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

    Neuronpedia

    INDEX
    Explanations

    greetings and friendly salutations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Greetings or salutations

    np_acts-logits-general · gemini-2.0-flash

    greetings and closings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.52
     esternos
    -0.52
    AccessorTable
    -0.51
    Identyfik
    -0.50
    >${
    -0.49
    jsonwebtoken
    -0.49
    naud
    -0.48
    └──
    -0.47
    //
    -0.47
    TestingModule
    -0.47
    POSITIVE LOGITS
     everyone
    0.87
     everybody
    0.76
     Everyone
    0.71
    Witam
    0.68
     👋
    0.68
     hello
    0.67
    everyone
    0.67
     again
    0.65
     guys
    0.64
     fellow
    0.64
    Act Density 0.093%

    No Known Activations