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

    Neuronpedia

    INDEX
    Explanations

    keywords related to maintaining safety and remaining quiet

    oai_token-act-pair · gpt-3.5-turbo

    terms related to safety and tranquility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oret
    -0.61
    apest
    -0.61
    jection
    -0.59
    tumblr
    -0.59
     roundup
    -0.57
     LOT
    -0.57
    oby
    -0.57
     descent
    -0.57
    former
    -0.57
    bey
    -0.56
    POSITIVE LOGITS
     whilst
    0.80
     lest
    0.78
     withd
    0.73
     Rico
    0.72
     suspic
    0.70
     Ruk
    0.67
     despite
    0.67
     throats
    0.67
     Hispan
    0.65
     ashore
    0.65
    Act Density 0.146%

    No Known Activations