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

    Neuronpedia

    INDEX
    Explanations

    keywords related to news topics like politics, technology, and events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods at the end of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bra
    -0.83
     spoiler
    -0.79
    ment
    -0.77
     heav
    -0.76
     regenerate
    -0.73
     fishes
    -0.72
     instinct
    -0.72
     defe
    -0.72
     uncom
    -0.71
     minion
    -0.70
    POSITIVE LOGITS
     Similarly
    1.34
     Likewise
    1.20
     Similar
    1.18
     Meanwhile
    1.16
     Another
    1.16
     Later
    1.09
     Previously
    1.08
     However
    1.06
     Additionally
    1.05
     Interestingly
    1.05
    Act Density 0.555%

    No Known Activations