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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence transitions that enhance the flow of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )”.
    -0.80
    "]).
    -0.77
    "',
    -0.69
    wherein
    -0.69
    )"),
    -0.69
    ']").
    -0.69
     tevens
    -0.68
    |$.
    -0.67
    melidir
    -0.67
    (""));
    -0.67
    POSITIVE LOGITS
     thôi
    0.86
     guys
    0.85
     but
    0.83
     anyway
    0.83
     maybe
    0.81
     something
    0.81
     disambiguazione
    0.77
     really
    0.77
     too
    0.69
    Anyway
    0.69
    Act Density 0.321%

    No Known Activations