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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the level of attention or importance given to various topics or subjects

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

    preceding "attention," "deserves," or "get"

    np_acts-logits-general · gemini-2.0-flash

    receiving or deserving attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jegyzetek
    -0.56
     Monfieur
    -0.53
     Jefus
    -0.49
    istics
    -0.48
     idée
    -0.47
    istically
    -0.47
    وصلات
    -0.47
     plezier
    -0.46
     numerically
    -0.46
     myſelf
    -0.45
    POSITIVE LOGITS
    0.86
    RenderAtEndOf
    0.79
     nahilalakip
    0.75
     attention
    0.69
    migrationBuilder
    0.67
    AnchorTagHelper
    0.62
     ATTENTION
    0.62
    attention
    0.60
     Infórmanos
    0.58
    ніципа
    0.57
    Act Density 0.201%

    No Known Activations