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

    Neuronpedia

    INDEX
    Explanations

    specific dates and names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.70
    itiveness
    -0.66
    xual
    -0.63
    latable
    -0.59
    worldly
    -0.58
    imbabwe
    -0.57
    foundland
    -0.56
    ictive
    -0.55
    icrobial
    -0.54
    itionally
    -0.54
    POSITIVE LOGITS
    ornia
    0.64
    veland
    0.63
    emp
    0.59
    otom
    0.59
    thur
    0.58
    pora
    0.57
    ģĸ
    0.56
    llan
    0.56
     Bowser
    0.54
     Chao
    0.54
    Act Density 1.151%

    No Known Activations