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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "normally" and related phrases indicating regularity or frequency of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recently
    -0.17
    ilst
    -0.17
    errat
    -0.16
    llib
    -0.15
     recent
    -0.15
    recent
    -0.15
     originally
    -0.14
    zeÅĦ
    -0.14
    ats
    -0.14
    avour
    -0.14
    POSITIVE LOGITS
     reserved
    0.19
     would
    0.18
     RESERVED
    0.17
     Would
    0.16
    ETO
    0.16
    kup
    0.16
    Handled
    0.15
    would
    0.15
    ãģ§ãģĤ
    0.14
     wouldn
    0.14
    Act Density 0.060%

    No Known Activations