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

    Neuronpedia

    INDEX
    Explanations

    references to identical entities or concepts in various contexts

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

    "same" followed by referring noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ctivité
    -0.41
    Spann
    -0.39
    Shel
    -0.36
    <?
    -0.36
    ßt
    -0.34
    Cant
    -0.34
    ERGY
    -0.33
    Psalms
    -0.32
     тебе
    -0.32
    preneurs
    -0.31
    POSITIVE LOGITS
     same
    0.93
     desselben
    0.80
    same
    0.78
     mesmas
    0.75
     dasselbe
    0.71
     selben
    0.71
     medesimo
    0.71
     gleiche
    0.69
     dieselbe
    0.69
     derselben
    0.67
    Act Density 0.024%

    No Known Activations