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

    Neuronpedia

    INDEX
    Explanations

    words related to country-specific languages, such as German or Swedish, including character combinations specific to those languages

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "n" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reconc
    -0.70
    CVE
    -0.70
     misunder
    -0.66
    AMD
    -0.63
    allows
    -0.62
     clipping
    -0.61
     Pengu
    -0.61
     percentages
    -0.59
     warr
    -0.58
     occas
    -0.58
    POSITIVE LOGITS
    én
    0.93
    rique
    0.92
    rica
    0.91
    ÃŃn
    0.90
    ér
    0.89
    ée
    0.86
    Ä
    0.83
    iste
    0.83
    á
    0.81
    nel
    0.80
    Act Density 0.135%

    No Known Activations