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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment or expressions of inability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    political and societal commentary, especially discussions about economics, race, and education policy.

    oai_token-act-pair · gpt-5-nanoTriggered by @jrosseruk
    New Auto-Interp
    Negative Logits
     objectMapper
    -0.70
     Mather
    -0.64
     Hiller
    -0.60
     genomen
    -0.60
    Kesimpulan
    -0.60
    avond
    -0.60
     Heine
    -0.59
     gerichtet
    -0.58
    هما
    -0.58
     verwijderen
    -0.58
    POSITIVE LOGITS
    t
    1.41
     not
    0.96
     Not
    0.90
    not
    0.89
    Not
    0.88
     wasnt
    0.85
     CANT
    0.83
     wont
    0.81
     isnt
    0.81
     wouldnt
    0.79
    Act Density 0.079%

    No Known Activations