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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "waive" and its associated forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bry
    -0.64
     Klass
    -0.60
     cog
    -0.60
     dispon
    -0.58
     Bree
    -0.58
     ilust
    -0.58
     kog
    -0.58
     perla
    -0.56
     GROSS
    -0.54
     Silk
    -0.54
    POSITIVE LOGITS
    wa
    2.68
     Wa
    2.66
    Wa
    2.60
     wa
    2.49
    WA
    2.30
     WA
    1.90
     waive
    1.52
     waiver
    1.49
     waived
    1.49
     waivers
    1.47
    Act Density 0.123%

    No Known Activations