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

    Neuronpedia

    INDEX
    Explanations

    titles of academic papers or articles

    oai_token-act-pair · gpt-3.5-turbo

    citations and references to academic works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azo
    -0.81
    yrim
    -0.78
    bryce
    -0.78
    iously
    -0.75
    ambo
    -0.69
    azon
    -0.68
    uchin
    -0.68
    heny
    -0.67
    irted
    -0.67
    haps
    -0.66
    POSITIVE LOGITS
     constant
    0.83
     ÙĪ
    0.78
     Sabha
    0.75
    Output
    0.74
     NCT
    0.68
     IDF
    0.66
     Expend
    0.63
    Services
    0.60
    noon
    0.59
    Solution
    0.59
    Act Density 0.000%

    No Known Activations