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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the word "done" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.74
    stateProvider
    -0.70
    PathVariable
    -0.69
     Sheppard
    -0.66
    guero
    -0.65
    unregister
    -0.62
     leitor
    -0.61
    déric
    -0.61
    Према
    -0.60
     jLabel
    -0.60
    POSITIVE LOGITS
     done
    3.47
    done
    2.90
     Done
    2.88
     DONE
    2.78
    Done
    2.76
    DONE
    2.43
     gedaan
    1.66
    isDone
    1.59
     doen
    1.35
     undone
    1.34
    Act Density 0.059%

    No Known Activations