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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the creation or establishment of something new or reform

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "new."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammers
    -0.74
    lees
    -0.71
    isters
    -0.68
    Zip
    -0.68
    umes
    -0.68
    enance
    -0.68
    tics
    -0.67
    WARE
    -0.67
    warts
    -0.66
    abouts
    -0.66
    POSITIVE LOGITS
    bie
    1.14
    foundland
    1.00
     batch
    0.97
     generation
    0.93
     edition
    0.89
     iteration
    0.87
     impetus
    0.86
     wave
    0.83
    bies
    0.82
     testament
    0.80
    Act Density 0.068%

    No Known Activations