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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

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

    what is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -1.07
     autorytatywna
    -1.06
    <unused16>
    -1.00
    <unused3>
    -1.00
    <unused51>
    -1.00
    <unused28>
    -1.00
    <unused43>
    -1.00
    <unused41>
    -1.00
    <unused8>
    -1.00
    <unused23>
    -1.00
    POSITIVE LOGITS
     in
    0.40
      
    0.39
     and
    0.39
     
    0.36
     about
    0.35
     is
    0.35
     par
    0.35
    ↵
    0.34
     on
    0.34
     with
    0.34
    Act Density 0.002%

    No Known Activations