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

    Neuronpedia

    INDEX
    Explanations

    the use of conjunctions and the occurrence of lists or sequences in text

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

    and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     féminin
    -0.39
     financieras
    -0.38
     chinois
    -0.38
     løpet
    -0.35
     griego
    -0.35
     asiatique
    -0.34
     literario
    -0.33
     Grüsse
    -0.33
     féminine
    -0.33
     desconocido
    -0.33
    POSITIVE LOGITS
    webf
    0.51
    omotor
    0.50
    aarrggbb
    0.50
     Basso
    0.50
    titch
    0.50
     incrí
    0.49
    spun
    0.48
     WIRE
    0.48
    ragment
    0.47
    ddress
    0.47
    Act Density 0.055%

    No Known Activations