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

    Neuronpedia

    INDEX
    Explanations

    phrases related to absence or lack of something

    oai_token-act-pair · gpt-3.5-turbo

    articles indicating the presence of a singular noun

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    redients
    -0.77
     Items
    -0.69
    agate
    -0.65
    Contents
    -0.65
    anders
    -0.64
    Types
    -0.64
     anonymously
    -0.63
     assorted
    -0.62
     Loans
    -0.62
    items
    -0.61
    POSITIVE LOGITS
     dime
    1.24
     single
    1.10
     satisfactory
    1.08
    ught
    1.02
     penny
    0.99
     shred
    0.98
     clue
    0.96
     coherent
    0.94
     definitive
    0.94
     slightest
    0.93
    Act Density 0.166%

    No Known Activations