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

    Neuronpedia

    INDEX
    Explanations

    words related to lists

    oai_token-act-pair · gpt-3.5-turbo

    lists or categories of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matter
    -0.82
    acus
    -0.82
    edin
    -0.80
    mpeg
    -0.78
    jong
    -0.75
    é¾įåĸļ士
    -0.75
    umption
    -0.74
    ester
    -0.72
    iber
    -0.72
    poke
    -0.69
    POSITIVE LOGITS
     allowable
    1.07
     accomplishments
    1.00
     grievances
    1.00
     acceptable
    0.92
     occupations
    0.92
     possible
    0.90
     permissible
    0.90
     possibilities
    0.90
     endorsements
    0.90
     endors
    0.88
    Act Density 0.148%

    No Known Activations