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

    Neuronpedia

    INDEX
    Explanations

    nouns and specialized terms related to academia or literature discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arro
    -0.19
    以
    -0.15
    ernational
    -0.14
    ivel
    -0.14
     DIY
    -0.14
    ayo
    -0.14
    acco
    -0.14
     pok
    -0.13
    Ãł
    -0.13
    erra
    -0.13
    POSITIVE LOGITS
    vil
    0.17
    .scalablytyped
    0.17
    nev
    0.17
    unks
    0.15
    æµ´
    0.15
     crossorigin
    0.15
    izedName
    0.15
    inspace
    0.15
    egrator
    0.15
    무
    0.14
    Act Density 0.264%

    No Known Activations