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

    Neuronpedia

    INDEX
    Explanations

    expressions related to memory and lasting impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ()]
    -0.64
    łecz
    -0.59
    Viitteet
    -0.58
    Leary
    -0.57
    عی
    -0.54
    ();
    -0.54
    Referenties
    -0.53
    kjø
    -0.52
     bicara
    -0.52
     recently
    -0.52
    POSITIVE LOGITS
     forever
    0.93
     memories
    0.92
     memory
    0.90
    forever
    0.81
     unforgettable
    0.81
     Forever
    0.80
     FOREVER
    0.80
     indelible
    0.79
     remembers
    0.78
    memory
    0.77
    Act Density 0.153%

    No Known Activations