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

    Neuronpedia

    INDEX
    Explanations

    words that are typically abbreviations or initials

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases containing abbreviations or initials followed by a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĵĺ
    -0.79
    ancies
    -0.65
    itives
    -0.63
    rador
    -0.62
    onies
    -0.59
    naire
    -0.59
    naires
    -0.58
    ariat
    -0.58
     Mechdragon
    -0.58
    itsch
    -0.57
    POSITIVE LOGITS
    J
    0.76
    RIC
    0.75
    vantage
    0.71
    pillar
    0.70
    Bs
    0.69
     Lange
    0.68
    pex
    0.67
    k
    0.66
    wa
    0.66
    ccording
    0.66
    Act Density 0.020%

    No Known Activations