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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases or expressions in conversations

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

    demonstrative pronoun "that"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Autorisations
    -0.47
    VersionUID
    -0.46
    blockList
    -0.45
    Insight
    -0.42
     вікісторінку
    -0.42
    sizeCache
    -0.41
    endor
    -0.40
    toBeTruthy
    -0.40
    mpro
    -0.40
    jur
    -0.39
    POSITIVE LOGITS
    那
    1.01
     aquel
    0.84
     aquella
    0.84
    あの
    0.81
     那
    0.79
     daquele
    0.79
    那個
    0.78
    那个
    0.77
    的那
    0.75
    那位
    0.71
    Act Density 0.012%

    No Known Activations