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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the" and related phrases emphasizing its recurrence in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inci
    -0.15
    Äįem
    -0.15
    azzi
    -0.14
    acci
    -0.14
     DeÄŁer
    -0.14
    rito
    -0.13
     gram
    -0.13
     respective
    -0.13
     respectively
    -0.13
    hi
    -0.13
    POSITIVE LOGITS
    oret
    0.19
    issant
    0.16
     cui
    0.15
     result
    0.15
    зна
    0.14
    ories
    0.14
    geme
    0.14
    ãĤĪãģ³
    0.14
     equivalent
    0.14
     sooner
    0.14
    Act Density 0.099%

    No Known Activations