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

    Neuronpedia

    INDEX
    Explanations

    codes or programming related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Notice" and related instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     outwe
    -0.83
     paran
    -0.81
     Carlton
    -0.73
     awa
    -0.73
     arri
    -0.69
     puberty
    -0.68
     assail
    -0.68
     ambassadors
    -0.68
     Crab
    -0.67
     unexplained
    -0.66
    POSITIVE LOGITS
    Output
    1.01
    PUT
    0.95
    Example
    0.94
    Usage
    0.90
    Frames
    0.88
    RAW
    0.88
    Console
    0.87
    Gener
    0.86
    {{
    0.86
    Returns
    0.85
    Act Density 0.132%

    No Known Activations