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

    Neuronpedia

    INDEX
    Explanations

    phrases related to signing up for newsletters or alerts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to receiving news updates and subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.79
    iciency
    -0.66
    ħĭ
    -0.66
     theorem
    -0.63
    gui
    -0.63
    uxe
    -0.63
    uthor
    -0.62
     scales
    -0.62
     grate
    -0.62
     unaccount
    -0.61
    POSITIVE LOGITS
    Trend
    0.84
     updates
    0.80
     NEWS
    0.77
     Updates
    0.76
     news
    0.75
     developments
    0.74
    NEWS
    0.71
     Breaking
    0.71
    News
    0.71
    odcast
    0.71
    Act Density 0.127%

    No Known Activations