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

    Neuronpedia

    INDEX
    Explanations

    instances of social interaction and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /io
    -0.15
     Demand
    -0.15
    iyon
    -0.15
     ìķĮìķĦ
    -0.15
     Supporting
    -0.14
    /misc
    -0.14
    нин
    -0.14
    erra
    -0.14
     excer
    -0.14
    .lookup
    -0.14
    POSITIVE LOGITS
     tell
    0.34
     explain
    0.34
     explaining
    0.32
     telling
    0.32
     sharing
    0.30
    tell
    0.30
    åijĬè¯ī
    0.30
     Tell
    0.30
     explanation
    0.29
     tells
    0.28
    Act Density 0.529%

    No Known Activations