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

    Neuronpedia

    INDEX
    Explanations

    references to news headlines, specifically related to front-page stories or prominent candidates

    oai_token-act-pair · gpt-3.5-turbo

    references to "front page" in news or media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.76
    cles
    -0.75
    cham
    -0.73
    IRO
    -0.73
    awk
    -0.69
    ornings
    -0.69
    ilk
    -0.68
    fortune
    -0.68
    ptives
    -0.67
    dayName
    -0.67
    POSITIVE LOGITS
    runners
    1.05
    iers
    1.01
     lawn
    0.89
     porch
    0.86
    court
    0.80
    office
    0.79
     burner
    0.77
    ing
    0.77
    lines
    0.76
    ages
    0.76
    Act Density 0.026%

    No Known Activations