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

    Neuronpedia

    INDEX
    Explanations

    words related to brackets or categorization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bracket" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.68
     Soy
    -0.66
    ternity
    -0.63
    uv
    -0.63
    BuyableInstoreAndOnline
    -0.60
     Traffic
    -0.59
    BLIC
    -0.59
     Antar
    -0.59
     Republic
    -0.57
    ULT
    -0.57
    POSITIVE LOGITS
     brackets
    1.33
     bracket
    1.30
    ackets
    1.16
    acket
    1.01
    halla
    0.75
    ashtra
    0.75
    cake
    0.73
    ftime
    0.71
    alon
    0.71
    olson
    0.70
    Act Density 0.013%

    No Known Activations