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

    Neuronpedia

    INDEX
    Explanations

    verbs or nouns related to being at work

    oai_token-act-pair · gpt-3.5-turbo

    references to the workplace or work-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ukrain
    -0.78
    EStream
    -0.75
    emonic
    -0.70
    laus
    -0.70
     Austral
    -0.69
     Sov
    -0.68
    Sov
    -0.67
     Bol
    -0.67
     Flavoring
    -0.65
    ĪĴ
    -0.63
    POSITIVE LOGITS
    station
    1.13
     ethic
    1.10
    aday
    1.08
    ername
    1.00
    bench
    0.96
    wear
    0.89
    fare
    0.88
    holiday
    0.84
    day
    0.83
    flows
    0.83
    Act Density 0.060%

    No Known Activations