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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating limited research or knowledge on a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wikipagina
    -0.60
    WriteBarrier
    -0.60
     eccell
    -0.59
    addPreferredGap
    -0.58
     militaires
    -0.58
    noinspection
    -0.58
     normaux
    -0.57
     chaude
    -0.56
     DriverManager
    -0.55
     stedet
    -0.54
    POSITIVE LOGITS
     bislang
    0.73
     hasn
    0.68
     rarely
    0.68
     seldom
    0.68
     haven
    0.68
     bisher
    0.66
    adaptiveStyles
    0.63
     hadn
    0.59
     yet
    0.57
     belum
    0.57
    Act Density 0.653%

    No Known Activations