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

    Neuronpedia

    INDEX
    Explanations

    words related to packing or bundling items together

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "pack" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iott
    -0.70
    answered
    -0.67
    icut
    -0.66
     Monroe
    -0.65
    mediated
    -0.64
    akespeare
    -0.64
     Armen
    -0.64
    çIJ
    -0.63
     Armenian
    -0.63
    edu
    -0.62
    POSITIVE LOGITS
     pack
    3.99
     packs
    3.00
    pack
    2.56
     Pack
    2.42
     Packs
    2.23
    Pack
    2.21
    packs
    2.01
     PACK
    1.86
     packing
    1.70
     packed
    1.44
    Act Density 0.017%

    No Known Activations