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

    instances of the word "headlines" and related news terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ework
    -0.78
    orney
    -0.71
    parent
    -0.70
     crafts
    -0.70
    tein
    -0.69
    ee
    -0.66
     laborers
    -0.64
    uana
    -0.63
    sis
    -0.62
    ees
    -0.61
    POSITIVE LOGITS
     headlines
    1.09
    waves
    0.83
    icter
    0.81
     notoriety
    0.74
     Hebdo
    0.74
    æ©
    0.73
    Ø©
    0.71
     enthusi
    0.68
     Vaugh
    0.67
    rovers
    0.67
    Act Density 0.058%

    No Known Activations