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

    Neuronpedia

    INDEX
    Explanations

    words that indicate possession or belonging to a specific entity

    oai_token-act-pair · gpt-3.5-turbo

    the term "respective" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arer
    -0.82
    lam
    -0.82
    uve
    -0.79
    avis
    -0.79
    cher
    -0.74
    ker
    -0.74
    bay
    -0.71
    chens
    -0.70
    fitting
    -0.70
    ctors
    -0.70
    POSITIVE LOGITS
     respective
    1.08
     strengths
    0.86
     sides
    0.85
     merits
    0.85
     administrations
    0.85
     halves
    0.85
     branches
    0.82
     genders
    0.81
     colours
    0.81
     stripes
    0.79
    Act Density 0.023%

    No Known Activations