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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gam
    -0.17
    .spawn
    -0.16
     LAS
    -0.15
     GAM
    -0.15
     gam
    -0.15
     SAS
    -0.14
    urat
    -0.14
     McCartney
    -0.14
     Bing
    -0.14
    geist
    -0.14
    POSITIVE LOGITS
    omaly
    0.18
     dual
    0.18
    ories
    0.16
    Dual
    0.16
     Dual
    0.16
    uluk
    0.16
     Myers
    0.16
     theories
    0.16
    SYM
    0.15
    akov
    0.15
    Act Density 0.027%

    No Known Activations