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

    Neuronpedia

    INDEX
    Explanations

    references to actions or tasks being performed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.82
    ChildScrollView
    -0.76
     RouterModule
    -0.69
    Geplaatst
    -0.69
     Ise
    -0.68
     surla
    -0.68
    Portale
    -0.67
     welkom
    -0.66
    Diwedd
    -0.66
    </tfoot>
    -0.65
    POSITIVE LOGITS
     done
    1.59
    done
    1.34
    Doing
    1.30
     doing
    1.28
     DONE
    1.25
     Doing
    1.23
    doing
    1.23
     DOING
    1.21
     Done
    1.19
    Done
    1.18
    Act Density 0.357%

    No Known Activations