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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or groupings of multiple entities

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or patterns referring to the concept of "each of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertodd
    -0.80
     surpr
    -0.75
     contam
    -0.69
    aji
    -0.68
     agre
    -0.68
    ersive
    -0.67
    ileaks
    -0.66
    WER
    -0.64
     reim
    -0.64
     orche
    -0.63
    POSITIVE LOGITS
     course
    0.72
    icial
    0.70
     Richards
    0.70
     sorts
    0.67
     majors
    0.66
     Presidency
    0.65
     Governors
    0.64
     Southeast
    0.62
     Fulton
    0.62
     Tampa
    0.61
    Act Density 0.100%

    No Known Activations