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

    Neuronpedia

    INDEX
    Explanations

    words related to people working in various professions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "worked" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.72
    emonic
    -0.65
    xual
    -0.65
     gratification
    -0.63
    powder
    -0.63
     Bubble
    -0.62
    neum
    -0.62
    mble
    -0.61
    ibia
    -0.61
     constitu
    -0.60
    POSITIVE LOGITS
     tirelessly
    1.11
    hops
    0.97
     undercover
    0.97
     diligently
    0.96
    bench
    0.90
     collabor
    0.89
     closely
    0.88
     ethic
    0.85
     alongside
    0.81
    station
    0.81
    Act Density 0.065%

    No Known Activations