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

    Neuronpedia

    INDEX
    Explanations

    references to academic or journalistic articles

    oai_token-act-pair · gpt-3.5-turbo

    references to journals or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holders
    -0.68
    creen
    -0.67
    minus
    -0.66
     Pric
    -0.63
     brightly
    -0.62
    FUL
    -0.62
     theirs
    -0.60
     ours
    -0.59
    dh
    -0.57
    YC
    -0.57
    POSITIVE LOGITS
    ists
    1.08
    ist
    1.04
    istic
    1.03
    ism
    1.01
    ournals
    1.00
    osphere
    0.99
    istically
    0.97
     Sentinel
    0.91
     Editors
    0.91
    ic
    0.88
    Act Density 0.028%

    No Known Activations