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

    Neuronpedia

    INDEX
    Explanations

    news headlines or article titles ending with "Read more" links

    oai_token-act-pair · gpt-3.5-turbo

    high activation values indicating certain topics or themes related to news and current events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.71
     hooked
    -0.69
     answ
    -0.66
    Ļ½
    -0.66
     honored
    -0.61
     homebrew
    -0.60
     XL
    -0.59
    mbuds
    -0.59
     Compact
    -0.59
    scill
    -0.58
    POSITIVE LOGITS
    than
    0.87
    Comments
    0.77
    perse
    0.75
    rug
    0.70
    dar
    0.70
    prev
    0.69
    fal
    0.68
    origin
    0.67
    notations
    0.67
    Fra
    0.67
    Act Density 0.059%

    No Known Activations