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

    Neuronpedia

    INDEX
    Explanations

    dates and events mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     achievement
    -0.64
     monetary
    -0.63
     untold
    -0.60
     longevity
    -0.60
     achievements
    -0.60
    OGR
    -0.59
     behavi
    -0.59
     intellectual
    -0.59
     recol
    -0.58
     elevator
    -0.57
    POSITIVE LOGITS
     31
    0.85
    ruary
    0.84
     29
    0.83
     28
    0.82
     Madness
    0.81
    furt
    0.80
     27
    0.78
     26
    0.77
    au
    0.76
    ools
    0.75
    Act Density 0.038%

    No Known Activations