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

    Neuronpedia

    INDEX
    Explanations

    proper names or titles that are influential or important

    oai_token-act-pair · gpt-3.5-turbo

    terms related to influential individuals or entities in various industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nance
    -0.70
    sterdam
    -0.67
    anium
    -0.67
    ©¶æ
    -0.65
    tein
    -0.62
    pleting
    -0.59
     LIFE
    -0.59
    othy
    -0.59
    clusive
    -0.58
     Reincarn
    -0.57
    POSITIVE LOGITS
    姫
    0.75
    doms
    0.71
     alike
    0.70
     Flavoring
    0.70
     within
    0.69
    acements
    0.68
    wcs
    0.68
     influ
    0.66
    stood
    0.66
     behind
    0.65
    Act Density 0.124%

    No Known Activations