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

    Neuronpedia

    INDEX
    Explanations

    references to variables and their manipulations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.85
     Chriſt
    -0.77
     purpoſe
    -0.75
     aimable
    -0.71
     Chriftian
    -0.69
     greateſt
    -0.67
     Cæsar
    -0.66
     Perſ
    -0.66
     ſeveral
    -0.65
     occaf
    -0.65
    POSITIVE LOGITS
    '),
    0.82
    '):
    0.82
    '))
    0.81
    __':
    0.81
     rospy
    0.76
    "))
    0.76
    '])
    0.73
     EconPapers
    0.73
    ']=='
    0.72
    ')],
    0.72
    Act Density 0.034%

    No Known Activations