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

    Neuronpedia

    INDEX
    Explanations

    titles or references to magazines

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various magazines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    private
    -0.71
    ETA
    -0.67
    cession
    -0.65
    posed
    -0.65
    none
    -0.65
    comes
    -0.65
    acted
    -0.63
    gotten
    -0.63
     troubled
    -0.62
    haul
    -0.62
    POSITIVE LOGITS
     Magazine
    1.29
    Magazine
    1.09
    azines
    1.09
    azine
    1.08
     magazine
    1.05
     magazines
    0.98
     Seym
    0.93
     Journals
    0.87
     Bullets
    0.87
    clip
    0.83
    Act Density 0.010%

    No Known Activations