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

    Neuronpedia

    INDEX
    Explanations

    the word "Cantonese"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or organization named "Cant" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¯¯¯¯¯¯¯¯
    -0.74
    Reviewer
    -0.73
    CVE
    -0.71
    PDATE
    -0.69
    ãģį
    -0.69
    senal
    -0.69
    ously
    -0.69
     unsur
    -0.68
    heads
    -0.66
     mosqu
    -0.62
    POSITIVE LOGITS
    illon
    1.14
    rell
    1.02
    onso
    0.98
    een
    0.92
    aleb
    0.91
    rip
    0.88
    lest
    0.85
    asia
    0.82
    esian
    0.81
    onal
    0.80
    Act Density 0.015%

    No Known Activations