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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a public or official announcement

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "re."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kissinger
    -0.66
     lapt
    -0.65
     Seah
    -0.64
     Engel
    -0.63
    BuyableInstoreAndOnline
    -0.63
     Mayer
    -0.62
     Poc
    -0.61
     Ukrain
    -0.60
     Bernstein
    -0.58
    VERTISEMENT
    -0.58
    POSITIVE LOGITS
    ngth
    1.04
    selves
    1.04
    versible
    0.87
    aper
    0.86
    apers
    0.83
    joice
    0.83
    becca
    0.79
    ploy
    0.78
     gonna
    0.77
    agine
    0.76
    Act Density 0.038%

    No Known Activations