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

    Neuronpedia

    INDEX
    Explanations

    specific sections or entities within articles, blogs, or reports

    oai_token-act-pair · gpt-3.5-turbo

    references to articles, reports, and posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibles
    -0.65
     Remain
    -0.61
    vae
    -0.60
    yrics
    -0.59
    ãĤ¨ãĥ«
    -0.58
     ingred
    -0.57
     Lover
    -0.57
     minorities
    -0.56
    Reloaded
    -0.56
     missiles
    -0.55
    POSITIVE LOGITS
    spot
    0.73
     GOODMAN
    0.71
    endix
    0.69
     affiliate
    0.68
    athon
    0.68
    chet
    0.67
    alysis
    0.67
    gha
    0.65
    bush
    0.64
    folio
    0.63
    Act Density 0.145%

    No Known Activations