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

    Neuronpedia

    INDEX
    Explanations

    legal or authoritative terms, possibly related to laws or regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to authority and power in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riad
    -0.76
     Mell
    -0.69
    Gil
    -0.69
    eor
    -0.68
    algia
    -0.68
    eday
    -0.67
    rio
    -0.66
    ÃŃa
    -0.65
     Dwell
    -0.65
    00200000
    -0.64
    POSITIVE LOGITS
     powers
    0.90
     conferred
    0.85
    Reviewer
    0.81
    hell
    0.81
     delegated
    0.78
     creep
    0.77
     vested
    0.75
     exerc
    0.73
     ashore
    0.73
    uits
    0.72
    Act Density 0.022%

    No Known Activations