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

    Neuronpedia

    INDEX
    Explanations

    mentions of events or activities related to learning and development in a workshop setting

    oai_token-act-pair · gpt-3.5-turbo

    mentions of workshops and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amy
    -0.63
    sey
    -0.63
    croft
    -0.63
     aging
    -0.61
    yll
    -0.61
    gins
    -0.60
    othy
    -0.60
    terior
    -0.60
     overw
    -0.59
     sovere
    -0.59
    POSITIVE LOGITS
    smanship
    1.00
    yrinth
    0.82
     Workshop
    0.79
     workshop
    0.79
    rador
    0.77
    craft
    0.75
    Works
    0.73
     Instruct
    0.71
    workshop
    0.71
    hops
    0.70
    Act Density 0.024%

    No Known Activations