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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that express contrast or clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Adverbial sentence starters

    np_acts-logits-general · gemini-2.0-flash

    specific clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "]);
    -0.79
    "];
    -0.77
     ""),
    -0.77
    ']);
    -0.76
    <bos>
    -0.76
    "]="
    -0.75
    "));
    -0.75
    ]--;
    -0.75
    ++]=
    -0.74
    enumii
    -0.73
    POSITIVE LOGITS
    ,
    1.19
     CIL
    0.56
    ،
    0.54
     entanto
    0.54
    setupUi
    0.52
     Huguen
    0.52
    IonicModule
    0.51
     quads
    0.51
     NSCoder
    0.50
     thri
    0.50
    Act Density 0.526%

    No Known Activations