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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "seen"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Talia
    -0.79
    \{\\
    -0.75
    UnitTesting
    -0.72
    JspWriter
    -0.72
     mourut
    -0.69
    cioso
    -0.69
     Allegretto
    -0.64
    cherie
    -0.64
     middel
    -0.64
    Middle
    -0.63
    POSITIVE LOGITS
     seen
    3.11
     Seen
    2.87
    Seen
    2.60
    seen
    2.54
     SEEN
    2.48
     visto
    1.54
     saw
    1.41
     gezien
    1.37
     viewed
    1.26
     vistos
    1.25
    Act Density 0.110%

    No Known Activations