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

    Neuronpedia

    INDEX
    Explanations

    commas in the text

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

    year followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.89
     ſta
    -0.87
     myſelf
    -0.85
     leſs
    -0.85
    leſs
    -0.78
     ſche
    -0.77
     ſch
    -0.77
     eſſ
    -0.76
     juſ
    -0.75
     ſeveral
    -0.75
    POSITIVE LOGITS
    ,
    0.78
     (
    0.55
     ,
    0.53
      
    0.51
    ",
    0.47
    ”,
    0.46
    ↵
    0.46
     in
    0.45
     on
    0.44
     –
    0.42
    Act Density 0.072%

    No Known Activations