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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ate" in various contexts related to eating and consumption

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

    eating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.59
    脚注の使い方
    -0.57
     InputDecoration
    -0.55
    Honduras
    -0.52
     Funk
    -0.52
     Portugal
    -0.52
     hawa
    -0.51
    guisement
    -0.51
     مشين
    -0.51
    Portugal
    -0.51
    POSITIVE LOGITS
     ate
    1.40
     Ate
    1.39
    Ate
    1.32
     ATE
    0.94
    ate
    0.69
     eaten
    0.66
    ATE
    0.59
    até
    0.59
    .*")]
    0.54
     ateliers
    0.50
    Act Density 0.005%

    No Known Activations