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

    Neuronpedia

    INDEX
    Explanations

    information related to tragic events or incidents resulting in death

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of dates or references to specific events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    $$
    -0.68
    wine
    -0.67
    expensive
    -0.67
    hov
    -0.64
    ripp
    -0.64
    vest
    -0.63
    ©¶æ¥µ
    -0.62
    hips
    -0.62
    MODE
    -0.61
    RL
    -0.61
    POSITIVE LOGITS
     behalf
    1.33
    shore
    1.12
     occasion
    1.12
    etime
    1.04
    erous
    1.01
     arrival
    1.00
     shores
    0.97
    site
    0.97
    eday
    0.97
     Sundays
    0.95
    Act Density 0.229%

    No Known Activations