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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships, specifically aspects related to being a son

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ltk
    -0.59
    ########.
    -0.59
    tvguidetime
    -0.55
     virke
    -0.52
    getline
    -0.47
     Varela
    -0.47
    thérapie
    -0.47
    evt
    -0.46
    googleapis
    -0.46
    \|^{
    -0.46
    POSITIVE LOGITS
    son
    3.72
     son
    3.36
    Son
    3.33
     Son
    3.26
    SON
    3.15
     SON
    3.02
     sons
    2.73
    sons
    2.47
     Sons
    2.21
     daughter
    2.09
    Act Density 0.044%

    No Known Activations