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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or requests for help

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

    Follows a period and starts with "Please", "I", or "It"

    np_acts-logits-general · gemini-2.0-flash

    been tainted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TextWatcher
    -0.61
    Вам
    -0.52
     comigo
    -0.50
    kiyor
    -0.49
    couvrez
    -0.47
    Índice
    -0.47
    ToPoint
    -0.46
    ajemy
    -0.46
     سكانية
    -0.46
     orgullo
    -0.46
    POSITIVE LOGITS
     any
    1.62
     anyone
    1.60
    Any
    1.52
     Any
    1.50
     anybody
    1.46
     Anybody
    1.43
     Anyone
    1.41
    Anyone
    1.38
    anyone
    1.38
    Anybody
    1.36
    Act Density 0.424%

    No Known Activations