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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating statements, claims, or assertions

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

    "I" followed by preference statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.76
    DockStyle
    -0.69
    XmlAccessType
    -0.66
    BeginInit
    -0.66
    setVerticalGroup
    -0.65
    <unused52>
    -0.65
    <unused74>
    -0.65
    <unused43>
    -0.65
    <unused8>
    -0.65
    <unused16>
    -0.65
    POSITIVE LOGITS
     Rabu
    0.35
     bahwa
    0.34
     Er
    0.31
     cuál
    0.29
     mukaan
    0.29
     généraux
    0.29
     personnalisé
    0.28
     admitir
    0.28
     проведение
    0.28
     stratégies
    0.28
    Act Density 0.195%

    No Known Activations