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

    Neuronpedia

    INDEX
    Explanations

    words related to blog and blog titles

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "gog" or related terms in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.73
    ensional
    -0.62
    IDENT
    -0.59
    wcs
    -0.59
     capsule
    -0.59
     inadequ
    -0.58
     Witnesses
    -0.58
     competitors
    -0.56
     calculus
    -0.55
     laps
    -0.55
    POSITIVE LOGITS
    roup
    1.27
    roups
    1.23
    allery
    1.18
    gers
    1.11
    gy
    1.10
    gin
    1.09
    ues
    1.09
    glers
    1.08
    uchi
    1.02
    raf
    1.02
    Act Density 0.027%

    No Known Activations