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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news headlines

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the symbol ')' indicating the end of parentheses or clauses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irlf
    -0.61
    haus
    -0.58
     respons
    -0.58
    racuse
    -0.56
    ition
    -0.53
    ozo
    -0.53
    ãĥł
    -0.52
    WithNo
    -0.51
    ccess
    -0.51
    ulhu
    -0.50
    POSITIVE LOGITS
    Reuters
    0.64
     BEL
    0.61
     REUTERS
    0.61
     Protesters
    0.61
    elsen
    0.56
    UTERS
    0.55
    ANK
    0.55
     stocks
    0.53
    tty
    0.53
    uers
    0.53
    Act Density 0.018%

    No Known Activations