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

    Neuronpedia

    INDEX
    Explanations

    opinions and critical statements related to social and economic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "a," "his," or "the" preceding "letter" or "motion."

    np_acts-logits-general · gemini-2.0-flash

    writing letters or to whom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.78
     opérés
    -0.77
    хьтан
    -0.76
    UrlResolution
    -0.73
     autorytatywna
    -0.65
    الإنجليزية
    -0.65
     onCancelled
    -0.65
     ujednoznacz
    -0.63
     DbSet
    -0.63
    AsUp
    -0.60
    POSITIVE LOGITS
     letter
    2.13
    letter
    1.66
     letters
    1.66
     Letter
    1.66
    Letter
    1.60
     lettre
    1.54
     LETTER
    1.50
     lettera
    1.40
    LETTER
    1.38
     Letters
    1.36
    Act Density 0.420%

    No Known Activations