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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest excess, exaggeration, or criticism

    oai_token-act-pair · gpt-3.5-turbo

    references to excessive or over-the-top situations or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.81
     Juliet
    -0.70
     Ranger
    -0.68
    itaire
    -0.68
     Bravo
    -0.67
     Bits
    -0.65
     Gazette
    -0.62
     WD
    -0.62
     Cassidy
    -0.62
     Doe
    -0.60
    POSITIVE LOGITS
    arching
    1.08
    represented
    1.08
    sized
    1.08
    whelming
    1.07
    emphasis
    1.07
    priced
    1.07
    performing
    1.06
    ealous
    1.02
    educated
    1.01
    regulated
    1.00
    Act Density 0.027%

    No Known Activations