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

    Neuronpedia

    INDEX
    Explanations

    phrases related to items being on shelves

    oai_token-act-pair · gpt-3.5-turbo

    references to shelves and their contents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nel
    -0.83
    nell
    -0.66
     oral
    -0.66
    IENT
    -0.64
    SL
    -0.63
     Emir
    -0.62
    slow
    -0.62
     Trib
    -0.59
    elope
    -0.59
     Valley
    -0.59
    POSITIVE LOGITS
     shelves
    1.67
     shelf
    1.03
    ĸļ
    0.97
    mith
    0.93
    uggest
    0.86
    ãĤ©
    0.83
     clerks
    0.81
     challeng
    0.79
    andise
    0.77
     stocked
    0.77
    Act Density 0.012%

    No Known Activations