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

    Neuronpedia

    INDEX
    Explanations

    references to publication details and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RH
    -0.17
    mdb
    -0.16
     RH
    -0.15
    lah
    -0.14
    ãĥ¼ãĥĢ
    -0.14
    oog
    -0.14
    ernes
    -0.14
    arin
    -0.14
    ог
    -0.14
    WebpackPlugin
    -0.13
    POSITIVE LOGITS
     synthetic
    0.16
    enas
    0.16
     pus
    0.16
    .nlm
    0.15
    annon
    0.15
    apest
    0.15
    ideon
    0.15
    chalk
    0.14
     dispatch
    0.14
    ->
    0.14
    Act Density 0.003%

    No Known Activations