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

    Neuronpedia

    INDEX
    Explanations

    references to numerical goals and targets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooks
    -0.72
    inside
    -0.67
    DOS
    -0.67
    ublic
    -0.67
    afort
    -0.65
    uddin
    -0.65
    Ô
    -0.65
    Newsletter
    -0.64
    oard
    -0.64
    aples
    -0.64
    POSITIVE LOGITS
     range
    0.89
     date
    0.88
    posts
    0.82
    setting
    0.81
     deadline
    0.78
     thresholds
    0.77
     timeframe
    0.77
     ranges
    0.76
     2025
    0.75
     2030
    0.75
    Act Density 0.024%

    No Known Activations