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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating summarization or commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    remember
    -0.16
     remember
    -0.15
    sov
    -0.15
    rvine
    -0.15
    edin
    -0.14
    icina
    -0.14
    iasi
    -0.14
    Ħĸ
    -0.14
    elden
    -0.14
    ãĥ¬ãĥĥãĥĪ
    -0.14
    POSITIVE LOGITS
     describe
    0.19
     explain
    0.18
     correct
    0.17
     tell
    0.17
     Tell
    0.17
     descri
    0.17
    Tell
    0.17
    Describe
    0.16
     Describe
    0.16
     Explain
    0.15
    Act Density 0.072%

    No Known Activations