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

    Neuronpedia

    INDEX
    Explanations

    terms related to filtering processes or mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nicas
    -0.16
    ả
    -0.16
    nicos
    -0.15
    íĴĪ
    -0.15
    sert
    -0.15
    ftar
    -0.15
    ening
    -0.15
    lish
    -0.14
     hollow
    -0.14
    qid
    -0.14
    POSITIVE LOGITS
    edReader
    0.25
    edImage
    0.23
    edList
    0.21
    _SANITIZE
    0.20
    ation
    0.20
    .Filter
    0.19
    banks
    0.19
    ë§ģ
    0.19
    able
    0.18
    æİī
    0.18
    Act Density 0.026%

    No Known Activations