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

    Neuronpedia

    INDEX
    Explanations

    mentions of children, family, and play-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idak
    -0.16
    URN
    -0.15
    ucken
    -0.15
     Zá
    -0.15
    unan
    -0.15
     pubs
    -0.14
    üst
    -0.14
    otte
    -0.14
    oga
    -0.14
    ivel
    -0.14
    POSITIVE LOGITS
     Barb
    0.24
     Leg
    0.24
     Thomas
    0.23
     Fisher
    0.23
     LEG
    0.23
     Dup
    0.22
     magna
    0.21
     trains
    0.21
     Ton
    0.20
     princess
    0.20
    Act Density 0.181%

    No Known Activations