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

    Neuronpedia

    INDEX
    Explanations

    threatening statements or commands

    oai_token-act-pair · gpt-3.5-turbo

    urgent requests or pleas for help

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agonists
    -0.66
    pmwiki
    -0.61
     strangely
    -0.59
     Grimoire
    -0.58
    odcast
    -0.58
     Canaver
    -0.57
     Hearthstone
    -0.56
    prisingly
    -0.56
     Hels
    -0.56
     oddly
    -0.56
    POSITIVE LOGITS
    sic
    1.10
    '"
    1.10
     âĢ¦"
    1.06
    !'"
    0.99
     ..."
    0.99
    .'"
    0.96
    }"
    0.88
    '."
    0.86
    !"
    0.85
    ,'"
    0.84
    Act Density 0.552%

    No Known Activations