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

    Neuronpedia

    INDEX
    Explanations

    country names or words related to country origin

    oai_token-act-pair · gpt-3.5-turbo

    references to countries and geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ij士
    -0.69
    HAEL
    -0.61
    ICAN
    -0.59
    kefeller
    -0.59
    imity
    -0.58
    acea
    -0.56
    ÃĥÃĤÃĥÃĤ
    -0.56
     Pwr
    -0.56
    PDATE
    -0.56
    isSpecial
    -0.54
    POSITIVE LOGITS
    oslav
    0.68
    achus
    0.63
    hler
    0.60
    urat
    0.60
    lde
    0.59
     Telescope
    0.59
    utsche
    0.58
     Indies
    0.57
     Poles
    0.57
    together
    0.57
    Act Density 1.053%

    No Known Activations