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

    Neuronpedia

    INDEX
    Explanations

    punctuations and pauses in the text

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

    Ah, what, ah

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.60
    Ӕ
    -0.57
     NSCoder
    -0.55
    StoryboardSegue
    -0.53
    httphttps
    -0.53
     ExecuteAsync
    -0.53
     kasarigan
    -0.52
    ModelSerializer
    -0.52
    rzost
    -0.52
    Panamoan
    -0.52
    POSITIVE LOGITS
     enggak
    0.49
    Oh
    0.47
     auroit
    0.47
     fédé
    0.46
     really
    0.43
     outta
    0.43
    Nobody
    0.43
    Somebody
    0.43
     Oh
    0.42
     feroit
    0.42
    Act Density 0.052%

    No Known Activations