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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases indicating past actions or events

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

    once + past action or statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    通常
    -0.32
    Panamoan
    -0.31
     иногда
    -0.30
     soms
    -0.30
    まず
    -0.30
     jederzeit
    -0.29
     artık
    -0.29
    PerformLayout
    -0.28
     teraz
    -0.28
    まずは
    -0.28
    POSITIVE LOGITS
     again
    0.86
    +#+
    0.77
    Again
    0.68
     nahilalakip
    0.68
     zwiſchen
    0.64
     zuſammen
    0.63
     utafitiHapana
    0.63
    enablog
    0.63
     Again
    0.62
    OGND
    0.62
    Act Density 0.006%

    No Known Activations