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

    Neuronpedia

    INDEX
    Explanations

    expressions of obligation or duty

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing obligations or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ula
    -0.72
    ul
    -0.70
    packs
    -0.69
    oric
    -0.68
    dream
    -0.67
    imposed
    -0.66
    UL
    -0.66
    cule
    -0.66
     Kramer
    -0.62
    Arab
    -0.62
    POSITIVE LOGITS
    ĺħ
    0.88
     ought
    0.88
     beh
    0.87
    EStream
    0.86
    igham
    0.84
    cffff
    0.83
     rightfully
    0.81
    ratulations
    0.81
    entimes
    0.81
    ĪĴ
    0.79
    Act Density 0.006%

    No Known Activations