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

    Neuronpedia

    INDEX
    Explanations

    significant interactions and expressions of power dynamics

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

    the restaurant, her lady, soon as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.73
     MainAxisSize
    -0.60
     (\<
    -0.59
     ―――――
    -0.58
    ⪜
    -0.58
    trendy
    -0.58
    <unused8>
    -0.58
    <unused51>
    -0.57
    <unused41>
    -0.57
    <pad>
    -0.57
    POSITIVE LOGITS
     uska
    0.44
    Vegeu
    0.39
    ativna
    0.37
     tears
    0.35
     propOrder
    0.34
     fossero
    0.34
     dejes
    0.33
     oír
    0.33
     muttering
    0.33
    MessageOf
    0.33
    Act Density 0.037%

    No Known Activations