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

    Neuronpedia

    INDEX
    Explanations

    references to sample size and related statistical metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defStyleAttr
    -0.60
     electricidad
    -0.56
     finanzas
    -0.52
     civilización
    -0.51
     dirigir
    -0.51
     direta
    -0.51
     graças
    -0.51
    lihatan
    -0.50
    Fordítás
    -0.50
     politiker
    -0.49
    POSITIVE LOGITS
     Sample
    1.18
     sample
    1.13
    Sample
    1.11
     SAMPLE
    1.05
    SAMPLE
    1.04
     Samples
    1.02
    sample
    0.99
     samples
    0.99
    Samples
    0.92
     SAMPLES
    0.83
    Act Density 0.219%

    No Known Activations