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

    Neuronpedia

    INDEX
    Explanations

    the word "remember" and its variations, indicating a focus on recollection or memory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.86
    $")
    -0.86
    $.
    -0.81
    vidia
    -0.80
    Amicalement
    -0.70
    ?»
    -0.70
    britannien
    -0.69
    ⁎
    -0.68
    первых
    -0.65
     StatefulWidget
    -0.64
    POSITIVE LOGITS
     remember
    2.16
     remembers
    2.00
     REMEMBER
    2.00
     remembering
    1.93
     Remember
    1.91
     remembered
    1.89
    remember
    1.82
    Remember
    1.81
    Remembering
    1.51
     Remembering
    1.51
    Act Density 0.040%

    No Known Activations