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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acers
    -0.78
    amp
    -0.76
    lee
    -0.75
    ashes
    -0.74
    marks
    -0.74
    jobs
    -0.73
    icons
    -0.73
    apes
    -0.73
    masters
    -0.71
    Examples
    -0.69
    POSITIVE LOGITS
     hemisphere
    1.02
     trope
    1.02
     particular
    1.00
     century
    1.00
     venerable
    0.93
     enigmatic
    0.92
     continent
    0.91
     country
    0.91
     newfound
    0.91
     generation
    0.88
    Act Density 0.129%

    No Known Activations