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

    Neuronpedia

    INDEX
    Explanations

    words related to government officials or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "du."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Policies
    -0.76
     Conditions
    -0.73
     Wanted
    -0.72
     Sector
    -0.72
     Units
    -0.72
     Across
    -0.69
     Respond
    -0.67
     Locked
    -0.67
     Echoes
    -0.66
     Angels
    -0.65
    POSITIVE LOGITS
    du
    1.00
    pling
    0.99
    plet
    0.95
    iple
    0.92
    gment
    0.91
    plets
    0.90
    ples
    0.87
    ffer
    0.83
    ress
    0.82
    pes
    0.81
    Act Density 0.006%

    No Known Activations