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

    Neuronpedia

    INDEX
    Explanations

    quantities related to weight or measurement in tons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to large quantities, particularly in tons

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gotten
    -0.75
    Journal
    -0.70
    Loop
    -0.69
    ournal
    -0.67
    issance
    -0.67
    Scotland
    -0.65
    Dub
    -0.65
    cknow
    -0.64
    yrinth
    -0.64
    Tokens
    -0.64
    POSITIVE LOGITS
     lbs
    0.90
    urgical
    0.89
     tons
    0.85
    umes
    0.81
     pounds
    0.80
    poons
    0.79
    ets
    0.78
    iles
    0.78
    ension
    0.77
    umatic
    0.76
    Act Density 0.014%

    No Known Activations