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

    Neuronpedia

    INDEX
    Explanations

    URL links within text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "link" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅŁ
    -0.63
    hma
    -0.61
     Liberties
    -0.58
    quez
    -0.57
    nces
    -0.56
     Palest
    -0.56
    FUL
    -0.54
     valued
    -0.54
    bered
    -0.53
    oplan
    -0.53
    POSITIVE LOGITS
    edin
    1.40
    ages
    1.10
    later
    1.09
    witz
    0.93
    within
    0.82
    erd
    0.82
     thereto
    0.73
    age
    0.73
    yll
    0.73
    letter
    0.72
    Act Density 0.057%

    No Known Activations