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

    Neuronpedia

    INDEX
    Explanations

    texts referring to the publishing of written works and related material

    oai_token-act-pair · gpt-3.5-turbo

    references to publication dates and issues of magazines or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brute
    -0.69
     prototyp
    -0.68
     simulated
    -0.64
     consensual
    -0.63
     customs
    -0.63
     stereotypical
    -0.61
     lifeless
    -0.61
     stunts
    -0.61
     costly
    -0.60
     fingerprints
    -0.59
    POSITIVE LOGITS
     Subscribe
    1.10
    podcast
    1.01
    Reader
    0.99
     Readers
    0.99
    .]
    0.96
    Reviewer
    0.95
    Subscribe
    0.92
     archive
    0.87
     .)
    0.87
    blogs
    0.87
    Act Density 0.418%

    No Known Activations