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

    Neuronpedia

    INDEX
    Explanations

    the word "done" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PathVariable
    -0.76
    theless
    -0.69
    wab
    -0.68
     McAllister
    -0.67
    stateProvider
    -0.66
    zubauen
    -0.65
    ViewInit
    -0.64
     hés
    -0.64
    Empereur
    -0.63
     jLabel
    -0.63
    POSITIVE LOGITS
     done
    2.36
     Done
    2.03
     DONE
    2.01
    Done
    1.97
    done
    1.97
    DONE
    1.84
    isDone
    1.35
     Donegal
    1.25
     gedaan
    1.15
     undone
    1.12
    Act Density 0.049%

    No Known Activations