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

    Neuronpedia

    INDEX
    Explanations

    references to causation and effects in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EndInit
    -0.65
    verständlich
    -0.63
    yntaxException
    -0.63
    compromised
    -0.61
    HostException
    -0.61
    🏻
    -0.59
     EconPapers
    -0.58
     Administrativna
    -0.58
    }{*}{}
    -0.58
    Autoritní
    -0.56
    POSITIVE LOGITS
     havoc
    1.00
     harm
    0.85
     célèbres
    0.82
     célèbre
    0.75
     headaches
    0.71
     consternation
    0.70
     damage
    0.69
     mayhem
    0.68
     uproar
    0.66
     stir
    0.66
    Act Density 0.134%

    No Known Activations