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

    Neuronpedia

    INDEX
    Explanations

    mentions of duties, responsibilities, obligations, and tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to rituals and ceremonies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Worse
    -0.63
    essim
    -0.63
     disrupting
    -0.63
    moil
    -0.63
     disrupt
    -0.62
    blocking
    -0.61
     losers
    -0.61
     headlines
    -0.60
     disrupted
    -0.59
     derail
    -0.59
    POSITIVE LOGITS
     wonderful
    0.87
     honour
    0.84
     utmost
    0.82
     blessed
    0.80
     lovely
    0.79
     dignity
    0.79
     nour
    0.78
     honoured
    0.78
     entrusted
    0.77
     wonderfully
    0.75
    Act Density 1.370%

    No Known Activations