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

    Neuronpedia

    INDEX
    Explanations

    phrases related to receiving updates or special offers

    oai_token-act-pair · gpt-3.5-turbo

    references to news and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eur
    -0.79
    avery
    -0.75
    verning
    -0.74
    rifice
    -0.71
    asus
    -0.69
    arton
    -0.68
    amina
    -0.68
    agall
    -0.68
    odor
    -0.67
    iac
    -0.66
    POSITIVE LOGITS
     updates
    0.86
    ilver
    0.85
     notifications
    0.84
     Updates
    0.79
     update
    0.77
    mith
    0.74
    peak
    0.72
     notification
    0.71
    peed
    0.71
    olitan
    0.71
    Act Density 0.015%

    No Known Activations