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

    Neuronpedia

    INDEX
    Explanations

    phrases where one thing is more significant or powerful than another

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to comparison and dominance in terms of quantity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lear
    -0.73
    cius
    -0.65
     BRA
    -0.60
    azel
    -0.59
     Renew
    -0.59
    alien
    -0.59
    oker
    -0.58
     cradle
    -0.58
    pring
    -0.58
     Directors
    -0.58
    POSITIVE LOGITS
    ighed
    1.29
     outweigh
    0.97
    ĺħ
    0.89
    ¿½
    0.86
     outwe
    0.85
    00200000
    0.77
    onent
    0.74
    200000
    0.74
    ĸļ
    0.73
    swer
    0.71
    Act Density 0.019%

    No Known Activations