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

    Neuronpedia

    INDEX
    Explanations

    references to memories and their significance

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

    memories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ɵɵ
    -0.40
    ран
    -0.40
    脚注の使い方
    -0.40
    thor
    -0.39
    ++.
    -0.38
    prefixer
    -0.37
     ​
    -0.37
     initi
    -0.37
    èlement
    -0.37
    UCE
    -0.36
    POSITIVE LOGITS
     miniaturka
    0.56
     ricordo
    0.55
     recuerdo
    0.54
    forgettable
    0.54
     myſelf
    0.52
     Erinnerung
    0.49
     herinner
    0.49
     memories
    0.49
     unforgettable
    0.48
     mauva
    0.47
    Act Density 0.010%

    No Known Activations