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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical tests and data processing functions

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

    webhook, form, creature, materials, cdc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.48
     a
    -0.36
      
    -0.36
    1
    -0.35
     all
    -0.34
        
    -0.32
    2
    -0.31
    <
    -0.31
    _
    -0.30
     and
    -0.30
    POSITIVE LOGITS
    <unused14>
    1.12
    [@BOS@]
    1.12
    <unused41>
    1.12
    <unused52>
    1.12
    <unused16>
    1.11
    <unused8>
    1.11
    <unused23>
    1.11
    <unused28>
    1.11
    <pad>
    1.11
    <unused3>
    1.11
    Act Density 0.094%

    No Known Activations