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

    Neuronpedia

    INDEX
    Explanations

    references to cell phones

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cell phones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rix
    -0.74
    ansson
    -0.65
    Ļ½
    -0.64
     Polk
    -0.63
    stad
    -0.62
    ivari
    -0.62
    phase
    -0.62
     Cumber
    -0.61
    pure
    -0.61
     Triangle
    -0.61
    POSITIVE LOGITS
    phones
    0.87
     phones
    0.83
     subscriptions
    0.76
     messenger
    0.75
    ographs
    0.75
    BOOK
    0.74
     charger
    0.74
    phone
    0.73
     handset
    0.72
     subscribers
    0.72
    Act Density 0.030%

    No Known Activations