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

    Neuronpedia

    INDEX
    Explanations

    references to total amounts or sums within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Total
    -0.22
     Total
    -0.20
     total
    -0.20
    _total
    -0.20
     TOTAL
    -0.19
     totaled
    -0.18
    _TOTAL
    -0.17
    zens
    -0.16
     totaling
    -0.16
    _totals
    -0.15
    POSITIVE LOGITS
    led
    0.34
    itarian
    0.34
    izing
    0.26
    izers
    0.25
    istic
    0.23
     strangers
    0.23
    izer
    0.23
    ities
    0.22
    iser
    0.21
    LED
    0.21
    Act Density 0.031%

    No Known Activations