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

    Neuronpedia

    INDEX
    Explanations

    phrases and descriptions related to government service or political positions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "served" and its variations, indicating past roles or positions held by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    00007
    -0.64
    apest
    -0.63
    pex
    -0.63
     stumbling
    -0.61
    razil
    -0.59
    STEP
    -0.59
     converter
    -0.57
    rians
    -0.57
    ãĤ¦ãĤ¹
    -0.56
    ãĥ¤
    -0.55
    POSITIVE LOGITS
     alongside
    0.82
     concurrently
    0.72
     adm
    0.71
    emate
    0.70
     colleg
    0.70
    imony
    0.69
    lyak
    0.68
     horm
    0.67
     faithfully
    0.67
     consecut
    0.67
    Act Density 0.034%

    No Known Activations