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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "remember" or related terms indicating recall of past experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ichert
    -0.16
    .appspot
    -0.15
    imary
    -0.15
    ixin
    -0.14
     known
    -0.14
    avanaugh
    -0.14
    ät
    -0.14
    gett
    -0.14
    ort
    -0.14
    issen
    -0.13
    POSITIVE LOGITS
     being
    0.16
    Ùĩد
    0.15
    (dtype
    0.15
    ube
    0.15
    (:,:,
    0.14
     how
    0.14
     marked
    0.14
    ardless
    0.14
    ãģĤãĤĭ
    0.14
     having
    0.13
    Act Density 0.028%

    No Known Activations