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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation that signal the end of sentences or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bragg
    -0.83
     بيها
    -0.83
    straw
    -0.76
    aData
    -0.69
    zelle
    -0.69
     Schot
    -0.68
     MacGregor
    -0.67
    zura
    -0.66
    dialogs
    -0.66
    agé
    -0.66
    POSITIVE LOGITS
    +#+
    0.83
    ])->
    0.80
    Tania
    0.79
    %"),
    0.78
    verwijspagina
    0.78
    />";
    0.74
     catalogues
    0.72
    pertino
    0.71
    ════════
    0.70
    er
    0.69
    Act Density 0.681%

    No Known Activations