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

    Neuronpedia

    INDEX
    Explanations

    keywords related to character interactions and transitions in gaming or storytelling

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

    followed by prepositions or commas

    np_acts-logits-general · gemini-2.0-flash

    improve service or quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.58
     JpaRepository
    -0.54
    ással
    -0.54
     SwitchCompat
    -0.51
    EnableWeb
    -0.51
     hace
    -0.51
    IVEREF
    -0.51
    horesis
    -0.50
    terdam
    -0.50
    brtc
    -0.49
    POSITIVE LOGITS
     faster
    0.93
     quicker
    0.90
     ולה
    0.90
    脚注の使い方
    0.88
     easier
    0.86
    faster
    0.86
     efficiently
    0.83
     efficacement
    0.79
     better
    0.77
     safely
    0.72
    Act Density 0.824%

    No Known Activations