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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific components or aspects of something

    oai_token-act-pair · gpt-3.5-turbo

    references to key elements or components related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.72
    ubs
    -0.72
     istg
    -0.71
    keys
    -0.71
    ãĤ¼ãĤ¦ãĤ¹
    -0.71
     teasp
    -0.70
    aries
    -0.70
    dayName
    -0.69
    eches
    -0.68
    pots
    -0.67
    POSITIVE LOGITS
     contention
    0.88
     life
    0.82
     our
    0.75
     persuasion
    0.69
     heroism
    0.69
     unification
    0.69
     gameplay
    0.68
     this
    0.67
     determining
    0.67
     existence
    0.67
    Act Density 0.141%

    No Known Activations