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

    Neuronpedia

    INDEX
    Explanations

    expressions of quality or evaluation, particularly focusing on the word "good."

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

    evaluating quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     famílias
    -0.51
    ksikon
    -0.51
     vrijwilli
    -0.49
    Vía
    -0.48
    enumii
    -0.47
     CreateTagHelper
    -0.47
    樣的
    -0.47
     brancas
    -0.47
     plateado
    -0.46
    -0.46
    POSITIVE LOGITS
    Better
    0.54
     Better
    0.52
     BETTER
    0.46
    better
    0.45
    Best
    0.43
     Best
    0.41
     meilleur
    0.41
     better
    0.41
     effic
    0.40
    ness
    0.40
    Act Density 0.008%

    No Known Activations