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

    Neuronpedia

    INDEX
    Explanations

    references to seasonal celebrations and rituals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.56
     lãng
    -0.54
    enumi
    -0.52
     sonnet
    -0.52
     purpoſe
    -0.51
     thinker
    -0.50
     Majefty
    -0.50
    Write
    -0.50
    Pot
    -0.49
     pleaſure
    -0.49
    POSITIVE LOGITS
    $_['
    0.72
     للمعارف
    0.63
    ImageContext
    0.62
     ritual
    0.61
     nargin
    0.60
    ´)
    0.60
    SBATCH
    0.59
    šinou
    0.59
    AndEndTag
    0.58
     lunghi
    0.55
    Act Density 0.491%

    No Known Activations