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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sdale
    -0.07
    /or
    -0.07
    gth
    -0.06
    å®ħ
    -0.06
    oit
    -0.06
    anto
    -0.06
    asmus
    -0.06
    ufact
    -0.06
    md
    -0.06
    /Gate
    -0.06
    POSITIVE LOGITS
    adays
    0.08
     instead
    0.07
    instead
    0.07
    657
    0.07
     mere
    0.06
    758
    0.06
    lesi
    0.06
    arde
    0.06
    805
    0.06
    aden
    0.06
    Act Density 0.006%

    No Known Activations