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

    Neuronpedia

    INDEX
    Explanations

    terminology related to filters and filtering processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ả
    -0.16
     hollow
    -0.16
    lish
    -0.15
    nicas
    -0.15
    uci
    -0.15
    íĴĪ
    -0.14
    ulet
    -0.14
    sert
    -0.14
    LIB
    -0.14
    nicos
    -0.14
    POSITIVE LOGITS
    edReader
    0.25
    edList
    0.22
    /filter
    0.21
    edImage
    0.21
    able
    0.20
    .Filter
    0.20
    _SANITIZE
    0.20
    ë§ģ
    0.19
    æİī
    0.19
    .Filters
    0.18
    Act Density 0.037%

    No Known Activations