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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the verb "do" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſche
    -0.96
     Efq
    -0.90
    ChildScrollView
    -0.83
    Datuak
    -0.83
     Reſ
    -0.78
     iſt
    -0.76
     ſy
    -0.74
    </tfoot>
    -0.74
     tartalomajánló
    -0.72
     Rena
    -0.72
    POSITIVE LOGITS
     do
    1.28
     does
    1.19
     did
    1.17
     done
    1.01
     indeed
    0.90
     DID
    0.89
     doing
    0.88
     DOES
    0.83
     Do
    0.82
     gedaan
    0.82
    Act Density 0.102%

    No Known Activations