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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rumors and claims

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rumors and speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nice
    -0.72
    alone
    -0.67
    artney
    -0.67
    elsh
    -0.67
    inctions
    -0.66
    nea
    -0.65
    urden
    -0.64
    drivers
    -0.64
     Governors
    -0.62
    Interstitial
    -0.62
    POSITIVE LOGITS
     rumors
    1.18
     rumor
    1.15
     rumours
    1.09
     swirling
    1.03
     circulating
    1.00
     abound
    0.95
     surrounding
    0.93
     circling
    0.93
     regarding
    0.92
     circulated
    0.92
    Act Density 0.080%

    No Known Activations