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

    Neuronpedia

    INDEX
    Explanations

    numeric data and statistical results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     uParam
    -0.85
    APORE
    -0.82
    er
    -0.82
    ing
    -0.80
    eret
    -0.78
     {!
    -0.77
     Solano
    -0.77
     Hause
    -0.77
     autrement
    -0.75
     Amigo
    -0.75
    POSITIVE LOGITS
     ± 
    1.56
     < 
    1.27
     × 
    1.16
     + 
    1.05
     = 
    0.98
     жив
    0.75
    )['
    0.73
    ± 
    0.73
    awtextra
    0.68
    chymal
    0.66
    Act Density 0.001%

    No Known Activations