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

    Neuronpedia

    INDEX
    Explanations

    references to sample sizes and sampling processes in research contexts

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

    statistical samples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.68
     electricidad
    -0.47
     Byr
    -0.47
     üzere
    -0.46
     dirigir
    -0.46
    Cuánt
    -0.43
     direta
    -0.41
    躇
    -0.41
    flexDirection
    -0.40
     marito
    -0.40
    POSITIVE LOGITS
     samples
    1.72
     Samples
    1.70
    Samples
    1.63
    samples
    1.57
     sample
    1.56
    Sample
    1.54
     Sample
    1.51
    sample
    1.51
     SAMPLE
    1.45
     SAMPLES
    1.44
    Act Density 0.032%

    No Known Activations