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

    Neuronpedia

    INDEX
    Explanations

    sentences involving legal matters, actions, or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to educational or developmental stages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ?)
    -0.70
    )|
    -0.67
     Publication
    -0.63
     )]
    -0.63
    })
    -0.62
    ?]
    -0.61
    }"
    -0.60
     Fixes
    -0.59
     FTC
    -0.59
    ?).
    -0.58
    POSITIVE LOGITS
     unimaginable
    1.01
     remarkably
    0.91
     unparalleled
    0.88
     indistinguishable
    0.86
     awfully
    0.82
     unmist
    0.81
     irresistible
    0.81
     unforgettable
    0.78
     profoundly
    0.77
     virtually
    0.76
    Act Density 1.578%

    No Known Activations