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

    Neuronpedia

    INDEX
    Explanations

    names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names of individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onet
    -0.85
    DragonMagazine
    -0.75
    ntil
    -0.64
    raints
    -0.63
    ocious
    -0.63
    geries
    -0.62
    :]
    -0.62
    arp
    -0.62
    amping
    -0.61
    ardless
    -0.61
    POSITIVE LOGITS
     deems
    1.26
     deem
    1.03
     sorely
    0.92
     excel
    0.91
     considers
    0.86
     cove
    0.85
     describes
    0.85
     desperately
    0.82
     undertook
    0.82
     forgot
    0.81
    Act Density 0.307%

    No Known Activations