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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the end of an article or piece of content

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the age or timeliness of an article

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.68
     awoken
    -0.66
    untarily
    -0.66
    icent
    -0.65
    WAY
    -0.63
     (%)
    -0.63
    auga
    -0.63
    iola
    -0.62
    reet
    -0.62
    MET
    -0.61
    POSITIVE LOGITS
     Paste
    0.73
    govtrack
    0.71
     captcha
    0.69
     headlines
    0.67
     Links
    0.66
     sponsored
    0.66
     Column
    0.65
     headlined
    0.65
     links
    0.64
     Hua
    0.63
    Act Density 0.345%

    No Known Activations