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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to organizations, people, and places

    oai_token-act-pair · gpt-3.5-turbo

    the end of text markers indicating sections or pieces of information that are complete

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.68
     grav
    -0.64
     dotted
    -0.63
     quo
    -0.62
     flare
    -0.62
     sabotage
    -0.61
     trooper
    -0.60
     reciproc
    -0.60
     needles
    -0.59
     expulsion
    -0.59
    POSITIVE LOGITS
    chel
    0.82
    Else
    0.81
    tons
    0.80
    oran
    0.79
    atson
    0.77
     Own
    0.77
     Happ
    0.76
    alt
    0.76
    esley
    0.75
    edes
    0.75
    Act Density 0.212%

    No Known Activations