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

    Neuronpedia

    INDEX
    Explanations

    themes relating to activities and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     churn
    -0.18
     sift
    -0.16
    uggle
    -0.15
     whipped
    -0.15
     jog
    -0.15
    PEND
    -0.15
     cultiv
    -0.14
     stalk
    -0.14
     indu
    -0.14
     sá»±
    -0.14
    POSITIVE LOGITS
    enting
    0.24
    otyping
    0.23
     parenting
    0.22
    ancing
    0.22
     painting
    0.22
     lawy
    0.22
     coloring
    0.22
     singing
    0.22
     shopping
    0.21
     eating
    0.21
    Act Density 0.511%

    No Known Activations