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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different aspects of work such as productivity, skills, and commitment

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with creative or professional work and its products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenant
    -0.78
     Samar
    -0.70
     Brit
    -0.68
    interstitial
    -0.66
    wered
    -0.65
    imov
    -0.64
    lehem
    -0.63
    ionage
    -0.63
    yip
    -0.63
     Stern
    -0.62
    POSITIVE LOGITS
     habits
    1.13
     choices
    1.12
     repertoire
    1.07
     regimen
    1.01
     endeavors
    1.00
     philosophies
    1.00
     practices
    0.96
     histories
    0.95
     arsenal
    0.95
    ographies
    0.94
    Act Density 0.426%

    No Known Activations