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

    Neuronpedia

    INDEX
    Explanations

    identifiers or codes with a specific format containing the string "ID"

    oai_token-act-pair · gpt-3.5-turbo

    identifiers for various entities, possibly related to programming or database records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unborn
    -0.67
     outdoors
    -0.67
     woods
    -0.64
     Auburn
    -0.63
     Schl
    -0.63
     men
    -0.62
     Sai
    -0.61
     thro
    -0.61
     quarters
    -0.60
     rehe
    -0.60
    POSITIVE LOGITS
    ID
    4.10
    IDs
    3.02
    IDS
    2.49
    ids
    1.97
     ID
    1.95
    id
    1.92
    IDE
    1.76
     IDs
    1.73
    IDES
    1.71
    IDA
    1.71
    Act Density 0.008%

    No Known Activations