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

    Neuronpedia

    INDEX
    Explanations

    references to chat conversations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of chat-related contexts or environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mandela
    -0.63
     encount
    -0.61
    CVE
    -0.61
    è¡
    -0.60
     assum
    -0.57
     homeland
    -0.56
     consecutive
    -0.54
     landfall
    -0.54
    ":"/
    -0.54
     Aven
    -0.54
    POSITIVE LOGITS
    anooga
    1.35
    bots
    1.21
    room
    1.21
    rooms
    1.18
    ters
    1.06
    ty
    1.04
    bot
    0.98
    tered
    0.98
    ting
    0.97
    acters
    0.94
    Act Density 0.024%

    No Known Activations