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

    Neuronpedia

    INDEX
    Explanations

    text related to newspaper editorials

    oai_token-act-pair · gpt-3.5-turbo

    references to editorials in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llan
    -0.77
    agne
    -0.76
    cles
    -0.75
    rell
    -0.72
    imilar
    -0.72
    roo
    -0.71
     Rover
    -0.69
    adows
    -0.69
    gging
    -0.68
    risome
    -0.68
    POSITIVE LOGITS
     editorial
    0.94
     cartoons
    0.93
     editor
    0.88
     Editorial
    0.85
     cartoon
    0.80
     commentary
    0.80
    izing
    0.77
     endorsements
    0.77
     flair
    0.74
     judgment
    0.74
    Act Density 0.014%

    No Known Activations