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

    Neuronpedia

    INDEX
    Explanations

    intensifiers or adverbs that amplify descriptions

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

    modified by intensifiers "extremely" or "incredibly"

    np_acts-logits-general · gemini-2.0-flash

    intensified adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgumentParser
    -0.69
     parlor
    -0.63
    LayoutPanel
    -0.61
    Salon
    -0.57
     informée
    -0.56
    </tfoot>
    -0.56
    exitRule
    -0.55
     CURIAM
    -0.55
     Ballot
    -0.54
     виправивши
    -0.54
    POSITIVE LOGITS
    huge
    1.05
     huge
    1.04
    extremely
    0.97
     Huge
    0.93
    Huge
    0.93
     extremely
    0.92
     enormous
    0.89
    Extremely
    0.88
     tremendous
    0.88
     Extremely
    0.87
    Act Density 0.149%

    No Known Activations