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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news reporting and articles

    oai_token-act-pair · gpt-3.5-turbo

    references to news articles or journalistic reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERAL
    -0.64
    uilt
    -0.61
    ãĤª
    -0.60
    LLOW
    -0.60
    姫
    -0.59
    pite
    -0.58
    anguage
    -0.57
    ghost
    -0.56
     veter
    -0.56
    ategory
    -0.56
    POSITIVE LOGITS
     debacle
    0.84
     incident
    0.77
     fiasco
    0.76
     spree
    0.73
     above
    0.68
     revelations
    0.67
     ordeal
    0.66
     Tsarnaev
    0.66
     controversy
    0.66
    ghazi
    0.64
    Act Density 0.955%

    No Known Activations