDEX
    Explanations

    file directory paths including specific keywords

    oai_token-act-pair · gpt-3.5-turbo

    file path components in a computer system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reich
    -0.76
     pronoun
    -0.75
     Him
    -0.74
     tighter
    -0.73
     TAMADRA
    -0.72
     warranted
    -0.72
     soaring
    -0.71
     Cassidy
    -0.71
     buzz
    -0.71
     Carrie
    -0.70
    POSITIVE LOGITS
    src
    1.56
    modules
    1.45
    sv
    1.42
    bin
    1.38
    etc
    1.37
    lib
    1.35
    scripts
    1.34
    drivers
    1.32
    addons
    1.32
    temp
    1.30
    Act Density 0.056%

    No Known Activations