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

    Neuronpedia

    INDEX
    Explanations

    personal anecdotes and stories about family

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     umo
    -0.67
     Jä
    -0.65
     surpl
    -0.64
     Simult
    -0.64
     parall
    -0.59
     asos
    -0.57
     kasa
    -0.57
     Illus
    -0.56
     Gorb
    -0.55
     makro
    -0.55
    POSITIVE LOGITS
    <bos>
    0.70
     parents
    0.58
    preco
    0.56
     school
    0.53
     dad
    0.52
    parents
    0.52
     kids
    0.51
     kid
    0.50
     PeEnEo
    0.50
     Parents
    0.50
    Act Density 0.636%

    No Known Activations