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

    Neuronpedia

    INDEX
    Explanations

    HTML attributes and assignment statements

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.84
    SequentialGroup
    -0.84
    <unused74>
    -0.81
    <unused8>
    -0.80
    <unused28>
    -0.80
    <pad>
    -0.80
    <unused14>
    -0.80
    <unused79>
    -0.80
    <unused16>
    -0.80
    <unused41>
    -0.80
    POSITIVE LOGITS
     "
    0.62
    ("
    0.59
    ="
    0.58
    :@"
    0.52
     '
    0.52
    ["
    0.52
     “
    0.51
    ='
    0.51
    ('
    0.51
     ‘
    0.47
    Act Density 0.001%

    No Known Activations