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

    Neuronpedia

    INDEX
    Explanations

    words related to comparison with other entities

    oai_token-act-pair · gpt-3.5-turbo

    references to alternative groups or entities in a context of comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ç¥ŀ
    -0.67
    zai
    -0.64
    ffee
    -0.64
     Retrieved
    -0.63
     Bride
    -0.63
     1915
    -0.61
    aucus
    -0.60
    ony
    -0.60
     THESE
    -0.59
    ctor
    -0.59
    POSITIVE LOGITS
    worldly
    1.90
     kinds
    1.01
     countries
    1.00
     aspects
    0.99
     peoples
    0.92
     types
    0.91
     nations
    0.88
     faiths
    0.87
     forms
    0.87
     disciplines
    0.87
    Act Density 0.099%

    No Known Activations