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

    Neuronpedia

    INDEX
    Explanations

    calls to action encouraging the reader to try or test something

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

    The token "try" or its variations

    np_acts-logits-general · gemini-2.0-flash

    try this, try it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arşivlendi
    -0.57
    GOTREF
    -0.56
    rungsseite
    -0.52
     الرياضيه
    -0.49
    AccessFile
    -0.48
     cuota
    -0.47
    Hentet
    -0.47
    verwijspagina
    -0.46
    ----</
    -0.45
    ⪜
    -0.45
    POSITIVE LOGITS
     Try
    0.46
     try
    0.44
    Try
    0.43
     different
    0.42
     luck
    0.40
     suerte
    0.40
     kræ
    0.39
    different
    0.39
     طعم
    0.38
    try
    0.38
    Act Density 0.134%

    No Known Activations