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

    Neuronpedia

    INDEX
    Explanations

    references to relationships and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issen
    -0.15
    Keywords
    -0.15
    eters
    -0.15
     keywords
    -0.15
     Exhibition
    -0.14
     Keywords
    -0.14
    etro
    -0.14
    utes
    -0.14
     values
    -0.14
    iphone
    -0.14
    POSITIVE LOGITS
     contexts
    0.23
     circles
    0.22
     everyday
    0.21
     popular
    0.20
     literature
    0.19
    popular
    0.19
     usage
    0.17
     daily
    0.17
    .scalablytyped
    0.17
    contexts
    0.16
    Act Density 0.243%

    No Known Activations