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

    Neuronpedia

    INDEX
    Explanations

    phrases or names related to a person's name "Wallace"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Wall" and "Wallace."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suscept
    -0.67
    urs
    -0.67
    Reloaded
    -0.67
    lihood
    -0.66
     Carbuncle
    -0.66
    Gene
    -0.65
     Norn
    -0.62
     Eug
    -0.61
    phrine
    -0.61
    vernment
    -0.61
    POSITIVE LOGITS
    abies
    1.53
    papers
    1.34
    aby
    1.22
    paper
    1.21
    clock
    0.99
    tops
    0.95
    top
    0.94
    igan
    0.94
    acea
    0.91
    igans
    0.91
    Act Density 0.028%

    No Known Activations