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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "covered" along with associated descriptions or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asco
    -0.15
    icl
    -0.15
     cụ
    -0.14
    ergency
    -0.14
     Mandarin
    -0.14
    ette
    -0.14
    ä¼´
    -0.13
    ett
    -0.13
    ad
    -0.13
    ι
    -0.13
    POSITIVE LOGITS
     layer
    0.17
    ksi
    0.16
    odash
    0.15
    -cover
    0.15
    nda
    0.15
    _STRUCT
    0.14
    eyen
    0.14
    apy
    0.14
    .gwt
    0.14
     cover
    0.14
    Act Density 0.052%

    No Known Activations