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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "create" and its variations, indicating a focus on construction or generation actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iw
    -0.18
    hel
    -0.17
    OrCreate
    -0.17
    ndata
    -0.15
    ships
    -0.15
    urb
    -0.15
    geh
    -0.15
    Element
    -0.15
    nid
    -0.15
    ãģĬãĤĬ
    -0.15
    POSITIVE LOGITS
     havoc
    0.22
    OrUpdate
    0.20
    /edit
    0.19
    éĢł
    0.18
    inine
    0.17
    สร
    0.17
    /open
    0.17
    /delete
    0.16
    /update
    0.16
    oucher
    0.16
    Act Density 0.090%

    No Known Activations