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

    Neuronpedia

    INDEX
    Explanations

    terms related to filtering processes and filter components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sert
    -0.17
    isl
    -0.16
    yor
    -0.15
    olis
    -0.15
    ả
    -0.15
    nicas
    -0.15
    /gcc
    -0.15
    íĴĪ
    -0.14
    sm
    -0.14
    ually
    -0.14
    POSITIVE LOGITS
    edReader
    0.26
    edList
    0.24
    ë§ģ
    0.22
    edImage
    0.21
    ered
    0.21
    ation
    0.21
    able
    0.19
    åĻ¨
    0.19
    æİī
    0.19
    bank
    0.18
    Act Density 0.025%

    No Known Activations