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

    Neuronpedia

    INDEX
    Explanations

    words related to filters or filtering

    oai_token-act-pair · gpt-3.5-turbo

    references to filtering mechanisms or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eanor
    -0.78
    nee
    -0.77
    DAY
    -0.69
    pered
    -0.68
    olars
    -0.68
    retch
    -0.66
    erald
    -0.66
    eworld
    -0.64
    NAS
    -0.63
    AAAAAAAA
    -0.63
    POSITIVE LOGITS
     filters
    1.04
     filtering
    1.03
     filter
    0.98
     Filter
    0.93
    filter
    0.86
     cleaners
    0.83
     cutoff
    0.81
     pores
    0.80
     filtered
    0.77
     capacitor
    0.73
    Act Density 0.013%

    No Known Activations