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

    Neuronpedia

    INDEX
    Explanations

    the proper noun "Ward" followed by a numerical value, possibly referring to people or places

    oai_token-act-pair · gpt-3.5-turbo

    the name "Ward" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gdala
    -0.87
    ãĥĪ
    -0.85
    ctions
    -0.82
    ivia
    -0.81
    ogene
    -0.81
    ãĥ¤
    -0.80
    kered
    -0.79
    alogue
    -0.77
    hedral
    -0.77
    urity
    -0.77
    POSITIVE LOGITS
    robe
    1.66
    ynski
    0.93
    ings
    0.86
    ages
    0.84
    ens
    0.84
    lock
    0.81
    ell
    0.78
    een
    0.77
    hips
    0.77
    wick
    0.76
    Act Density 0.023%

    No Known Activations