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

    Neuronpedia

    INDEX
    Explanations

    references to the word "who" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.67
    はじめに
    -0.67
    Tembelea
    -0.65
     autorytatywna
    -0.65
     betweenstory
    -0.64
     Biôgrafia
    -0.60
    WebServlet
    -0.59
    findpost
    -0.57
    XmlAccessType
    -0.57
    utives
    -0.56
    POSITIVE LOGITS
     else
    0.78
     among
    0.76
    ops
    0.73
    among
    0.69
     am
    0.68
     amongst
    0.68
     AMONG
    0.64
    opi
    0.61
    oping
    0.58
     TF
    0.57
    Act Density 0.118%

    No Known Activations