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

    Neuronpedia

    INDEX
    Explanations

    repetitive references to the word "one"

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

    nobody or anyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )="
    -0.48
    AISSEE
    -0.46
    $/,
    -0.45
     GenerationType
    -0.45
    RenderAtEndOf
    -0.44
    "><?=
    -0.44
    vensis
    -0.42
     opérés
    -0.42
    Примітки
    -0.42
    ナメント
    -0.42
    POSITIVE LOGITS
     nobody
    1.07
     Nadie
    1.03
    Nobody
    1.01
     anyone
    1.00
     nadie
    0.98
     Niemand
    0.98
    anyone
    0.96
    Nadie
    0.96
    nobody
    0.96
     Nobody
    0.96
    Act Density 0.008%

    No Known Activations