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

    Neuronpedia

    INDEX
    Explanations

    phrases related to greetings and introductions in a conversational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _lifetime
    -0.15
     ÑĪÑĤ
    -0.15
    eltas
    -0.15
    rell
    -0.14
    orris
    -0.14
     Bloss
    -0.14
    uly
    -0.14
    릴
    -0.14
    496
    -0.14
     Broad
    -0.14
    POSITIVE LOGITS
     hello
    0.25
     greetings
    0.22
     greeting
    0.22
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.21
    Greetings
    0.21
     Hello
    0.19
     welcome
    0.19
    hello
    0.18
     greet
    0.18
    Hello
    0.18
    Act Density 0.141%

    No Known Activations