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

    Neuronpedia

    INDEX
    Explanations

    legal or official terms and requirements related to declarations, testimony, and transparency

    oai_token-act-pair · gpt-3.5-turbo

    references to legal and regulatory requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itars
    -0.68
     mell
    -0.66
     Anniversary
    -0.64
    ipel
    -0.64
    ï¸
    -0.63
     metaphors
    -0.62
     Rhythm
    -0.60
    BSD
    -0.60
     rejoice
    -0.59
     Endless
    -0.58
    POSITIVE LOGITS
     competence
    0.85
     factual
    0.78
     elector
    0.78
    udic
    0.76
     consent
    0.76
     impartial
    0.74
     dossier
    0.73
     electors
    0.73
    worthiness
    0.72
     constitu
    0.71
    Act Density 0.803%

    No Known Activations