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

    Neuronpedia

    INDEX
    Explanations

    keywords related to manual control or procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to "manual" in various contexts, often associated with procedures, labor, or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.89
    kok
    -0.87
    rak
    -0.86
    ments
    -0.79
    apest
    -0.77
    ihar
    -0.74
    gdala
    -0.73
    amus
    -0.73
    wick
    -0.70
    roud
    -0.69
    POSITIVE LOGITS
     dexterity
    1.18
     transmission
    1.00
     typew
    0.98
     transmissions
    0.86
     lockout
    0.85
    ized
    0.82
     override
    0.82
     labor
    0.78
     laborers
    0.75
     labour
    0.75
    Act Density 0.056%

    No Known Activations