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

    Neuronpedia

    INDEX
    Explanations

    instances of text-related commands or queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.72
    ########.
    -0.72
    utilisons
    -0.70
     Sopho
    -0.66
     Majefty
    -0.65
     joaat
    -0.65
    !("{
    -0.64
    InjectAttribute
    -0.63
    saraba
    -0.61
    ponses
    -0.61
    POSITIVE LOGITS
    <eos>
    0.79
     ...
    0.73
     ..."
    0.70
     […]
    0.68
    [...]
    0.64
    ↵
    0.64
     [...]
    0.61
    ↵↵
    0.59
     …
    0.58
    </blockquote>
    0.54
    Act Density 0.367%

    No Known Activations