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

    Neuronpedia

    INDEX
    Explanations

    references to societal values and their consequences

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

    Punctuation followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    hoped and intended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ServletRequest
    -0.56
     متحده
    -0.52
    attuale
    -0.50
    uc
    -0.46
     limites
    -0.46
    <eos>
    -0.46
    AntiForgeryToken
    -0.45
    CORE
    -0.45
    ței
    -0.43
    IActionResult
    -0.43
    POSITIVE LOGITS
     supposed
    1.07
     promising
    1.04
     hoped
    1.02
    supposed
    0.95
     supposedly
    0.94
     promised
    0.91
     supuestamente
    0.83
     hopes
    0.81
     promises
    0.80
     promise
    0.80
    Act Density 0.440%

    No Known Activations