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

    Neuronpedia

    INDEX
    Explanations

    the presence of structure or formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     }}"></
    -0.97
    omiast
    -0.91
     entanto
    -0.90
    -};
    -0.80
    Ayrıca
    -0.79
     furthermore
    -0.79
     moreover
    -0.79
     Etc
    -0.78
    Etc
    -0.77
     andererseits
    -0.76
    POSITIVE LOGITS
    When
    0.88
     When
    0.82
    Welcome
    0.81
    Dear
    0.80
     Welcome
    0.79
    Imagine
    0.77
    Hello
    0.77
    Greetings
    0.76
    During
    0.76
     Hello
    0.74
    Act Density 0.529%

    No Known Activations