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

    Neuronpedia

    INDEX
    Explanations

    words related to filters and filtering processes

    oai_token-act-pair · gpt-3.5-turbo

    references to filtering processes or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.82
    eanor
    -0.78
    nee
    -0.69
    retch
    -0.68
    olars
    -0.67
    peak
    -0.65
    lished
    -0.65
    roach
    -0.64
    SIGN
    -0.63
    ngth
    -0.63
    POSITIVE LOGITS
     filters
    0.87
     Filter
    0.82
    filter
    0.81
     filter
    0.80
     filtering
    0.78
     cutoff
    0.74
    operator
    0.74
    arette
    0.73
    inator
    0.72
     sweeps
    0.71
    Act Density 0.014%

    No Known Activations