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

    Neuronpedia

    INDEX
    Explanations

    phrases that promote values such as compassion and respect

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

    Followed by "user"

    np_acts-logits-general · gemini-2.0-flash

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.63
    Билгалдахарш
    -0.56
    setVerticalGroup
    -0.56
    الحياه
    -0.54
     marty
    -0.52
     незавершена
    -0.49
    ItemLayout
    -0.49
    ugeot
    -0.48
    __((
    -0.48
     externi
    -0.48
    POSITIVE LOGITS
     eşofman
    0.40
     صوتيه
    0.39
    cambrian
    0.39
    IBOutlet
    0.39
     excellence
    0.37
     dignité
    0.37
     vermogen
    0.37
     jakość
    0.36
     ucapnya
    0.35
    baomidou
    0.35
    Act Density 0.139%

    No Known Activations