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

    Neuronpedia

    INDEX
    Explanations

    phrases and descriptions of physical sensations and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     levy
    -0.67
     tariffs
    -0.66
     lobbied
    -0.66
     levied
    -0.65
     championed
    -0.62
    otide
    -0.62
     Clause
    -0.61
     incentiv
    -0.61
     responsibly
    -0.61
     rhet
    -0.61
    POSITIVE LOGITS
     emptiness
    1.01
     lifeless
    0.93
     darkness
    0.88
    âĢ¦"
    0.85
     indist
    0.79
    âĢ¦."
    0.79
     hallucinations
    0.77
     invisible
    0.76
     sensations
    0.75
     blurry
    0.75
    Act Density 0.316%

    No Known Activations