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

    Neuronpedia

    INDEX
    Explanations

    references to individuals, particularly through the use of pronouns

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

    he/she followed by verbs of saying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oky
    -0.55
    NameInMap
    -0.53
    ByVersion
    -0.52
    cpy
    -0.49
     Valky
    -0.49
    ыгана
    -0.49
     AsyncTask
    -0.48
    ezy
    -0.48
    oxys
    -0.48
     nonUne
    -0.47
    POSITIVE LOGITS
     defaultstate
    0.50
     urged
    0.47
     said
    0.47
    Παραπομπές
    0.47
     вікісторінку
    0.46
     şöyle
    0.45
     następnie
    0.45
     aliento
    0.45
     stating
    0.45
     reiter
    0.44
    Act Density 0.029%

    No Known Activations