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

    Neuronpedia

    INDEX
    Explanations

    the word "when" indicating temporal references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.41
     always
    -0.37
    soort
    -0.36
     ddelweddau
    -0.34
    oroz
    -0.32
     sempre
    -0.32
     Foote
    -0.31
     tab
    -0.31
     content
    -0.30
    حياته
    -0.30
    POSITIVE LOGITS
    󠁴
    0.71
     Numerade
    0.62
     GenerationType
    0.59
    новниш
    0.58
     hvor
    0.58
     where
    0.58
    GEBURTS
    0.58
     kdy
    0.57
    0.55
    oneph
    0.54
    Act Density 0.217%

    No Known Activations