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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation typically used in theoretical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lat
    -0.74
     "</
    -0.67
     gam
    -0.66
    tfrac
    -0.65
     bit
    -0.64
     szer
    -0.62
    sen
    -0.62
     fa
    -0.62
    apura
    -0.62
    vska
    -0.60
    POSITIVE LOGITS
    verwijspagina
    1.03
     Roskov
    0.94
     تكبرها
    0.91
    \}\\
    0.87
    ↵↵↵
    0.86
    ↵↵↵↵↵↵
    0.84
    ↵↵↵↵
    0.82
     ejus
    0.82
     Waikato
    0.80
     myeloma
    0.79
    Act Density 0.027%

    No Known Activations