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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "will."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amps
    -0.67
     Pict
    -0.66
     Extras
    -0.66
    BuyableInstoreAndOnline
    -0.65
     Tracker
    -0.64
     Modified
    -0.62
     Sources
    -0.60
    amped
    -0.60
     Concept
    -0.60
     Measures
    -0.60
    POSITIVE LOGITS
     gladly
    1.28
    iam
    1.11
     forever
    1.05
     someday
    1.04
     inevitably
    1.03
     happily
    0.96
     NEVER
    0.96
    fulness
    0.95
     doubtless
    0.94
    ow
    0.93
    Act Density 0.168%

    No Known Activations