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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to the name "Wallace."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name Wallace

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mal
    -0.82
    amins
    -0.79
    aic
    -0.77
    mine
    -0.77
    joined
    -0.76
    mits
    -0.76
    icably
    -0.74
    rity
    -0.72
    ibal
    -0.71
    lia
    -0.71
    POSITIVE LOGITS
     Wallace
    1.12
     Ellis
    0.79
     Cros
    0.78
     Stevens
    0.75
     Williams
    0.73
     Walters
    0.72
     Strait
    0.72
     Walls
    0.70
     Borders
    0.70
     Hampton
    0.69
    Act Density 0.032%

    No Known Activations