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

    Neuronpedia

    INDEX
    Explanations

    phrases related to size and magnitude

    oai_token-act-pair · gpt-3.5-turbo

    words that denote significant size or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cling
    -0.82
    posted
    -0.78
    wich
    -0.76
    eve
    -0.76
    icle
    -0.74
    line
    -0.73
    nan
    -0.72
    dar
    -0.71
     Yel
    -0.71
    tag
    -0.70
    POSITIVE LOGITS
     amounts
    1.07
     quantities
    0.95
     cumbers
    0.92
     amount
    0.88
     enormous
    0.87
     mammoth
    0.85
     sums
    0.81
     earthqu
    0.81
     lengths
    0.80
     leaps
    0.80
    Act Density 0.012%

    No Known Activations