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

    Neuronpedia

    INDEX
    Explanations

    words and phrases expressing greetings or welcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imgur
    -0.86
     devriez
    -0.74
     Spie
    -0.73
     ModelExpression
    -0.72
    protoimpl
    -0.72
    fortawesome
    -0.71
    AdapterView
    -0.69
    pageY
    -0.69
    styleUrls
    -0.68
    Dina
    -0.67
    POSITIVE LOGITS
     welcome
    3.52
     Welcome
    3.01
    welcome
    2.96
     welcomed
    2.94
     WELCOME
    2.90
    Welcome
    2.77
     welcomes
    2.72
     welcoming
    2.71
    WELCOME
    2.61
     bienvenida
    2.31
    Act Density 0.042%

    No Known Activations