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

    Neuronpedia

    INDEX
    Explanations

    elements related to confirmation and deletion actions in user interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.96
    ValueStyle
    -0.94
     myſelf
    -0.92
     Beſ
    -0.89
     itſelf
    -0.86
     fevere
    -0.82
     Monfieur
    -0.81
     ſever
    -0.80
     reaſon
    -0.80
     ſtate
    -0.78
    POSITIVE LOGITS
    DeleteMapping
    0.68
    DialogInterface
    0.46
    dataTables
    0.45
     del
    0.43
    telser
    0.42
     vált
    0.42
     rencana
    0.41
    UTF
    0.41
    ล
    0.40
     @
    0.40
    Act Density 0.058%

    No Known Activations