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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     monetary
    -0.64
     achievement
    -0.62
     behavi
    -0.61
     brilliance
    -0.60
     intangible
    -0.60
     recol
    -0.59
     intellectual
    -0.58
     longevity
    -0.58
     genius
    -0.58
     spoiler
    -0.57
    POSITIVE LOGITS
     28
    0.83
     31
    0.83
     29
    0.83
    ruary
    0.82
    ools
    0.80
     Madness
    0.79
     26
    0.78
    furt
    0.78
     27
    0.78
    eteenth
    0.76
    Act Density 0.021%

    No Known Activations