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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and words indicating contrast or exception in statements

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

    introducing contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.60
    GEBURTSDATUM
    -0.56
    المشاركات
    -0.55
    Portály
    -0.53
    Kjelder
    -0.52
    Bibliograf
    -0.52
    InjectAttribute
    -0.51
     gawas
    -0.51
    tonode
    -0.50
     onBind
    -0.49
    POSITIVE LOGITS
    tiva
    0.36
    Alas
    0.36
     alas
    0.36
     Alas
    0.35
    param
    0.34
     FAT
    0.34
    VENTORY
    0.34
    ENEZ
    0.33
    fat
    0.33
     Fat
    0.33
    Act Density 0.024%

    No Known Activations