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

    Neuronpedia

    INDEX
    Explanations

    instances of data or entities being transferred from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "transferred."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    194
    -0.67
    Eth
    -0.65
    à©
    -0.65
    Ale
    -0.64
     Howe
    -0.62
    {{
    -0.62
    FORE
    -0.61
    é¾įå
    -0.59
    Hol
    -0.59
     Answer
    -0.59
    POSITIVE LOGITS
     transfers
    1.05
     transferred
    1.02
     transferring
    0.98
     transfer
    0.87
    terness
    0.86
    llular
    0.86
    Transfer
    0.77
    metry
    0.76
    ients
    0.74
    icut
    0.73
    Act Density 0.011%

    No Known Activations